diff options
Diffstat (limited to 'monitoring')
81 files changed, 21235 insertions, 0 deletions
diff --git a/monitoring/ceph-mixin/.gitignore b/monitoring/ceph-mixin/.gitignore new file mode 100644 index 000000000..22d0d82f8 --- /dev/null +++ b/monitoring/ceph-mixin/.gitignore @@ -0,0 +1 @@ +vendor diff --git a/monitoring/ceph-mixin/.pylintrc b/monitoring/ceph-mixin/.pylintrc new file mode 120000 index 000000000..26d91e4cd --- /dev/null +++ b/monitoring/ceph-mixin/.pylintrc @@ -0,0 +1 @@ +../../src/pybind/mgr/dashboard/.pylintrc
\ No newline at end of file diff --git a/monitoring/ceph-mixin/CMakeLists.txt b/monitoring/ceph-mixin/CMakeLists.txt new file mode 100644 index 000000000..e63c740b7 --- /dev/null +++ b/monitoring/ceph-mixin/CMakeLists.txt @@ -0,0 +1,57 @@ +if(WITH_GRAFANA) + set(CEPH_GRAFANA_DASHBOARDS_DIR "${CMAKE_INSTALL_SYSCONFDIR}/grafana/dashboards/ceph-dashboard" + CACHE PATH "Location for grafana dashboards") + file(GLOB CEPH_GRAFANA_DASHBOARDS "dashboards_out/*.json") + install(FILES + ${CEPH_GRAFANA_DASHBOARDS} + DESTINATION ${CEPH_GRAFANA_DASHBOARDS_DIR}) + if(WITH_TESTS) + set(CEPH_BUILD_VIRTUALENV $ENV{TMPDIR}) + if(NOT CEPH_BUILD_VIRTUALENV) + include(AddCephTest) + set(CEPH_BUILD_VIRTUALENV ${CMAKE_BINARY_DIR}) + + add_test(NAME jsonnet-bundler-build + COMMAND ${CMAKE_CURRENT_SOURCE_DIR}/jsonnet-bundler-build.sh ${CMAKE_CURRENT_BINARY_DIR}) + set_property(TEST jsonnet-bundler-build PROPERTY + FIXTURES_SETUP jsonnet-bundler) + add_test(NAME jsonnet-bundler-cleanup + COMMAND rm -rf jsonnet-bundler ${CMAKE_CURRENT_BINARY_DIR}/jb) + set_property(TEST jsonnet-bundler-cleanup PROPERTY + FIXTURES_CLEANUP jsonnet-bundler) + + add_tox_test(grafana-lint TOX_ENVS lint) + add_tox_test(jsonnet-lint TOX_ENVS jsonnet-lint) + set_property(TEST run-tox-jsonnet-lint PROPERTY + FIXTURES_REQUIRED venv-for-jsonnet-lint) + add_tox_test(jsonnet-check TOX_ENVS jsonnet-check) + set_property(TEST run-tox-jsonnet-check PROPERTY + FIXTURES_REQUIRED venv-for-jsonnet-check jsonnet-bundler) + + add_tox_test(alerts-check TOX_ENVS alerts-check) + add_tox_test(alerts-lint TOX_ENVS alerts-lint) + add_tox_test(promql-query-test TOX_ENVS promql-query-test) + endif() + + if(DEFINED PROMTOOL_EXECUTABLE) + set(promtool_executable_checked TRUE) + endif() + + find_program(PROMTOOL_EXECUTABLE promtool) + if(PROMTOOL_EXECUTABLE) + execute_process( + COMMAND ${PROMTOOL_EXECUTABLE} test rules /dev/null + RESULT_VARIABLE rc + OUTPUT_QUIET) + if(NOT rc) + add_ceph_test(run-promtool-unittests + ${PROMTOOL_EXECUTABLE} test rules ${CMAKE_SOURCE_DIR}/monitoring/ceph-mixin/tests_alerts/test_alerts.yml) + elseif(NOT promtool_executable_checked) + message(WARNING "'${PROMTOOL_EXECUTABLE} test rules' does not work, " + "please use a newer prometheus") + endif() + elseif(NOT promtool_executable_checked) + message(WARNING "run-promtool-unittests is skipped due to missing promtool") + endif() + endif() +endif() diff --git a/monitoring/ceph-mixin/Makefile b/monitoring/ceph-mixin/Makefile new file mode 100644 index 000000000..0cb7aa539 --- /dev/null +++ b/monitoring/ceph-mixin/Makefile @@ -0,0 +1,24 @@ +all: fmt generate lint test + +fmt: + ./lint-jsonnet.sh -i + +generate: dashboards_out + +vendor: jsonnetfile.lock.json + tox -ejsonnet-bundler-install + +dashboards_out: vendor dashboards + tox -ejsonnet-fix + +lint: + tox -ejsonnet-lint + tox -ealerts-lint + +test: generate + tox -ejsonnet-check + tox -epromql-query-test + tox -ealerts-check +check: test + +.PHONY: all fmt generate lint test check diff --git a/monitoring/ceph-mixin/README.md b/monitoring/ceph-mixin/README.md new file mode 100644 index 000000000..477202193 --- /dev/null +++ b/monitoring/ceph-mixin/README.md @@ -0,0 +1,76 @@ +## Prometheus Monitoring Mixin for Ceph +A set of Grafana dashboards and Prometheus alerts for Ceph. + +All the Grafana dashboards are already generated in the `dashboards_out` +directory and alerts in the `prometheus_alerts.yml` file. + +You can use the Grafana dashboards and alerts with Jsonnet like any other +prometheus mixin. You can find more resources about mixins in general on +[monitoring.mixins.dev](https://monitoring.mixins.dev/). + +### Grafana dashboards for Ceph +In `dashboards_out` you can find a collection of +[Grafana](https://grafana.com/grafana) dashboards for Ceph Monitoring. + +These dashboards are based on metrics collected +from [prometheus](https://prometheus.io/) scraping the [prometheus mgr +plugin](http://docs.ceph.com/en/latest/mgr/prometheus/) and the +[node_exporter (0.17.0)](https://github.com/prometheus/node_exporter). + + +##### Recommended versions: +-grafana 8.3.5 + -grafana-piechart-panel 1.6.2 + -grafana-status-panel 1.0.11 + +#### Requirements + +- [Status Panel](https://grafana.com/plugins/vonage-status-panel) installed on + your Grafana instance +- [Pie Chart Panel](https://grafana.com/grafana/plugins/grafana-piechart-panel/) + installed on your Grafana instance + + +### Prometheus alerts +In `prometheus_alerts.libsonnet` you'll find a set of Prometheus +alert rules that should provide a decent set of default alerts for a +Ceph cluster. After building them with jsonnet put this file in place according to your Prometheus +configuration (wherever the `rules` configuration stanza points). + +### Multi-cluster support +Ceph-mixin supports dashboards and alerts across multiple clusters. +To enable this feature you need to configure the following in `config.libsonnnet`: + +``` +showMultiCluster: true, +clusterLabel: '<your cluster label>', +``` + +##### Recommended versions: +-prometheus v2.33.4 + +#### SNMP +Ceph provides a MIB (CEPH-PROMETHEUS-ALERT-MIB.txt) to support sending +Prometheus alerts to an SNMP management platform. The translation from +Prometheus alert to SNMP trap requires the Prometheus alert to contain an OID +that maps to a definition within the MIB. When making changes to the Prometheus +alert rules file, developers should include any necessary changes to the MIB. + + +##### Recommended: +-alertmanager 0.16.2 + +### Building from Jsonnet + +- Install [jsonnet](https://jsonnet.org/) (at least v0.18.0) + - By installing the package `jsonnet` in most of the distro and + `golang-github-google-jsonnet` in fedora +- Install [jsonnet-bundler](https://github.com/jsonnet-bundler/jsonnet-bundler) + +To rebuild all the generated files, you can run `tox -egrafonnet-fix`. + +The jsonnet code located in this directory depends on some Jsonnet third party +libraries. To update those libraries you can run `jb update` and then update +the generated files using `tox -egrafonnet-fix`. + +##### Any upgrade or downgrade to different major versions of the recommended tools mentioned above is not supported. diff --git a/monitoring/ceph-mixin/alerts.jsonnet b/monitoring/ceph-mixin/alerts.jsonnet new file mode 100644 index 000000000..43826eedd --- /dev/null +++ b/monitoring/ceph-mixin/alerts.jsonnet @@ -0,0 +1 @@ +std.manifestYamlDoc((import 'alerts.libsonnet').prometheusAlerts, indent_array_in_object=true, quote_keys=false) diff --git a/monitoring/ceph-mixin/alerts.libsonnet b/monitoring/ceph-mixin/alerts.libsonnet new file mode 100644 index 000000000..c2d39e2d3 --- /dev/null +++ b/monitoring/ceph-mixin/alerts.libsonnet @@ -0,0 +1,4 @@ +{ + prometheusAlerts+:: (import 'prometheus_alerts.libsonnet') + + { _config:: $._config }, +} diff --git a/monitoring/ceph-mixin/config.libsonnet b/monitoring/ceph-mixin/config.libsonnet new file mode 100644 index 000000000..7ee1210b0 --- /dev/null +++ b/monitoring/ceph-mixin/config.libsonnet @@ -0,0 +1,11 @@ +{ + _config+:: { + dashboardTags: ['ceph-mixin'], + + clusterLabel: 'cluster', + showMultiCluster: false, + + CephNodeNetworkPacketDropsThreshold: 0.005, + CephNodeNetworkPacketDropsPerSec: 10, + }, +} diff --git a/monitoring/ceph-mixin/dashboards.jsonnet b/monitoring/ceph-mixin/dashboards.jsonnet new file mode 100644 index 000000000..9d913ed3f --- /dev/null +++ b/monitoring/ceph-mixin/dashboards.jsonnet @@ -0,0 +1,6 @@ +local dashboards = (import 'mixin.libsonnet').grafanaDashboards; + +{ + [name]: dashboards[name] + for name in std.objectFields(dashboards) +} diff --git a/monitoring/ceph-mixin/dashboards.libsonnet b/monitoring/ceph-mixin/dashboards.libsonnet new file mode 100644 index 000000000..5cae18329 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards.libsonnet @@ -0,0 +1,10 @@ +{ + grafanaDashboards+:: + (import 'dashboards/cephfs.libsonnet') + + (import 'dashboards/host.libsonnet') + + (import 'dashboards/osd.libsonnet') + + (import 'dashboards/pool.libsonnet') + + (import 'dashboards/rbd.libsonnet') + + (import 'dashboards/rgw.libsonnet') + + { _config:: $._config }, +} diff --git a/monitoring/ceph-mixin/dashboards/cephfs.libsonnet b/monitoring/ceph-mixin/dashboards/cephfs.libsonnet new file mode 100644 index 000000000..d12d9f4dd --- /dev/null +++ b/monitoring/ceph-mixin/dashboards/cephfs.libsonnet @@ -0,0 +1,89 @@ +local g = import 'grafonnet/grafana.libsonnet'; + +(import 'utils.libsonnet') { + 'cephfs-overview.json': + $.dashboardSchema( + 'MDS Performance', + '', + 'tbO9LAiZz', + 'now-1h', + '30s', + 16, + $._config.dashboardTags, + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.3.2' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema('mds_servers', + '$datasource', + 'label_values(ceph_mds_inodes{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + true, + 1, + 'MDS Server', + '') + ) + .addPanels([ + $.addRowSchema(false, true, 'MDS Performance') + { gridPos: { x: 0, y: 0, w: 24, h: 1 } }, + $.simpleGraphPanel( + {}, + 'MDS Workload - $mds_servers', + '', + 'none', + 'Reads(-) / Writes (+)', + 0, + 'sum(rate(ceph_objecter_op_r{%(matchers)s, ceph_daemon=~"($mds_servers).*"}[$__rate_interval]))' % $.matchers(), + 'Read Ops', + 0, + 1, + 12, + 9 + ) + .addTarget($.addTargetSchema( + 'sum(rate(ceph_objecter_op_w{%(matchers)s, ceph_daemon=~"($mds_servers).*"}[$__rate_interval]))' % $.matchers(), + 'Write Ops' + )) + .addSeriesOverride( + { alias: '/.*Reads/', transform: 'negative-Y' } + ), + $.simpleGraphPanel( + {}, + 'Client Request Load - $mds_servers', + '', + 'none', + 'Client Requests', + 0, + 'ceph_mds_server_handle_client_request{%(matchers)s, ceph_daemon=~"($mds_servers).*"}' % $.matchers(), + '{{ceph_daemon}}', + 12, + 1, + 12, + 9 + ), + ]), +} diff --git a/monitoring/ceph-mixin/dashboards/host.libsonnet b/monitoring/ceph-mixin/dashboards/host.libsonnet new file mode 100644 index 000000000..4fd35c3ed --- /dev/null +++ b/monitoring/ceph-mixin/dashboards/host.libsonnet @@ -0,0 +1,748 @@ +local g = import 'grafonnet/grafana.libsonnet'; + +(import 'utils.libsonnet') { + 'hosts-overview.json': + $.dashboardSchema( + 'Host Overview', + '', + 'y0KGL0iZz', + 'now-1h', + '30s', + 16, + $._config.dashboardTags, + '', + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.3.2' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addRequired( + type='panel', id='singlestat', name='Singlestat', version='5.0.0' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addTemplate( + g.template.datasource('datasource', + 'prometheus', + 'default', + label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema('osd_hosts', + '$datasource', + 'label_values(ceph_disk_occupation{%(matchers)s}, exported_instance)' % $.matchers(), + 1, + true, + 1, + null, + '([^.]*).*') + ) + .addTemplate( + $.addTemplateSchema('mon_hosts', + '$datasource', + 'label_values(ceph_mon_metadata{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + true, + 1, + null, + 'mon.(.*)') + ) + .addTemplate( + $.addTemplateSchema('mds_hosts', + '$datasource', + 'label_values(ceph_mds_inodes{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + true, + 1, + null, + 'mds.(.*)') + ) + .addTemplate( + $.addTemplateSchema('rgw_hosts', + '$datasource', + 'label_values(ceph_rgw_metadata{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + true, + 1, + null, + 'rgw.(.*)') + ) + .addPanels([ + $.simpleSingleStatPanel( + 'none', + 'OSD Hosts', + '', + 'current', + 'count(sum by (hostname) (ceph_osd_metadata{%(matchers)s}))' % $.matchers(), + true, + 'time_series', + 0, + 0, + 4, + 5 + ), + $.simpleSingleStatPanel( + 'percentunit', + 'AVG CPU Busy', + 'Average CPU busy across all hosts (OSD, RGW, MON etc) within the cluster', + 'current', + ||| + avg(1 - ( + avg by(instance) ( + rate(node_cpu_seconds_total{mode='idle',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[$__rate_interval]) or + rate(node_cpu{mode='idle',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[$__rate_interval]) + ) + )) + |||, + true, + 'time_series', + 4, + 0, + 4, + 5 + ), + $.simpleSingleStatPanel( + 'percentunit', + 'AVG RAM Utilization', + 'Average Memory Usage across all hosts in the cluster (excludes buffer/cache usage)', + 'current', + ||| + avg (( + ( + node_memory_MemTotal{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or + node_memory_MemTotal_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} + ) - (( + node_memory_MemFree{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or + node_memory_MemFree_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}) + + ( + node_memory_Cached{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or + node_memory_Cached_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} + ) + ( + node_memory_Buffers{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or + node_memory_Buffers_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} + ) + ( + node_memory_Slab{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or + node_memory_Slab_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} + ) + ) + ) / ( + node_memory_MemTotal{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"} or + node_memory_MemTotal_bytes{instance=~"($osd_hosts|$rgw_hosts|$mon_hosts|$mds_hosts).*"} + )) + |||, + true, + 'time_series', + 8, + 0, + 4, + 5 + ), + $.simpleSingleStatPanel( + 'none', + 'Physical IOPS', + 'IOPS Load at the device as reported by the OS on all OSD hosts', + 'current', + ||| + sum (( + rate(node_disk_reads_completed{instance=~"($osd_hosts).*"}[$__rate_interval]) or + rate(node_disk_reads_completed_total{instance=~"($osd_hosts).*"}[$__rate_interval]) + ) + ( + rate(node_disk_writes_completed{instance=~"($osd_hosts).*"}[$__rate_interval]) or + rate(node_disk_writes_completed_total{instance=~"($osd_hosts).*"}[$__rate_interval]) + )) + |||, + true, + 'time_series', + 12, + 0, + 4, + 5 + ), + $.simpleSingleStatPanel( + 'percent', + 'AVG Disk Utilization', + 'Average Disk utilization for all OSD data devices (i.e. excludes journal/WAL)', + 'current', + ||| + avg ( + label_replace( + (rate(node_disk_io_time_ms[$__rate_interval]) / 10 ) or + (rate(node_disk_io_time_seconds_total[$__rate_interval]) * 100), + "instance", "$1", "instance", "([^.:]*).*" + ) * on(instance, device) group_left(ceph_daemon) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, instance=~"($osd_hosts).*"}, + "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^.:]*).*" + ) + ) + ||| % $.matchers(), + true, + 'time_series', + 16, + 0, + 4, + 5 + ), + $.simpleSingleStatPanel( + 'bytes', + 'Network Load', + 'Total send/receive network load across all hosts in the ceph cluster', + 'current', + ||| + sum ( + ( + rate(node_network_receive_bytes{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[$__rate_interval]) or + rate(node_network_receive_bytes_total{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[$__rate_interval]) + ) unless on (device, instance) + label_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)") + ) + + sum ( + ( + rate(node_network_transmit_bytes{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[$__rate_interval]) or + rate(node_network_transmit_bytes_total{instance=~"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*",device!="lo"}[$__rate_interval]) + ) unless on (device, instance) + label_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)") + ) + |||, + true, + 'time_series', + 20, + 0, + 4, + 5 + ), + $.simpleGraphPanel( + {}, + 'CPU Busy - Top 10 Hosts', + 'Show the top 10 busiest hosts by cpu', + 'percent', + null, + 0, + ||| + topk(10, + 100 * ( + 1 - ( + avg by(instance) ( + rate(node_cpu_seconds_total{mode='idle',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[$__rate_interval]) or + rate(node_cpu{mode='idle',instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*"}[$__rate_interval]) + ) + ) + ) + ) + |||, + '{{instance}}', + 0, + 5, + 12, + 9 + ), + $.simpleGraphPanel( + {}, + 'Network Load - Top 10 Hosts', + 'Top 10 hosts by network load', + 'Bps', + null, + 0, + ||| + topk(10, (sum by(instance) ( + ( + rate(node_network_receive_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[$__rate_interval]) or + rate(node_network_receive_bytes_total{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[$__rate_interval]) + ) + + ( + rate(node_network_transmit_bytes{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[$__rate_interval]) or + rate(node_network_transmit_bytes_total{instance=~"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*",device!="lo"}[$__rate_interval]) + ) unless on (device, instance) + label_replace((bonding_slaves > 0), "device", "$1", "master", "(.+)")) + )) + |||, + '{{instance}}', + 12, + 5, + 12, + 9 + ), + ]), + 'host-details.json': + $.dashboardSchema( + 'Host Details', + '', + 'rtOg0AiWz', + 'now-1h', + '30s', + 16, + $._config.dashboardTags + ['overview'], + '' + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.3.2' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addRequired( + type='panel', id='singlestat', name='Singlestat', version='5.0.0' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, '-- Grafana --', true, true, 'rgba(0, 211, 255, 1)', 'Annotations & Alerts', 'dashboard' + ) + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema('ceph_hosts', + '$datasource', + if $._config.showMultiCluster then ('label_values({%(clusterMatcher)s}, instance)' % $.matchers()) else 'label_values(instance)', + 1, + false, + 3, + 'Hostname', + '([^.:]*).*') + ) + .addPanels([ + $.addRowSchema(false, true, '$ceph_hosts System Overview') + { gridPos: { x: 0, y: 0, w: 24, h: 1 } }, + $.simpleSingleStatPanel( + 'none', + 'OSDs', + '', + 'current', + "count(sum by (ceph_daemon) (ceph_osd_metadata{%(matchers)s, hostname='$ceph_hosts'}))" % $.matchers(), + null, + 'time_series', + 0, + 1, + 3, + 5 + ), + $.simpleGraphPanel( + { + interrupt: '#447EBC', + steal: '#6D1F62', + system: '#890F02', + user: '#3F6833', + wait: '#C15C17', + }, + 'CPU Utilization', + "Shows the CPU breakdown. When multiple servers are selected, only the first host's cpu data is shown", + 'percent', + '% Utilization', + null, + ||| + sum by (mode) ( + rate(node_cpu{instance=~"($ceph_hosts)([\\\\.:].*)?", mode=~"(irq|nice|softirq|steal|system|user|iowait)"}[$__rate_interval]) or + rate(node_cpu_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?", mode=~"(irq|nice|softirq|steal|system|user|iowait)"}[$__rate_interval]) + ) / ( + scalar( + sum(rate(node_cpu{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_cpu_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval])) + ) * 100 + ) + |||, + '{{mode}}', + 3, + 1, + 6, + 10 + ), + $.simpleGraphPanel( + { + Available: '#508642', + Free: '#508642', + Total: '#bf1b00', + Used: '#bf1b00', + total: '#bf1b00', + used: '#0a50a1', + }, + 'RAM Usage', + '', + 'bytes', + 'RAM used', + null, + ||| + node_memory_MemFree{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_MemFree_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + |||, + 'Free', + 9, + 1, + 6, + 10 + ) + .addTargets( + [ + $.addTargetSchema( + ||| + node_memory_MemTotal{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_MemTotal_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + |||, + 'total' + ), + $.addTargetSchema( + ||| + ( + node_memory_Cached{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_Cached_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) + ( + node_memory_Buffers{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_Buffers_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) + ( + node_memory_Slab{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_Slab_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) + |||, + 'buffers/cache' + ), + $.addTargetSchema( + ||| + ( + node_memory_MemTotal{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_MemTotal_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) - ( + ( + node_memory_MemFree{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_MemFree_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) + ( + node_memory_Cached{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_Cached_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) + ( + node_memory_Buffers{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_Buffers_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) + + ( + node_memory_Slab{instance=~"$ceph_hosts([\\\\.:].*)?"} or + node_memory_Slab_bytes{instance=~"$ceph_hosts([\\\\.:].*)?"} + ) + ) + |||, + 'used' + ), + ] + ) + .addSeriesOverride( + { + alias: 'total', + color: '#bf1b00', + fill: 0, + linewidth: 2, + stack: false, + } + ), + $.simpleGraphPanel( + {}, + 'Network Load', + "Show the network load (rx,tx) across all interfaces (excluding loopback 'lo')", + 'decbytes', + 'Send (-) / Receive (+)', + null, + ||| + sum by (device) ( + rate( + node_network_receive_bytes{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[$__rate_interval]) or + rate(node_network_receive_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[$__rate_interval] + ) + ) + |||, + '{{device}}.rx', + 15, + 1, + 6, + 10 + ) + .addTargets( + [ + $.addTargetSchema( + ||| + sum by (device) ( + rate(node_network_transmit_bytes{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[$__rate_interval]) or + rate(node_network_transmit_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?",device!="lo"}[$__rate_interval]) + ) + |||, + '{{device}}.tx' + ), + ] + ) + .addSeriesOverride( + { alias: '/.*tx/', transform: 'negative-Y' } + ), + $.simpleGraphPanel( + {}, + 'Network drop rate', + '', + 'pps', + 'Send (-) / Receive (+)', + null, + ||| + rate(node_network_receive_drop{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_network_receive_drop_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) + |||, + '{{device}}.rx', + 21, + 1, + 3, + 5 + ) + .addTargets( + [ + $.addTargetSchema( + ||| + rate(node_network_transmit_drop{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_network_transmit_drop_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) + |||, + '{{device}}.tx' + ), + ] + ) + .addSeriesOverride( + { + alias: '/.*tx/', + transform: 'negative-Y', + } + ), + $.simpleSingleStatPanel( + 'bytes', + 'Raw Capacity', + 'Each OSD consists of a Journal/WAL partition and a data partition. The RAW Capacity shown is the sum of the data partitions across all OSDs on the selected OSD hosts.', + 'current', + ||| + sum( + ceph_osd_stat_bytes{%(matchers)s} and + on (ceph_daemon) ceph_disk_occupation{%(matchers)s, instance=~"($ceph_hosts)([\\\\.:].*)?"} + ) + ||| % $.matchers(), + null, + 'time_series', + 0, + 6, + 3, + 5 + ), + $.simpleGraphPanel( + {}, + 'Network error rate', + '', + 'pps', + 'Send (-) / Receive (+)', + null, + ||| + rate(node_network_receive_errs{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_network_receive_errs_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) + |||, + '{{device}}.rx', + 21, + 6, + 3, + 5 + ) + .addTargets( + [$.addTargetSchema( + ||| + rate(node_network_transmit_errs{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_network_transmit_errs_total{instance=~"$ceph_hosts([\\\\.:].*)?"}[$__rate_interval]) + |||, + '{{device}}.tx' + )] + ) + .addSeriesOverride( + { + alias: '/.*tx/', + transform: 'negative-Y', + } + ), + $.addRowSchema(false, + true, + 'OSD Disk Performance Statistics') + { gridPos: { x: 0, y: 11, w: 24, h: 1 } }, + $.simpleGraphPanel( + {}, + '$ceph_hosts Disk IOPS', + "For any OSD devices on the host, this chart shows the iops per physical device. Each device is shown by it's name and corresponding OSD id value", + 'ops', + 'Read (-) / Write (+)', + null, + ||| + label_replace( + ( + rate(node_disk_writes_completed{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_disk_writes_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) + ), "instance", "$1", "instance", "([^:.]*).*" + ) * on(instance, device) group_left(ceph_daemon) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s}, "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}}({{ceph_daemon}}) writes', + 0, + 12, + 11, + 9 + ) + .addTargets( + [ + $.addTargetSchema( + ||| + label_replace( + ( + rate(node_disk_reads_completed{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_disk_reads_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) + ), "instance", "$1", "instance", "([^:.]*).*" + ) * on(instance, device) group_left(ceph_daemon) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s},"device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}}({{ceph_daemon}}) reads' + ), + ] + ) + .addSeriesOverride( + { alias: '/.*reads/', transform: 'negative-Y' } + ), + $.simpleGraphPanel( + {}, + '$ceph_hosts Throughput by Disk', + 'For OSD hosts, this chart shows the disk bandwidth (read bytes/sec + write bytes/sec) of the physical OSD device. Each device is shown by device name, and corresponding OSD id', + 'Bps', + 'Read (-) / Write (+)', + null, + ||| + label_replace( + ( + rate(node_disk_bytes_written{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_disk_written_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) + ), "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) + group_left(ceph_daemon) label_replace( + label_replace(ceph_disk_occupation_human{%(matchers)s}, "device", "$1", "device", "/dev/(.*)"), + "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}}({{ceph_daemon}}) write', + 12, + 12, + 11, + 9 + ) + .addTargets( + [$.addTargetSchema( + ||| + label_replace( + ( + rate(node_disk_bytes_read{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) or + rate(node_disk_read_bytes_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) + ), + "instance", "$1", "instance", "([^:.]*).*") * on(instance, device) + group_left(ceph_daemon) label_replace( + label_replace(ceph_disk_occupation_human{%(matchers)s}, "device", "$1", "device", "/dev/(.*)"), + "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}}({{ceph_daemon}}) read' + )] + ) + .addSeriesOverride( + { alias: '/.*read/', transform: 'negative-Y' } + ), + $.simpleGraphPanel( + {}, + '$ceph_hosts Disk Latency', + "For OSD hosts, this chart shows the latency at the physical drive. Each drive is shown by device name, with it's corresponding OSD id", + 's', + '', + null, + ||| + max by(instance, device) (label_replace( + (rate(node_disk_write_time_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval])) / + clamp_min(rate(node_disk_writes_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]), 0.001) or + (rate(node_disk_read_time_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval])) / + clamp_min(rate(node_disk_reads_completed_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]), 0.001), + "instance", "$1", "instance", "([^:.]*).*" + )) * on(instance, device) group_left(ceph_daemon) label_replace( + label_replace( + ceph_disk_occupation_human{instance=~"($ceph_hosts)([\\\\.:].*)?"}, + "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}}({{ceph_daemon}})', + 0, + 21, + 11, + 9 + ), + $.simpleGraphPanel( + {}, + '$ceph_hosts Disk utilization', + 'Show disk utilization % (util) of any OSD devices on the host by the physical device name and associated OSD id.', + 'percent', + '%Util', + null, + ||| + label_replace( + ( + (rate(node_disk_io_time_ms{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) / 10) or + rate(node_disk_io_time_seconds_total{instance=~"($ceph_hosts)([\\\\.:].*)?"}[$__rate_interval]) * 100 + ), "instance", "$1", "instance", "([^:.]*).*" + ) * on(instance, device) group_left(ceph_daemon) label_replace( + label_replace(ceph_disk_occupation_human{%(matchers)s, instance=~"($ceph_hosts)([\\\\.:].*)?"}, + "device", "$1", "device", "/dev/(.*)"), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}}({{ceph_daemon}})', + 12, + 21, + 11, + 9 + ), + $.addTableSchema( + '$datasource', + 'This table shows the 10 hosts with the highest number of slow ops', + { col: 2, desc: true }, + [ + $.overviewStyle('Instance', 'instance', 'string', 'short'), + $.overviewStyle('Slow Ops', 'Value', 'number', 'none'), + $.overviewStyle('', '/.*/', 'hidden', 'short'), + ], + 'Top Slow Ops per Host', + 'table' + ) + .addTarget( + $.addTargetSchema( + ||| + topk(10, + (sum by (instance)(ceph_daemon_health_metrics{type="SLOW_OPS", ceph_daemon=~"osd.*"})) + ) + ||| % $.matchers(), + '', + 'table', + 1, + true + ) + ) + { gridPos: { x: 0, y: 40, w: 4, h: 8 } }, + ]), +} diff --git a/monitoring/ceph-mixin/dashboards/osd.libsonnet b/monitoring/ceph-mixin/dashboards/osd.libsonnet new file mode 100644 index 000000000..0ea43c96f --- /dev/null +++ b/monitoring/ceph-mixin/dashboards/osd.libsonnet @@ -0,0 +1,618 @@ +local g = import 'grafonnet/grafana.libsonnet'; + +(import 'utils.libsonnet') { + 'osds-overview.json': + $.dashboardSchema( + 'OSD Overview', + '', + 'lo02I1Aiz', + 'now-1h', + '30s', + 16, + $._config.dashboardTags, + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.0.0' + ) + .addRequired( + type='panel', id='grafana-piechart-panel', name='Pie Chart', version='1.3.3' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addRequired( + type='panel', id='table', name='Table', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addPanels([ + $.simpleGraphPanel( + { '@95%ile': '#e0752d' }, + 'OSD Read Latencies', + '', + 'ms', + null, + '0', + ||| + avg ( + rate(ceph_osd_op_r_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_r_latency_count{%(matchers)s}[$__rate_interval]) * 1000 + ) + ||| % $.matchers(), + 'AVG read', + 0, + 0, + 8, + 8 + ) + .addTargets( + [ + $.addTargetSchema( + ||| + max( + rate(ceph_osd_op_r_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_r_latency_count{%(matchers)s}[$__rate_interval]) * 1000 + ) + ||| % $.matchers(), + 'MAX read' + ), + $.addTargetSchema( + ||| + quantile(0.95, + ( + rate(ceph_osd_op_r_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_r_latency_count{%(matchers)s}[$__rate_interval]) + * 1000 + ) + ) + ||| % $.matchers(), + '@95%ile' + ), + ], + ), + $.addTableSchema( + '$datasource', + "This table shows the osd's that are delivering the 10 highest read latencies within the cluster", + { col: 2, desc: true }, + [ + $.overviewStyle('OSD ID', 'ceph_daemon', 'string', 'short'), + $.overviewStyle('Latency (ms)', 'Value', 'number', 'none'), + $.overviewStyle('', '/.*/', 'hidden', 'short'), + ], + 'Highest READ Latencies', + 'table' + ) + .addTarget( + $.addTargetSchema( + ||| + topk(10, + (sort( + ( + rate(ceph_osd_op_r_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_r_latency_count{%(matchers)s}[$__rate_interval]) * + 1000 + ) + )) + ) + ||| % $.matchers(), + '', + 'table', + 1, + true + ) + ) + { gridPos: { x: 8, y: 0, w: 4, h: 8 } }, + $.simpleGraphPanel( + { + '@95%ile write': '#e0752d', + }, + 'OSD Write Latencies', + '', + 'ms', + null, + '0', + ||| + avg( + rate(ceph_osd_op_w_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_w_latency_count{%(matchers)s}[$__rate_interval]) + * 1000 + ) + ||| % $.matchers(), + 'AVG write', + 12, + 0, + 8, + 8 + ) + .addTargets( + [ + $.addTargetSchema( + ||| + max( + rate(ceph_osd_op_w_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_w_latency_count{%(matchers)s}[$__rate_interval]) * + 1000 + ) + ||| % $.matchers(), 'MAX write' + ), + $.addTargetSchema( + ||| + quantile(0.95, ( + rate(ceph_osd_op_w_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_w_latency_count{%(matchers)s}[$__rate_interval]) * + 1000 + )) + ||| % $.matchers(), '@95%ile write' + ), + ], + ), + $.addTableSchema( + '$datasource', + "This table shows the osd's that are delivering the 10 highest write latencies within the cluster", + { col: 2, desc: true }, + [ + $.overviewStyle( + 'OSD ID', 'ceph_daemon', 'string', 'short' + ), + $.overviewStyle('Latency (ms)', 'Value', 'number', 'none'), + $.overviewStyle('', '/.*/', 'hidden', 'short'), + ], + 'Highest WRITE Latencies', + 'table' + ) + .addTarget( + $.addTargetSchema( + ||| + topk(10, + (sort( + (rate(ceph_osd_op_w_latency_sum{%(matchers)s}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_w_latency_count{%(matchers)s}[$__rate_interval]) * + 1000) + )) + ) + ||| % $.matchers(), + '', + 'table', + 1, + true + ) + ) + { gridPos: { x: 20, y: 0, w: 4, h: 8 } }, + $.simplePieChart( + {}, '', 'OSD Types Summary' + ) + .addTarget( + $.addTargetSchema('count by (device_class) (ceph_osd_metadata{%(matchers)s})' % $.matchers(), '{{device_class}}') + ) + { gridPos: { x: 0, y: 8, w: 4, h: 8 } }, + $.simplePieChart( + { 'Non-Encrypted': '#E5AC0E' }, '', 'OSD Objectstore Types' + ) + .addTarget( + $.addTargetSchema( + 'count(ceph_bluefs_wal_total_bytes{%(matchers)s})' % $.matchers(), 'bluestore', 'time_series', 2 + ) + ) + .addTarget( + $.addTargetSchema( + 'absent(ceph_bluefs_wal_total_bytes{%(matchers)s}) * count(ceph_osd_metadata{%(matchers)s})' % $.matchers(), 'filestore', 'time_series', 2 + ) + ) + { gridPos: { x: 4, y: 8, w: 4, h: 8 } }, + $.simplePieChart( + {}, 'The pie chart shows the various OSD sizes used within the cluster', 'OSD Size Summary' + ) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} < 1099511627776)' % $.matchers(), '<1TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 1099511627776 < 2199023255552)' % $.matchers(), '<2TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 2199023255552 < 3298534883328)' % $.matchers(), '<3TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 3298534883328 < 4398046511104)' % $.matchers(), '<4TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 4398046511104 < 6597069766656)' % $.matchers(), '<6TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 6597069766656 < 8796093022208)' % $.matchers(), '<8TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 8796093022208 < 10995116277760)' % $.matchers(), '<10TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 10995116277760 < 13194139533312)' % $.matchers(), '<12TB', 'time_series', 2 + )) + .addTarget($.addTargetSchema( + 'count(ceph_osd_stat_bytes{%(matchers)s} >= 13194139533312)' % $.matchers(), '<12TB+', 'time_series', 2 + )) + { gridPos: { x: 8, y: 8, w: 4, h: 8 } }, + g.graphPanel.new(bars=true, + datasource='$datasource', + title='Distribution of PGs per OSD', + x_axis_buckets=20, + x_axis_mode='histogram', + x_axis_values=['total'], + formatY1='short', + formatY2='short', + labelY1='# of OSDs', + min='0', + nullPointMode='null') + .addTarget($.addTargetSchema( + 'ceph_osd_numpg{%(matchers)s}' % $.matchers(), 'PGs per OSD', 'time_series', 1, true + )) + { gridPos: { x: 12, y: 8, w: 8, h: 8 } }, + $.gaugeSingleStatPanel( + 'percentunit', + 'OSD onode Hits Ratio', + 'This gauge panel shows onode Hits ratio to help determine if increasing RAM per OSD could help improve the performance of the cluster', + 'current', + true, + 1, + true, + false, + '.75', + ||| + sum(ceph_bluestore_onode_hits{%(matchers)s}) / ( + sum(ceph_bluestore_onode_hits{%(matchers)s}) + + sum(ceph_bluestore_onode_misses{%(matchers)s}) + ) + ||| % $.matchers(), + 'time_series', + 20, + 8, + 4, + 8 + ), + $.addRowSchema(false, + true, + 'R/W Profile') + { gridPos: { x: 0, y: 16, w: 24, h: 1 } }, + $.simpleGraphPanel( + {}, + 'Read/Write Profile', + 'Show the read/write workload profile overtime', + 'short', + null, + null, + 'round(sum(rate(ceph_pool_rd{%(matchers)s}[$__rate_interval])))' % $.matchers(), + 'Reads', + 0, + 17, + 24, + 8 + ) + .addTargets([$.addTargetSchema( + 'round(sum(rate(ceph_pool_wr{%(matchers)s}[$__rate_interval])))' % $.matchers(), 'Writes' + )]), + $.addTableSchema( + '$datasource', + 'This table shows the 10 OSDs with the highest number of slow ops', + { col: 2, desc: true }, + [ + $.overviewStyle('OSD ID', 'ceph_daemon', 'string', 'short'), + $.overviewStyle('Slow Ops', 'Value', 'number', 'none'), + $.overviewStyle('', '/.*/', 'hidden', 'short'), + ], + 'Top Slow Ops', + 'table' + ) + .addTarget( + $.addTargetSchema( + ||| + topk(10, + (ceph_daemon_health_metrics{type="SLOW_OPS", ceph_daemon=~"osd.*"}) + ) + ||| % $.matchers(), + '', + 'table', + 1, + true + ) + ) + { gridPos: { x: 0, y: 20, w: 4, h: 8 } }, + ]), + 'osd-device-details.json': + local OsdDeviceDetailsPanel(title, + description, + formatY1, + labelY1, + expr1, + expr2, + legendFormat1, + legendFormat2, + x, + y, + w, + h) = + $.graphPanelSchema({}, + title, + description, + 'null', + false, + formatY1, + 'short', + labelY1, + null, + null, + 1, + '$datasource') + .addTargets( + [ + $.addTargetSchema(expr1, + legendFormat1), + $.addTargetSchema(expr2, legendFormat2), + ] + ) + { gridPos: { x: x, y: y, w: w, h: h } }; + + $.dashboardSchema( + 'OSD device details', + '', + 'CrAHE0iZz', + 'now-3h', + '30s', + 16, + $._config.dashboardTags, + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.3.2' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', + 'prometheus', + 'default', + label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema('osd', + '$datasource', + 'label_values(ceph_osd_metadata{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + false, + 1, + 'OSD', + '(.*)') + ) + .addPanels([ + $.addRowSchema( + false, true, 'OSD Performance' + ) + { gridPos: { x: 0, y: 0, w: 24, h: 1 } }, + OsdDeviceDetailsPanel( + '$osd Latency', + '', + 's', + 'Read (-) / Write (+)', + ||| + rate(ceph_osd_op_r_latency_sum{%(matchers)s, ceph_daemon=~"$osd"}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_r_latency_count{%(matchers)s}[$__rate_interval]) + ||| % $.matchers(), + ||| + rate(ceph_osd_op_w_latency_sum{%(matchers)s, ceph_daemon=~"$osd"}[$__rate_interval]) / + on (ceph_daemon) rate(ceph_osd_op_w_latency_count{%(matchers)s}[$__rate_interval]) + ||| % $.matchers(), + 'read', + 'write', + 0, + 1, + 6, + 9 + ) + .addSeriesOverride( + { + alias: 'read', + transform: 'negative-Y', + } + ), + OsdDeviceDetailsPanel( + '$osd R/W IOPS', + '', + 'short', + 'Read (-) / Write (+)', + 'rate(ceph_osd_op_r{%(matchers)s, ceph_daemon=~"$osd"}[$__rate_interval])' % $.matchers(), + 'rate(ceph_osd_op_w{%(matchers)s, ceph_daemon=~"$osd"}[$__rate_interval])' % $.matchers(), + 'Reads', + 'Writes', + 6, + 1, + 6, + 9 + ) + .addSeriesOverride( + { alias: 'Reads', transform: 'negative-Y' } + ), + OsdDeviceDetailsPanel( + '$osd R/W Bytes', + '', + 'bytes', + 'Read (-) / Write (+)', + 'rate(ceph_osd_op_r_out_bytes{%(matchers)s, ceph_daemon=~"$osd"}[$__rate_interval])' % $.matchers(), + 'rate(ceph_osd_op_w_in_bytes{%(matchers)s, ceph_daemon=~"$osd"}[$__rate_interval])' % $.matchers(), + 'Read Bytes', + 'Write Bytes', + 12, + 1, + 6, + 9 + ) + .addSeriesOverride({ alias: 'Read Bytes', transform: 'negative-Y' }), + $.addRowSchema( + false, true, 'Physical Device Performance' + ) + { gridPos: { x: 0, y: 10, w: 24, h: 1 } }, + OsdDeviceDetailsPanel( + 'Physical Device Latency for $osd', + '', + 's', + 'Read (-) / Write (+)', + ||| + ( + label_replace( + rate(node_disk_read_time_seconds_total{%(clusterMatcher)s}[$__rate_interval]) / + rate(node_disk_reads_completed_total{%(clusterMatcher)s}[$__rate_interval]), + "instance", "$1", "instance", "([^:.]*).*" + ) and on (instance, device) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, ceph_daemon=~"$osd"}, + "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ) + ||| % $.matchers(), + ||| + ( + label_replace( + rate(node_disk_write_time_seconds_total{%(clusterMatcher)s}[$__rate_interval]) / + rate(node_disk_writes_completed_total{%(clusterMatcher)s}[$__rate_interval]), + "instance", "$1", "instance", "([^:.]*).*") and on (instance, device) + label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ) + ||| % $.matchers(), + '{{instance}}/{{device}} Reads', + '{{instance}}/{{device}} Writes', + 0, + 11, + 6, + 9 + ) + .addSeriesOverride( + { alias: '/.*Reads/', transform: 'negative-Y' } + ), + OsdDeviceDetailsPanel( + 'Physical Device R/W IOPS for $osd', + '', + 'short', + 'Read (-) / Write (+)', + ||| + label_replace( + rate(node_disk_writes_completed_total{%(clusterMatcher)s}[$__rate_interval]), + "instance", "$1", "instance", "([^:.]*).*" + ) and on (instance, device) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, ceph_daemon=~"$osd"}, + "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + ||| + label_replace( + rate(node_disk_reads_completed_total{%(clusterMatcher)s}[$__rate_interval]), + "instance", "$1", "instance", "([^:.]*).*" + ) and on (instance, device) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, ceph_daemon=~"$osd"}, + "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}} on {{instance}} Writes', + '{{device}} on {{instance}} Reads', + 6, + 11, + 6, + 9 + ) + .addSeriesOverride( + { alias: '/.*Reads/', transform: 'negative-Y' } + ), + OsdDeviceDetailsPanel( + 'Physical Device R/W Bytes for $osd', + '', + 'Bps', + 'Read (-) / Write (+)', + ||| + label_replace( + rate(node_disk_read_bytes_total{%(clusterMatcher)s}[$__rate_interval]), "instance", "$1", "instance", "([^:.]*).*" + ) and on (instance, device) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, ceph_daemon=~"$osd"}, + "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + ||| + label_replace( + rate(node_disk_written_bytes_total{%(clusterMatcher)s}[$__rate_interval]), "instance", "$1", "instance", "([^:.]*).*" + ) and on (instance, device) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, ceph_daemon=~"$osd"}, + "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{instance}} {{device}} Reads', + '{{instance}} {{device}} Writes', + 12, + 11, + 6, + 9 + ) + .addSeriesOverride( + { alias: '/.*Reads/', transform: 'negative-Y' } + ), + $.graphPanelSchema( + {}, + 'Physical Device Util% for $osd', + '', + 'null', + false, + 'percentunit', + 'short', + null, + null, + null, + 1, + '$datasource' + ) + .addTarget($.addTargetSchema( + ||| + label_replace( + rate(node_disk_io_time_seconds_total{%(clusterMatcher)s}[$__rate_interval]), + "instance", "$1", "instance", "([^:.]*).*" + ) and on (instance, device) label_replace( + label_replace( + ceph_disk_occupation_human{%(matchers)s, ceph_daemon=~"$osd"}, "device", "$1", "device", "/dev/(.*)" + ), "instance", "$1", "instance", "([^:.]*).*" + ) + ||| % $.matchers(), + '{{device}} on {{instance}}' + )) + { gridPos: { x: 18, y: 11, w: 6, h: 9 } }, + ]), +} diff --git a/monitoring/ceph-mixin/dashboards/pool.libsonnet b/monitoring/ceph-mixin/dashboards/pool.libsonnet new file mode 100644 index 000000000..6444335d9 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards/pool.libsonnet @@ -0,0 +1,552 @@ +local g = import 'grafonnet/grafana.libsonnet'; + +(import 'utils.libsonnet') { + 'pool-overview.json': + $.dashboardSchema( + 'Ceph Pools Overview', + '', + 'z99hzWtmk', + 'now-1h', + '30s', + 22, + $._config.dashboardTags, + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + g.template.custom(label='TopK', + name='topk', + current='15', + query='15') + ) + .addPanels([ + $.simpleSingleStatPanel( + 'none', + 'Pools', + '', + 'avg', + 'count(ceph_pool_metadata{%(matchers)s})' % $.matchers(), + true, + 'table', + 0, + 0, + 3, + 3 + ), + $.simpleSingleStatPanel( + 'none', + 'Pools with Compression', + 'Count of the pools that have compression enabled', + 'current', + 'count(ceph_pool_metadata{%(matchers)s, compression_mode!="none"})' % $.matchers(), + null, + '', + 3, + 0, + 3, + 3 + ), + $.simpleSingleStatPanel( + 'bytes', + 'Total Raw Capacity', + 'Total raw capacity available to the cluster', + 'current', + 'sum(ceph_osd_stat_bytes{%(matchers)s})' % $.matchers(), + null, + '', + 6, + 0, + 3, + 3 + ), + $.simpleSingleStatPanel( + 'bytes', + 'Raw Capacity Consumed', + 'Total raw capacity consumed by user data and associated overheads (metadata + redundancy)', + 'current', + 'sum(ceph_pool_bytes_used{%(matchers)s})' % $.matchers(), + true, + '', + 9, + 0, + 3, + 3 + ), + $.simpleSingleStatPanel( + 'bytes', + 'Logical Stored ', + 'Total of client data stored in the cluster', + 'current', + 'sum(ceph_pool_stored{%(matchers)s})' % $.matchers(), + true, + '', + 12, + 0, + 3, + 3 + ), + $.simpleSingleStatPanel( + 'bytes', + 'Compression Savings', + 'A compression saving is determined as the data eligible to be compressed minus the capacity used to store the data after compression', + 'current', + ||| + sum( + ceph_pool_compress_under_bytes{%(matchers)s} - + ceph_pool_compress_bytes_used{%(matchers)s} + ) + ||| % $.matchers(), + null, + '', + 15, + 0, + 3, + 3 + ), + $.simpleSingleStatPanel( + 'percent', + 'Compression Eligibility', + 'Indicates how suitable the data is within the pools that are/have been enabled for compression - averaged across all pools holding compressed data', + 'current', + ||| + ( + sum(ceph_pool_compress_under_bytes{%(matchers)s} > 0) / + sum(ceph_pool_stored_raw{%(matchers)s} and ceph_pool_compress_under_bytes{%(matchers)s} > 0) + ) * 100 + ||| % $.matchers(), + null, + 'table', + 18, + 0, + 3, + 3 + ), + $.simpleSingleStatPanel( + 'none', + 'Compression Factor', + 'This factor describes the average ratio of data eligible to be compressed divided by the data actually stored. It does not account for data written that was ineligible for compression (too small, or compression yield too low)', + 'current', + ||| + sum( + ceph_pool_compress_under_bytes{%(matchers)s} > 0) + / sum(ceph_pool_compress_bytes_used{%(matchers)s} > 0 + ) + ||| % $.matchers(), + null, + '', + 21, + 0, + 3, + 3 + ), + $.addTableSchema( + '$datasource', + '', + { col: 5, desc: true }, + [ + $.overviewStyle('', 'Time', 'hidden', 'short'), + $.overviewStyle('', 'instance', 'hidden', 'short'), + $.overviewStyle('', 'job', 'hidden', 'short'), + $.overviewStyle('Pool Name', 'name', 'string', 'short'), + $.overviewStyle('Pool ID', 'pool_id', 'hidden', 'none'), + $.overviewStyle('Compression Factor', 'Value #A', 'number', 'none'), + $.overviewStyle('% Used', 'Value #D', 'number', 'percentunit', 'value', ['70', '85']), + $.overviewStyle('Usable Free', 'Value #B', 'number', 'bytes'), + $.overviewStyle('Compression Eligibility', 'Value #C', 'number', 'percent'), + $.overviewStyle('Compression Savings', 'Value #E', 'number', 'bytes'), + $.overviewStyle('Growth (5d)', 'Value #F', 'number', 'bytes', 'value', ['0', '0']), + $.overviewStyle('IOPS', 'Value #G', 'number', 'none'), + $.overviewStyle('Bandwidth', 'Value #H', 'number', 'Bps'), + $.overviewStyle('', '__name__', 'hidden', 'short'), + $.overviewStyle('', 'type', 'hidden', 'short'), + $.overviewStyle('', 'compression_mode', 'hidden', 'short'), + $.overviewStyle('Type', 'description', 'string', 'short'), + $.overviewStyle('Stored', 'Value #J', 'number', 'bytes'), + $.overviewStyle('', 'Value #I', 'hidden', 'short'), + $.overviewStyle('Compression', 'Value #K', 'string', 'short', null, [], [{ text: 'ON', value: '1' }]), + ], + 'Pool Overview', + 'table' + ) + .addTargets( + [ + $.addTargetSchema( + ||| + ( + ceph_pool_compress_under_bytes{%(matchers)s} / + ceph_pool_compress_bytes_used{%(matchers)s} > 0 + ) and on(pool_id) ( + ( + (ceph_pool_compress_under_bytes{%(matchers)s} > 0) / + ceph_pool_stored_raw{%(matchers)s} + ) * 100 > 0.5 + ) + ||| % $.matchers(), + 'A', + 'table', + 1, + true + ), + $.addTargetSchema( + ||| + ceph_pool_max_avail{%(matchers)s} * + on(pool_id) group_left(name) ceph_pool_metadata{%(matchers)s} + ||| % $.matchers(), + 'B', + 'table', + 1, + true + ), + $.addTargetSchema( + ||| + ( + (ceph_pool_compress_under_bytes{%(matchers)s} > 0) / + ceph_pool_stored_raw{%(matchers)s} + ) * 100 + ||| % $.matchers(), + 'C', + 'table', + 1, + true + ), + $.addTargetSchema( + ||| + ceph_pool_percent_used{%(matchers)s} * + on(pool_id) group_left(name) ceph_pool_metadata{%(matchers)s} + ||| % $.matchers(), + 'D', + 'table', + 1, + true + ), + $.addTargetSchema( + ||| + ceph_pool_compress_under_bytes{%(matchers)s} - + ceph_pool_compress_bytes_used{%(matchers)s} > 0 + ||| % $.matchers(), + 'E', + 'table', + 1, + true + ), + $.addTargetSchema( + 'delta(ceph_pool_stored{%(matchers)s}[5d])' % $.matchers(), 'F', 'table', 1, true + ), + $.addTargetSchema( + ||| + rate(ceph_pool_rd{%(matchers)s}[$__rate_interval]) + + rate(ceph_pool_wr{%(matchers)s}[$__rate_interval]) + ||| % $.matchers(), + 'G', + 'table', + 1, + true + ), + $.addTargetSchema( + ||| + rate(ceph_pool_rd_bytes{%(matchers)s}[$__rate_interval]) + + rate(ceph_pool_wr_bytes{%(matchers)s}[$__rate_interval]) + ||| % $.matchers(), + 'H', + 'table', + 1, + true + ), + $.addTargetSchema( + 'ceph_pool_metadata{%(matchers)s}' % $.matchers(), 'I', 'table', 1, true + ), + $.addTargetSchema( + 'ceph_pool_stored{%(matchers)s} * on(pool_id) group_left ceph_pool_metadata{%(matchers)s}' % $.matchers(), + 'J', + 'table', + 1, + true + ), + $.addTargetSchema( + 'ceph_pool_metadata{%(matchers)s, compression_mode!="none"}' % $.matchers(), 'K', 'table', 1, true + ), + $.addTargetSchema('', 'L', '', '', null), + ] + ) + { gridPos: { x: 0, y: 3, w: 24, h: 6 } }, + $.simpleGraphPanel( + {}, + 'Top $topk Client IOPS by Pool', + 'This chart shows the sum of read and write IOPS from all clients by pool', + 'short', + 'IOPS', + 0, + ||| + topk($topk, + round( + ( + rate(ceph_pool_rd{%(matchers)s}[$__rate_interval]) + + rate(ceph_pool_wr{%(matchers)s}[$__rate_interval]) + ), 1 + ) * on(pool_id) group_left(instance,name) ceph_pool_metadata{%(matchers)s}) + ||| % $.matchers(), + '{{name}} ', + 0, + 9, + 12, + 8 + ) + .addTarget( + $.addTargetSchema( + ||| + topk($topk, + rate(ceph_pool_wr{%(matchers)s}[$__rate_interval]) + + on(pool_id) group_left(instance,name) ceph_pool_metadata{%(matchers)s} + ) + ||| % $.matchers(), + '{{name}} - write' + ) + ), + $.simpleGraphPanel( + {}, + 'Top $topk Client Bandwidth by Pool', + 'The chart shows the sum of read and write bytes from all clients, by pool', + 'Bps', + 'Throughput', + 0, + ||| + topk($topk, + ( + rate(ceph_pool_rd_bytes{%(matchers)s}[$__rate_interval]) + + rate(ceph_pool_wr_bytes{%(matchers)s}[$__rate_interval]) + ) * on(pool_id) group_left(instance, name) ceph_pool_metadata{%(matchers)s} + ) + ||| % $.matchers(), + '{{name}}', + 12, + 9, + 12, + 8 + ), + $.simpleGraphPanel( + {}, + 'Pool Capacity Usage (RAW)', + 'Historical view of capacity usage, to help identify growth and trends in pool consumption', + 'bytes', + 'Capacity Used', + 0, + 'ceph_pool_bytes_used{%(matchers)s} * on(pool_id) group_right ceph_pool_metadata{%(matchers)s}' % $.matchers(), + '{{name}}', + 0, + 17, + 24, + 7 + ), + ]), + 'pool-detail.json': + $.dashboardSchema( + 'Ceph Pool Details', + '', + '-xyV8KCiz', + 'now-1h', + '30s', + 22, + $._config.dashboardTags, + '' + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.3.2' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addRequired( + type='panel', id='singlestat', name='Singlestat', version='5.0.0' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema('pool_name', + '$datasource', + 'label_values(ceph_pool_metadata{%(matchers)s}, name)' % $.matchers(), + 1, + false, + 1, + 'Pool Name', + '') + ) + .addPanels([ + $.gaugeSingleStatPanel( + 'percentunit', + 'Capacity used', + '', + 'current', + true, + 1, + true, + true, + '.7,.8', + ||| + (ceph_pool_stored{%(matchers)s} / (ceph_pool_stored{%(matchers)s} + ceph_pool_max_avail{%(matchers)s})) * + on(pool_id) group_left(instance, name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} + ||| % $.matchers(), + 'time_series', + 0, + 0, + 7, + 7 + ), + $.gaugeSingleStatPanel( + 's', + 'Time till full', + 'Time till pool is full assuming the average fill rate of the last 6 hours', + false, + 100, + false, + false, + '', + 'current', + ||| + (ceph_pool_max_avail{%(matchers)s} / deriv(ceph_pool_stored{%(matchers)s}[6h])) * + on(pool_id) group_left(instance, name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} > 0 + ||| % $.matchers(), + 'time_series', + 7, + 0, + 5, + 7 + ), + $.simpleGraphPanel( + { + read_op_per_sec: + '#3F6833', + write_op_per_sec: '#E5AC0E', + }, + '$pool_name Object Ingress/Egress', + '', + 'ops', + 'Objects out(-) / in(+) ', + null, + ||| + deriv(ceph_pool_objects{%(matchers)s}[1m]) * + on(pool_id) group_left(instance, name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} + ||| % $.matchers(), + 'Objects per second', + 12, + 0, + 12, + 7 + ), + $.simpleGraphPanel( + { + read_op_per_sec: '#3F6833', + write_op_per_sec: '#E5AC0E', + }, + '$pool_name Client IOPS', + '', + 'iops', + 'Read (-) / Write (+)', + null, + ||| + rate(ceph_pool_rd{%(matchers)s}[$__rate_interval]) * + on(pool_id) group_left(instance,name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} + ||| % $.matchers(), + 'reads', + 0, + 7, + 12, + 7 + ) + .addSeriesOverride({ alias: 'reads', transform: 'negative-Y' }) + .addTarget( + $.addTargetSchema( + ||| + rate(ceph_pool_wr{%(matchers)s}[$__rate_interval]) * + on(pool_id) group_left(instance, name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} + ||| % $.matchers(), + 'writes' + ) + ), + $.simpleGraphPanel( + { + read_op_per_sec: '#3F6833', + write_op_per_sec: '#E5AC0E', + }, + '$pool_name Client Throughput', + '', + 'Bps', + 'Read (-) / Write (+)', + null, + ||| + rate(ceph_pool_rd_bytes{%(matchers)s}[$__rate_interval]) + + on(pool_id) group_left(instance, name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} + ||| % $.matchers(), + 'reads', + 12, + 7, + 12, + 7 + ) + .addSeriesOverride({ alias: 'reads', transform: 'negative-Y' }) + .addTarget( + $.addTargetSchema( + ||| + rate(ceph_pool_wr_bytes{%(matchers)s}[$__rate_interval]) + + on(pool_id) group_left(instance,name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} + ||| % $.matchers(), + 'writes' + ) + ), + $.simpleGraphPanel( + { + read_op_per_sec: '#3F6833', + write_op_per_sec: '#E5AC0E', + }, + '$pool_name Objects', + '', + 'short', + 'Objects', + null, + ||| + ceph_pool_objects{%(matchers)s} * + on(pool_id) group_left(instance,name) ceph_pool_metadata{%(matchers)s, name=~"$pool_name"} + ||| % $.matchers(), + 'Number of Objects', + 0, + 14, + 12, + 7 + ), + ]), +} diff --git a/monitoring/ceph-mixin/dashboards/rbd.libsonnet b/monitoring/ceph-mixin/dashboards/rbd.libsonnet new file mode 100644 index 000000000..0eca5a877 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards/rbd.libsonnet @@ -0,0 +1,337 @@ +local g = import 'grafonnet/grafana.libsonnet'; +local u = import 'utils.libsonnet'; + +(import 'utils.libsonnet') { + 'rbd-details.json': + local RbdDetailsPanel(title, formatY1, expr1, expr2, x, y, w, h) = + $.graphPanelSchema({}, + title, + '', + 'null as zero', + false, + formatY1, + formatY1, + null, + null, + 0, + 1, + '$datasource') + .addTargets( + [ + $.addTargetSchema(expr1, + '{{pool}} Write'), + $.addTargetSchema(expr2, '{{pool}} Read'), + ] + ) + { gridPos: { x: x, y: y, w: w, h: h } }; + + $.dashboardSchema( + 'RBD Details', + 'Detailed Performance of RBD Images (IOPS/Throughput/Latency)', + 'YhCYGcuZz', + 'now-1h', + '30s', + 16, + $._config.dashboardTags, + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.3.3' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema('pool', + '$datasource', + 'label_values(pool)', + 1, + false, + 0, + '', + '') + ) + .addTemplate( + $.addTemplateSchema('image', + '$datasource', + 'label_values(image)', + 1, + false, + 0, + '', + '') + ) + .addPanels([ + RbdDetailsPanel( + 'IOPS', + 'iops', + 'rate(ceph_rbd_write_ops{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval])' % $.matchers() + , + 'rate(ceph_rbd_read_ops{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval])' % $.matchers(), + 0, + 0, + 8, + 9 + ), + RbdDetailsPanel( + 'Throughput', + 'Bps', + 'rate(ceph_rbd_write_bytes{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval])' % $.matchers(), + 'rate(ceph_rbd_read_bytes{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval])' % $.matchers(), + 8, + 0, + 8, + 9 + ), + RbdDetailsPanel( + 'Average Latency', + 'ns', + ||| + rate(ceph_rbd_write_latency_sum{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval]) / + rate(ceph_rbd_write_latency_count{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval]) + ||| % $.matchers(), + ||| + rate(ceph_rbd_read_latency_sum{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval]) / + rate(ceph_rbd_read_latency_count{%(matchers)s, pool="$pool", image="$image"}[$__rate_interval]) + ||| % $.matchers(), + 16, + 0, + 8, + 9 + ), + ]), + 'rbd-overview.json': + local RbdOverviewPanel(title, + formatY1, + expr1, + expr2, + legendFormat1, + legendFormat2, + x, + y, + w, + h) = + $.graphPanelSchema({}, + title, + '', + 'null', + false, + formatY1, + 'short', + null, + null, + 0, + 1, + '$datasource') + .addTargets( + [ + $.addTargetSchema(expr1, + legendFormat1), + $.addTargetSchema(expr2, + legendFormat2), + ] + ) + { gridPos: { x: x, y: y, w: w, h: h } }; + + $.dashboardSchema( + 'RBD Overview', + '', + '41FrpeUiz', + 'now-1h', + '30s', + 16, + $._config.dashboardTags + ['overview'], + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.4.2' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addRequired( + type='datasource', id='prometheus', name='Prometheus', version='5.0.0' + ) + .addRequired( + type='panel', id='table', name='Table', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addPanels([ + RbdOverviewPanel( + 'IOPS', + 'short', + 'round(sum(rate(ceph_rbd_write_ops{%(matchers)s}[$__rate_interval])))' % $.matchers(), + 'round(sum(rate(ceph_rbd_read_ops{%(matchers)s}[$__rate_interval])))' % $.matchers(), + 'Writes', + 'Reads', + 0, + 0, + 8, + 7 + ), + RbdOverviewPanel( + 'Throughput', + 'Bps', + 'round(sum(rate(ceph_rbd_write_bytes{%(matchers)s}[$__rate_interval])))' % $.matchers(), + 'round(sum(rate(ceph_rbd_read_bytes{%(matchers)s}[$__rate_interval])))' % $.matchers(), + 'Write', + 'Read', + 8, + 0, + 8, + 7 + ), + RbdOverviewPanel( + 'Average Latency', + 'ns', + ||| + round( + sum(rate(ceph_rbd_write_latency_sum{%(matchers)s}[$__rate_interval])) / + sum(rate(ceph_rbd_write_latency_count{%(matchers)s}[$__rate_interval])) + ) + ||| % $.matchers(), + ||| + round( + sum(rate(ceph_rbd_read_latency_sum{%(matchers)s}[$__rate_interval])) / + sum(rate(ceph_rbd_read_latency_count{%(matchers)s}[$__rate_interval])) + ) + ||| % $.matchers(), + 'Write', + 'Read', + 16, + 0, + 8, + 7 + ), + $.addTableSchema( + '$datasource', + '', + { col: 3, desc: true }, + [ + $.overviewStyle('Pool', 'pool', 'string', 'short'), + $.overviewStyle('Image', 'image', 'string', 'short'), + $.overviewStyle('IOPS', 'Value', 'number', 'iops'), + $.overviewStyle('', '/.*/', 'hidden', 'short'), + ], + 'Highest IOPS', + 'table' + ) + .addTarget( + $.addTargetSchema( + ||| + topk(10, + ( + sort(( + rate(ceph_rbd_write_ops{%(matchers)s}[$__rate_interval]) + + on (image, pool, namespace) rate(ceph_rbd_read_ops{%(matchers)s}[$__rate_interval]) + )) + ) + ) + ||| % $.matchers(), + '', + 'table', + 1, + true + ) + ) + { gridPos: { x: 0, y: 7, w: 8, h: 7 } }, + $.addTableSchema( + '$datasource', + '', + { col: 3, desc: true }, + [ + $.overviewStyle('Pool', 'pool', 'string', 'short'), + $.overviewStyle('Image', 'image', 'string', 'short'), + $.overviewStyle('Throughput', 'Value', 'number', 'Bps'), + $.overviewStyle('', '/.*/', 'hidden', 'short'), + ], + 'Highest Throughput', + 'table' + ) + .addTarget( + $.addTargetSchema( + ||| + topk(10, + sort( + sum( + rate(ceph_rbd_read_bytes{%(matchers)s}[$__rate_interval]) + + rate(ceph_rbd_write_bytes{%(matchers)s}[$__rate_interval]) + ) by (pool, image, namespace) + ) + ) + ||| % $.matchers(), + '', + 'table', + 1, + true + ) + ) + { gridPos: { x: 8, y: 7, w: 8, h: 7 } }, + $.addTableSchema( + '$datasource', + '', + { col: 3, desc: true }, + [ + $.overviewStyle('Pool', 'pool', 'string', 'short'), + $.overviewStyle('Image', 'image', 'string', 'short'), + $.overviewStyle('Latency', 'Value', 'number', 'ns'), + $.overviewStyle('', '/.*/', 'hidden', 'short'), + ], + 'Highest Latency', + 'table' + ) + .addTarget( + $.addTargetSchema( + ||| + topk(10, + sum( + rate(ceph_rbd_write_latency_sum{%(matchers)s}[$__rate_interval]) / + clamp_min(rate(ceph_rbd_write_latency_count{%(matchers)s}[$__rate_interval]), 1) + + rate(ceph_rbd_read_latency_sum{%(matchers)s}[$__rate_interval]) / + clamp_min(rate(ceph_rbd_read_latency_count{%(matchers)s}[$__rate_interval]), 1) + ) by (pool, image, namespace) + ) + ||| % $.matchers(), + '', + 'table', + 1, + true + ) + ) + { gridPos: { x: 16, y: 7, w: 8, h: 7 } }, + ]), +} diff --git a/monitoring/ceph-mixin/dashboards/rgw.libsonnet b/monitoring/ceph-mixin/dashboards/rgw.libsonnet new file mode 100644 index 000000000..892480d1c --- /dev/null +++ b/monitoring/ceph-mixin/dashboards/rgw.libsonnet @@ -0,0 +1,872 @@ +local g = import 'grafonnet/grafana.libsonnet'; +local u = import 'utils.libsonnet'; + +(import 'utils.libsonnet') { + 'radosgw-sync-overview.json': + local RgwSyncOverviewPanel(title, formatY1, labelY1, rgwMetric, x, y, w, h) = + $.graphPanelSchema({}, + title, + '', + 'null as zero', + true, + formatY1, + 'short', + labelY1, + null, + 0, + 1, + '$datasource') + .addTargets( + [ + $.addTargetSchema( + 'sum by (source_zone) (rate(%(rgwMetric)s{%(matchers)s}[$__rate_interval]))' + % ($.matchers() + { rgwMetric: rgwMetric }), + '{{source_zone}}' + ), + ] + ) + { gridPos: { x: x, y: y, w: w, h: h } }; + + $.dashboardSchema( + 'RGW Sync Overview', + '', + 'rgw-sync-overview', + 'now-1h', + '30s', + 16, + $._config.dashboardTags + ['overview'], + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.0.0' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', 'prometheus', 'default', label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema( + 'rgw_servers', + '$datasource', + 'label_values(ceph_rgw_metadata{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + true, + 1, + '', + 'RGW Server' + ) + ) + .addPanels([ + RgwSyncOverviewPanel( + 'Replication (throughput) from Source Zone', + 'Bps', + null, + 'ceph_data_sync_from_zone_fetch_bytes_sum', + 0, + 0, + 8, + 7 + ), + RgwSyncOverviewPanel( + 'Replication (objects) from Source Zone', + 'short', + 'Objects/s', + 'ceph_data_sync_from_zone_fetch_bytes_count', + 8, + 0, + 8, + 7 + ), + RgwSyncOverviewPanel( + 'Polling Request Latency from Source Zone', + 'ms', + null, + 'ceph_data_sync_from_zone_poll_latency_sum', + 16, + 0, + 8, + 7 + ), + RgwSyncOverviewPanel( + 'Unsuccessful Object Replications from Source Zone', + 'short', + 'Count/s', + 'ceph_data_sync_from_zone_fetch_errors', + 0, + 7, + 8, + 7 + ), + ]), + 'radosgw-overview.json': + local RgwOverviewPanel( + title, + description, + formatY1, + formatY2, + expr1, + legendFormat1, + x, + y, + w, + h, + datasource='$datasource', + legend_alignAsTable=false, + legend_avg=false, + legend_min=false, + legend_max=false, + legend_current=false, + legend_values=false + ) = + $.graphPanelSchema( + {}, + title, + description, + 'null', + false, + formatY1, + formatY2, + null, + null, + 0, + 1, + datasource, + legend_alignAsTable, + legend_avg, + legend_min, + legend_max, + legend_current, + legend_values + ) + .addTargets( + [$.addTargetSchema(expr1, legendFormat1)] + ) + { gridPos: { x: x, y: y, w: w, h: h } }; + + $.dashboardSchema( + 'RGW Overview', + '', + 'WAkugZpiz', + 'now-1h', + '30s', + 16, + $._config.dashboardTags + ['overview'], + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.0.0' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', + 'prometheus', + 'default', + label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema( + 'rgw_servers', + '$datasource', + 'label_values(ceph_rgw_metadata{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + true, + 1, + '', + 'RGW Server' + ) + ) + .addTemplate( + $.addTemplateSchema( + 'code', + '$datasource', + 'label_values(haproxy_server_http_responses_total{job=~"$job_haproxy", instance=~"$ingress_service"}, code)', + 1, + true, + 1, + 'HTTP Code', + '' + ) + ) + .addTemplate( + $.addTemplateSchema( + 'job_haproxy', + '$datasource', + 'label_values(haproxy_server_status, job)', + 1, + true, + 1, + 'job haproxy', + '(.*)', + multi=true, + allValues='.+', + ), + ) + .addTemplate( + $.addTemplateSchema( + 'ingress_service', + '$datasource', + 'label_values(haproxy_server_status{job=~"$job_haproxy"}, instance)', + 1, + true, + 1, + 'Ingress Service', + '' + ) + ) + .addPanels([ + $.addRowSchema(false, + true, + 'RGW Overview - All Gateways') + + { + gridPos: { x: 0, y: 0, w: 24, h: 1 }, + }, + RgwOverviewPanel( + 'Average GET/PUT Latencies by RGW Instance', + '', + 's', + 'short', + ||| + label_replace( + rate(ceph_rgw_get_initial_lat_sum{%(matchers)s}[$__rate_interval]) / + rate(ceph_rgw_get_initial_lat_count{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s}, + "rgw_host", "$1", "ceph_daemon", "rgw.(.*)" + ) + ||| % $.matchers(), + 'GET {{rgw_host}}', + 0, + 1, + 8, + 7 + ).addTargets( + [ + $.addTargetSchema( + ||| + label_replace( + rate(ceph_rgw_put_initial_lat_sum{%(matchers)s}[$__rate_interval]) / + rate(ceph_rgw_put_initial_lat_count{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s}, + "rgw_host", "$1", "ceph_daemon", "rgw.(.*)" + ) + ||| % $.matchers(), + 'PUT {{rgw_host}}' + ), + ] + ), + RgwOverviewPanel( + 'Total Requests/sec by RGW Instance', + '', + 'none', + 'short', + ||| + sum by (rgw_host) ( + label_replace( + rate(ceph_rgw_req{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s}, + "rgw_host", "$1", "ceph_daemon", "rgw.(.*)" + ) + ) + ||| % $.matchers(), + '{{rgw_host}}', + 8, + 1, + 7, + 7 + ), + RgwOverviewPanel( + 'GET Latencies by RGW Instance', + 'Latencies are shown stacked, without a yaxis to provide a visual indication of GET latency imbalance across RGW hosts', + 's', + 'short', + ||| + label_replace( + rate(ceph_rgw_get_initial_lat_sum{%(matchers)s}[$__rate_interval]) / + rate(ceph_rgw_get_initial_lat_count{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s}, + "rgw_host", "$1", "ceph_daemon", "rgw.(.*)" + ) + ||| % $.matchers(), + '{{rgw_host}}', + 15, + 1, + 6, + 7 + ), + RgwOverviewPanel( + 'Bandwidth Consumed by Type', + 'Total bytes transferred in/out of all radosgw instances within the cluster', + 'bytes', + 'short', + 'sum(rate(ceph_rgw_get_b{%(matchers)s}[$__rate_interval]))' % $.matchers(), + 'GETs', + 0, + 8, + 8, + 6 + ).addTargets( + [$.addTargetSchema('sum(rate(ceph_rgw_put_b{%(matchers)s}[$__rate_interval]))' % $.matchers(), + 'PUTs')] + ), + RgwOverviewPanel( + 'Bandwidth by RGW Instance', + 'Total bytes transferred in/out through get/put operations, by radosgw instance', + 'bytes', + 'short', + ||| + label_replace(sum by (instance_id) ( + rate(ceph_rgw_get_b{%(matchers)s}[$__rate_interval]) + + rate(ceph_rgw_put_b{%(matchers)s}[$__rate_interval])) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s}, + "rgw_host", "$1", "ceph_daemon", "rgw.(.*)" + ) + ||| % $.matchers(), + '{{rgw_host}}', + 8, + 8, + 7, + 6 + ), + RgwOverviewPanel( + 'PUT Latencies by RGW Instance', + 'Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts', + 's', + 'short', + ||| + label_replace( + rate(ceph_rgw_put_initial_lat_sum{%(matchers)s}[$__rate_interval]) / + rate(ceph_rgw_put_initial_lat_count{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s}, + "rgw_host", "$1", "ceph_daemon", "rgw.(.*)" + ) + ||| % $.matchers(), + '{{rgw_host}}', + 15, + 8, + 6, + 6 + ), + $.addRowSchema( + false, true, 'RGW Overview - HAProxy Metrics' + ) + { gridPos: { x: 0, y: 12, w: 9, h: 12 } }, + RgwOverviewPanel( + 'Total responses by HTTP code', + '', + 'short', + 'short', + ||| + sum( + rate( + haproxy_frontend_http_responses_total{code=~"$code", job=~"$job_haproxy", instance=~"$ingress_service", proxy=~"frontend"}[$__rate_interval] + ) + ) by (code) + |||, + 'Frontend {{ code }}', + 0, + 12, + 5, + 12, + '$datasource', + true, + true, + true, + true, + true, + true + ) + .addTargets( + [ + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_http_responses_total{code=~"$code", job=~"$job_haproxy", instance=~"$ingress_service", proxy=~"backend"}[$__rate_interval] + ) + ) by (code) + |||, 'Backend {{ code }}' + ), + ] + ) + .addSeriesOverride([ + { + alias: '/.*Back.*/', + transform: 'negative-Y', + }, + { alias: '/.*1.*/' }, + { alias: '/.*2.*/' }, + { alias: '/.*3.*/' }, + { alias: '/.*4.*/' }, + { alias: '/.*5.*/' }, + { alias: '/.*other.*/' }, + ]), + RgwOverviewPanel( + 'Total requests / responses', + '', + 'short', + 'short', + ||| + sum( + rate( + haproxy_frontend_http_requests_total{proxy=~"frontend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, + 'Requests', + 5, + 12, + 5, + 12, + '$datasource', + true, + true, + true, + true, + true, + true + ) + .addTargets( + [ + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_response_errors_total{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, 'Response errors', 'time_series', 2 + ), + $.addTargetSchema( + ||| + sum( + rate( + haproxy_frontend_request_errors_total{proxy=~"frontend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, 'Requests errors' + ), + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_redispatch_warnings_total{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, 'Backend redispatch', 'time_series', 2 + ), + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_retry_warnings_total{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, 'Backend retry', 'time_series', 2 + ), + $.addTargetSchema( + ||| + sum( + rate( + haproxy_frontend_requests_denied_total{proxy=~"frontend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, 'Request denied', 'time_series', 2 + ), + $.addTargetSchema( + ||| + sum( + haproxy_backend_current_queue{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"} + ) by (instance) + |||, 'Backend Queued', 'time_series', 2 + ), + ] + ) + .addSeriesOverride([ + { + alias: '/.*Response.*/', + transform: 'negative-Y', + }, + { + alias: '/.*Backend.*/', + transform: 'negative-Y', + }, + ]), + RgwOverviewPanel( + 'Total number of connections', + '', + 'short', + 'short', + ||| + sum( + rate( + haproxy_frontend_connections_total{proxy=~"frontend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, + 'Front', + 10, + 12, + 5, + 12, + '$datasource', + true, + true, + true, + true, + true, + true + ) + .addTargets( + [ + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_connection_attempts_total{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, 'Back' + ), + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_connection_errors_total{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) + ) by (instance) + |||, 'Back errors' + ), + ] + ) + .addSeriesOverride([ + { + alias: '/.*Back.*/', + transform: 'negative-Y', + }, + ]), + RgwOverviewPanel( + 'Current total of incoming / outgoing bytes', + '', + 'short', + 'short', + ||| + sum( + rate( + haproxy_frontend_bytes_in_total{proxy=~"frontend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) * 8 + ) by (instance) + |||, + 'IN Front', + 15, + 12, + 6, + 12, + '$datasource', + true, + true, + true, + true, + true, + true + ) + .addTargets( + [ + $.addTargetSchema( + ||| + sum( + rate( + haproxy_frontend_bytes_out_total{proxy=~"frontend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) * 8 + ) by (instance) + |||, 'OUT Front', 'time_series', 2 + ), + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_bytes_in_total{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) * 8 + ) by (instance) + |||, 'IN Back', 'time_series', 2 + ), + $.addTargetSchema( + ||| + sum( + rate( + haproxy_backend_bytes_out_total{proxy=~"backend", job=~"$job_haproxy", instance=~"$ingress_service"}[$__rate_interval] + ) * 8 + ) by (instance) + |||, 'OUT Back', 'time_series', 2 + ), + ] + ) + .addSeriesOverride([ + { + alias: '/.*OUT.*/', + transform: 'negative-Y', + }, + ]), + ]), + 'radosgw-detail.json': + local RgwDetailsPanel(aliasColors, + title, + description, + formatY1, + formatY2, + expr1, + expr2, + legendFormat1, + legendFormat2, + x, + y, + w, + h) = + $.graphPanelSchema(aliasColors, + title, + description, + 'null', + false, + formatY1, + formatY2, + null, + null, + 0, + 1, + '$datasource') + .addTargets( + [$.addTargetSchema(expr1, legendFormat1), $.addTargetSchema(expr2, legendFormat2)] + ) + { gridPos: { x: x, y: y, w: w, h: h } }; + + $.dashboardSchema( + 'RGW Instance Detail', + '', + 'x5ARzZtmk', + 'now-1h', + '30s', + 16, + $._config.dashboardTags + ['overview'], + '' + ) + .addAnnotation( + $.addAnnotationSchema( + 1, + '-- Grafana --', + true, + true, + 'rgba(0, 211, 255, 1)', + 'Annotations & Alerts', + 'dashboard' + ) + ) + .addRequired( + type='grafana', id='grafana', name='Grafana', version='5.0.0' + ) + .addRequired( + type='panel', + id='grafana-piechart-panel', + name='Pie Chart', + version='1.3.3' + ) + .addRequired( + type='panel', id='graph', name='Graph', version='5.0.0' + ) + .addTemplate( + g.template.datasource('datasource', + 'prometheus', + 'default', + label='Data Source') + ) + .addTemplate( + $.addClusterTemplate() + ) + .addTemplate( + $.addJobTemplate() + ) + .addTemplate( + $.addTemplateSchema('rgw_servers', + '$datasource', + 'label_values(ceph_rgw_metadata{%(matchers)s}, ceph_daemon)' % $.matchers(), + 1, + true, + 1, + '', + '') + ) + .addPanels([ + $.addRowSchema(false, true, 'RGW Host Detail : $rgw_servers') + { gridPos: { x: 0, y: 0, w: 24, h: 1 } }, + RgwDetailsPanel( + {}, + '$rgw_servers GET/PUT Latencies', + '', + 's', + 'short', + ||| + sum by (instance_id) ( + rate(ceph_rgw_get_initial_lat_sum{%(matchers)s}[$__rate_interval]) / + rate(ceph_rgw_get_initial_lat_count{%(matchers)s}[$__rate_interval]) + ) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + ||| + sum by (instance_id) ( + rate(ceph_rgw_put_initial_lat_sum{%(matchers)s}[$__rate_interval]) / + rate(ceph_rgw_put_initial_lat_count{%(matchers)s}[$__rate_interval]) + ) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'GET {{ceph_daemon}}', + 'PUT {{ceph_daemon}}', + 0, + 1, + 6, + 8 + ), + RgwDetailsPanel( + {}, + 'Bandwidth by HTTP Operation', + '', + 'bytes', + 'short', + ||| + rate(ceph_rgw_get_b{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + ||| + rate(ceph_rgw_put_b{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) + ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'GETs {{ceph_daemon}}', + 'PUTs {{ceph_daemon}}', + 6, + 1, + 7, + 8 + ), + RgwDetailsPanel( + { + GETs: '#7eb26d', + Other: '#447ebc', + PUTs: '#eab839', + Requests: '#3f2b5b', + 'Requests Failed': '#bf1b00', + }, + 'HTTP Request Breakdown', + '', + 'short', + 'short', + ||| + rate(ceph_rgw_failed_req{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s,ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + ||| + rate(ceph_rgw_get{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'Requests Failed {{ceph_daemon}}', + 'GETs {{ceph_daemon}}', + 13, + 1, + 7, + 8 + ) + .addTargets( + [ + $.addTargetSchema( + ||| + rate(ceph_rgw_put{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'PUTs {{ceph_daemon}}' + ), + $.addTargetSchema( + ||| + ( + rate(ceph_rgw_req{%(matchers)s}[$__rate_interval]) - + ( + rate(ceph_rgw_get{%(matchers)s}[$__rate_interval]) + + rate(ceph_rgw_put{%(matchers)s}[$__rate_interval]) + ) + ) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'Other {{ceph_daemon}}' + ), + ] + ), + $.simplePieChart( + { + GETs: '#7eb26d', + 'Other (HEAD,POST,DELETE)': '#447ebc', + PUTs: '#eab839', + Requests: '#3f2b5b', + Failures: '#bf1b00', + }, '', 'Workload Breakdown' + ) + .addTarget($.addTargetSchema( + ||| + rate(ceph_rgw_failed_req{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'Failures {{ceph_daemon}}' + )) + .addTarget($.addTargetSchema( + ||| + rate(ceph_rgw_get{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'GETs {{ceph_daemon}}' + )) + .addTarget($.addTargetSchema( + ||| + rate(ceph_rgw_put{%(matchers)s}[$__rate_interval]) * + on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'PUTs {{ceph_daemon}}' + )) + .addTarget($.addTargetSchema( + ||| + ( + rate(ceph_rgw_req{%(matchers)s}[$__rate_interval]) - + ( + rate(ceph_rgw_get{%(matchers)s}[$__rate_interval]) + + rate(ceph_rgw_put{%(matchers)s}[$__rate_interval]) + ) + ) * on (instance_id) group_left (ceph_daemon) + ceph_rgw_metadata{%(matchers)s, ceph_daemon=~"$rgw_servers"} + ||| % $.matchers(), + 'Other (DELETE,LIST) {{ceph_daemon}}' + )) + { gridPos: { x: 20, y: 1, w: 4, h: 8 } }, + ]), +} diff --git a/monitoring/ceph-mixin/dashboards/utils.libsonnet b/monitoring/ceph-mixin/dashboards/utils.libsonnet new file mode 100644 index 000000000..a7774c7ce --- /dev/null +++ b/monitoring/ceph-mixin/dashboards/utils.libsonnet @@ -0,0 +1,333 @@ +local g = import 'grafonnet/grafana.libsonnet'; + +{ + _config:: error 'must provide _config', + + dashboardSchema(title, + description, + uid, + time_from, + refresh, + schemaVersion, + tags, + timezone):: + g.dashboard.new(title=title, + description=description, + uid=uid, + time_from=time_from, + refresh=refresh, + schemaVersion=schemaVersion, + tags=tags, + timezone=timezone), + + graphPanelSchema(aliasColors, + title, + description, + nullPointMode, + stack, + formatY1, + formatY2, + labelY1, + labelY2, + min, + fill, + datasource, + legend_alignAsTable=false, + legend_avg=false, + legend_min=false, + legend_max=false, + legend_current=false, + legend_values=false):: + g.graphPanel.new(aliasColors=aliasColors, + title=title, + description=description, + nullPointMode=nullPointMode, + stack=stack, + formatY1=formatY1, + formatY2=formatY2, + labelY1=labelY1, + labelY2=labelY2, + min=min, + fill=fill, + datasource=datasource, + legend_alignAsTable=legend_alignAsTable, + legend_avg=legend_avg, + legend_min=legend_min, + legend_max=legend_max, + legend_current=legend_current, + legend_values=legend_values), + + + addTargetSchema(expr, legendFormat='', format='time_series', intervalFactor=1, instant=null):: + g.prometheus.target(expr=expr, + legendFormat=legendFormat, + format=format, + intervalFactor=intervalFactor, + instant=instant), + + addTemplateSchema(name, + datasource, + query, + refresh, + includeAll, + sort, + label, + regex, + hide='', + multi=false, + allValues=null):: + g.template.new(name=name, + datasource=datasource, + query=query, + refresh=refresh, + includeAll=includeAll, + sort=sort, + label=label, + regex=regex, + hide=hide, + multi=multi, + allValues=allValues), + + addAnnotationSchema(builtIn, + datasource, + enable, + hide, + iconColor, + name, + type):: + g.annotation.datasource(builtIn=builtIn, + datasource=datasource, + enable=enable, + hide=hide, + iconColor=iconColor, + name=name, + type=type), + + addRowSchema(collapse, showTitle, title):: + g.row.new(collapse=collapse, showTitle=showTitle, title=title), + + addSingleStatSchema(colors, + datasource, + format, + title, + description, + valueName, + colorValue, + gaugeMaxValue, + gaugeShow, + sparklineShow, + thresholds):: + g.singlestat.new(colors=colors, + datasource=datasource, + format=format, + title=title, + description=description, + valueName=valueName, + colorValue=colorValue, + gaugeMaxValue=gaugeMaxValue, + gaugeShow=gaugeShow, + sparklineShow=sparklineShow, + thresholds=thresholds), + + addPieChartSchema(aliasColors, + datasource, + description, + legendType, + pieType, + title, + valueName):: + g.pieChartPanel.new(aliasColors=aliasColors, + datasource=datasource, + description=description, + legendType=legendType, + pieType=pieType, + title=title, + valueName=valueName), + + addTableSchema(datasource, description, sort, styles, title, transform):: + g.tablePanel.new(datasource=datasource, + description=description, + sort=sort, + styles=styles, + title=title, + transform=transform), + + addStyle(alias, + colorMode, + colors, + dateFormat, + decimals, + mappingType, + pattern, + thresholds, + type, + unit, + valueMaps):: + { + alias: alias, + colorMode: colorMode, + colors: colors, + dateFormat: dateFormat, + decimals: decimals, + mappingType: mappingType, + pattern: pattern, + thresholds: thresholds, + type: type, + unit: unit, + valueMaps: valueMaps, + }, + + matchers():: + local jobMatcher = 'job=~"$job"'; + local clusterMatcher = '%s=~"$cluster"' % $._config.clusterLabel; + { + // Common labels + jobMatcher: jobMatcher, + clusterMatcher: (if $._config.showMultiCluster then clusterMatcher else ''), + matchers: jobMatcher + + (if $._config.showMultiCluster then ', ' + clusterMatcher else ''), + }, + + addClusterTemplate():: + $.addTemplateSchema( + 'cluster', + '$datasource', + 'label_values(ceph_osd_metadata, %s)' % $._config.clusterLabel, + 1, + true, + 1, + 'cluster', + '(.*)', + if !$._config.showMultiCluster then 'variable' else '', + multi=true, + allValues='.+', + ), + + addJobTemplate():: + $.addTemplateSchema( + 'job', + '$datasource', + 'label_values(ceph_osd_metadata{%(clusterMatcher)s}, job)' % $.matchers(), + 1, + true, + 1, + 'job', + '(.*)', + multi=true, + allValues='.+', + ), + + overviewStyle(alias, + pattern, + type, + unit, + colorMode=null, + thresholds=[], + valueMaps=[]):: + $.addStyle(alias, + colorMode, + [ + 'rgba(245, 54, 54, 0.9)', + 'rgba(237, 129, 40, 0.89)', + 'rgba(50, 172, 45, 0.97)', + ], + 'YYYY-MM-DD HH:mm:ss', + 2, + 1, + pattern, + thresholds, + type, + unit, + valueMaps), + + simpleGraphPanel(alias, + title, + description, + formatY1, + labelY1, + min, + expr, + legendFormat, + x, + y, + w, + h):: + $.graphPanelSchema(alias, + title, + description, + 'null', + false, + formatY1, + 'short', + labelY1, + null, + min, + 1, + '$datasource') + .addTargets( + [$.addTargetSchema(expr, legendFormat)] + ) + { gridPos: { x: x, y: y, w: w, h: h } }, + + simpleSingleStatPanel(format, + title, + description, + valueName, + expr, + instant, + targetFormat, + x, + y, + w, + h):: + $.addSingleStatSchema(['#299c46', 'rgba(237, 129, 40, 0.89)', '#d44a3a'], + '$datasource', + format, + title, + description, + valueName, + false, + 100, + false, + false, + '') + .addTarget($.addTargetSchema(expr, '', targetFormat, 1, instant)) + { + gridPos: { x: x, y: y, w: w, h: h }, + }, + gaugeSingleStatPanel(format, + title, + description, + valueName, + colorValue, + gaugeMaxValue, + gaugeShow, + sparkLineShow, + thresholds, + expr, + targetFormat, + x, + y, + w, + h):: + $.addSingleStatSchema(['#299c46', 'rgba(237, 129, 40, 0.89)', '#d44a3a'], + '$datasource', + format, + title, + description, + valueName, + colorValue, + gaugeMaxValue, + gaugeShow, + sparkLineShow, + thresholds) + .addTarget($.addTargetSchema(expr, '', targetFormat)) + { gridPos: { x: + x, y: y, w: w, h: h } }, + + simplePieChart(alias, description, title):: + $.addPieChartSchema(alias, + '$datasource', + description, + 'Under graph', + 'pie', + title, + 'current'), +} diff --git a/monitoring/ceph-mixin/dashboards_out/.lint b/monitoring/ceph-mixin/dashboards_out/.lint new file mode 100644 index 000000000..6352e858f --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/.lint @@ -0,0 +1,5 @@ +exclusions: + template-instance-rule: + reason: "Instance template not needed because of ceph-mgr leader election." + target-instance-rule: + reason: "Instance matcher not needed because of ceph-mgr leader election." diff --git a/monitoring/ceph-mixin/dashboards_out/ceph-cluster.json b/monitoring/ceph-mixin/dashboards_out/ceph-cluster.json new file mode 100644 index 000000000..2cd151ae1 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/ceph-cluster.json @@ -0,0 +1,1279 @@ +{ + "__requires": [ + { + "type": "grafana", + "id": "grafana", + "name": "Grafana", + "version": "5.0.0" + }, + { + "type": "panel", + "id": "graph", + "name": "Graph", + "version": "5.0.0" + }, + { + "type": "panel", + "id": "heatmap", + "name": "Heatmap", + "version": "5.0.0" + }, + { + "type": "panel", + "id": "singlestat", + "name": "Singlestat", + "version": "5.0.0" + } + ], + "annotations": { + "list": [] + }, + "description": "Ceph cluster overview", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "id": null, + "iteration": 1525415495309, + "links": [], + "panels": [ + { + "cacheTimeout": null, + "colorBackground": true, + "colorValue": false, + "colors": [ + "rgba(50, 128, 45, 0.9)", + "rgba(237, 129, 40, 0.9)", + "rgb(255, 0, 0)" + ], + "datasource": "$datasource", + "editable": false, + "error": false, + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 6, + "x": 0, + "y": 0 + }, + "hideTimeOverride": true, + "id": 21, + "interval": "1m", + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "ceph_health_status", + "format": "time_series", + "instant": true, + "interval": "$interval", + "intervalFactor": 1, + "refId": "A", + "step": 60 + } + ], + "thresholds": "1,2", + "timeFrom": null, + "title": "Health Status", + "transparent": false, + "type": "singlestat", + "valueFontSize": "50%", + "valueMaps": [ + { + "op": "=", + "text": "OK", + "value": "0" + }, + { + "op": "=", + "text": "WARN", + "value": "1" + }, + { + "op": "=", + "text": "ERR", + "value": "2" + } + ], + "valueName": "current" + }, + { + "colorMode": "Panel", + "colors": { + "crit": "rgb(255, 0, 0)", + "disable": "rgba(128, 128, 128, 0.9)", + "ok": "rgba(50, 128, 45, 0.9)", + "warn": "rgba(237, 129, 40, 0.9)" + }, + "cornerRadius": 0, + "datasource": "$datasource", + "displayName": "", + "flipCard": false, + "flipTime": 5, + "fontFormat": "Regular", + "gridPos": { + "h": 3, + "w": 6, + "x": 6, + "y": 0 + }, + "id": 43, + "isAutoScrollOnOverflow": false, + "isGrayOnNoData": false, + "isHideAlertsOnDisable": false, + "isIgnoreOKColors": false, + "links": [], + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "aggregation": "Last", + "alias": "All", + "decimals": 2, + "displayAliasType": "Always", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "count(ceph_osd_metadata)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "All", + "refId": "A", + "units": "none", + "valueHandler": "Number Threshold" + }, + { + "aggregation": "Last", + "alias": "In", + "decimals": 2, + "displayAliasType": "Always", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "sum(ceph_osd_in)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "In", + "refId": "B", + "units": "none", + "valueHandler": "Number Threshold" + }, + { + "aggregation": "Last", + "alias": "Out", + "decimals": 2, + "displayAliasType": "Warning / Critical", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "sum(ceph_osd_in == bool 0)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "Out", + "refId": "C", + "units": "none", + "valueHandler": "Number Threshold", + "warn": 1 + }, + { + "aggregation": "Last", + "alias": "Up", + "decimals": 2, + "displayAliasType": "Always", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "sum(ceph_osd_up)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Up", + "refId": "D", + "units": "none", + "valueHandler": "Number Threshold" + }, + { + "aggregation": "Last", + "alias": "Down", + "crit": 2, + "decimals": 2, + "displayAliasType": "Warning / Critical", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "sum(ceph_osd_up == bool 0)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Down", + "refId": "E", + "units": "none", + "valueHandler": "Number Threshold", + "warn": 1 + } + ], + "title": "OSDs", + "type": "stat" + }, + { + "clusterName": "", + "colorMode": "Panel", + "colors": { + "crit": "rgba(245, 54, 54, 0.9)", + "disable": "rgba(128, 128, 128, 0.9)", + "ok": "rgba(50, 128, 45, 0.9)", + "warn": "rgba(237, 129, 40, 0.9)" + }, + "cornerRadius": 1, + "datasource": "$datasource", + "displayName": "", + "flipCard": false, + "flipTime": 5, + "fontFormat": "Regular", + "gridPos": { + "h": 3, + "w": 6, + "x": 12, + "y": 0 + }, + "id": 41, + "isAutoScrollOnOverflow": false, + "isGrayOnNoData": false, + "isHideAlertsOnDisable": false, + "isIgnoreOKColors": false, + "links": [], + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "aggregation": "Last", + "alias": "In Quorum", + "decimals": 2, + "displayAliasType": "Always", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "sum(ceph_mon_quorum_status)", + "format": "time_series", + "interval": "", + "intervalFactor": 1, + "legendFormat": "In Quorum", + "refId": "A", + "units": "none", + "valueHandler": "Text Only" + }, + { + "aggregation": "Last", + "alias": "Total", + "crit": 1, + "decimals": 2, + "displayAliasType": "Always", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "count(ceph_mon_quorum_status)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Total", + "refId": "B", + "units": "none", + "valueHandler": "Text Only", + "warn": 2 + }, + { + "aggregation": "Last", + "alias": "MONs out of Quorum", + "crit": 1.6, + "decimals": 2, + "displayAliasType": "Warning / Critical", + "displayType": "Annotation", + "displayValueWithAlias": "Never", + "expr": "count(ceph_mon_quorum_status) / sum(ceph_mon_quorum_status)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "MONs out of Quorum", + "refId": "C", + "units": "none", + "valueHandler": "Number Threshold", + "warn": 1.1 + } + ], + "title": "Monitors", + "type": "stat" + }, + { + "colorMode": "Panel", + "colors": { + "crit": "rgba(245, 54, 54, 0.9)", + "disable": "rgba(128, 128, 128, 0.9)", + "ok": "rgba(50, 128, 45, 0.9)", + "warn": "rgba(237, 129, 40, 0.9)" + }, + "cornerRadius": 1, + "datasource": "$datasource", + "displayName": "", + "flipCard": false, + "flipTime": 5, + "fontFormat": "Regular", + "gridPos": { + "h": 3, + "w": 6, + "x": 18, + "y": 0 + }, + "id": 68, + "isAutoScrollOnOverflow": false, + "isGrayOnNoData": false, + "isHideAlertsOnDisable": false, + "isIgnoreOKColors": false, + "links": [], + "options": { + "colorMode": "background", + "graphMode": "none", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + } + }, + "targets": [ + { + "aggregation": "Last", + "alias": "Active", + "decimals": 2, + "displayAliasType": "Always", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "count(ceph_mgr_status == 1) or vector(0)", + "format": "time_series", + "intervalFactor": 1, + "instant": true, + "legendFormat": "Active", + "refId": "A", + "units": "none", + "valueHandler": "Number Threshold" + }, + { + "aggregation": "Last", + "alias": "Standby", + "decimals": 2, + "displayAliasType": "Always", + "displayType": "Regular", + "displayValueWithAlias": "When Alias Displayed", + "expr": "count(ceph_mgr_status == 0) or vector(0)", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "Standby", + "refId": "B", + "units": "none", + "valueHandler": "Number Threshold" + } + ], + "title": "MGRs", + "type": "stat" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 2, + "format": "percentunit", + "gauge": { + "maxValue": 1, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 6, + "w": 6, + "x": 0, + "y": 6 + }, + "id": 47, + "interval": null, + "links": [], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(ceph_osd_stat_bytes_used)/sum(ceph_osd_stat_bytes)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used", + "refId": "A" + } + ], + "thresholds": "0.7,0.8", + "title": "Capacity used", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "gridPos": { + "h": 6, + "w": 9, + "x": 6, + "y": 6 + }, + "id": 53, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Active", + "color": "#508642", + "fill": 1, + "stack": "A" + }, + { + "alias": "Total", + "color": "#f9e2d2" + }, + { + "alias": "Degraded", + "color": "#eab839" + }, + { + "alias": "Undersized", + "color": "#f9934e" + }, + { + "alias": "Inconsistent", + "color": "#e24d42" + }, + { + "alias": "Down", + "color": "#bf1b00" + }, + { + "alias": "Inactive", + "color": "#bf1b00", + "fill": 4, + "linewidth": 0, + "stack": "A" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(ceph_pg_total)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Total", + "refId": "A" + }, + { + "expr": "sum(ceph_pg_active)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Active", + "refId": "B" + }, + { + "expr": "sum(ceph_pg_total - ceph_pg_active)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Inactive", + "refId": "G" + }, + { + "expr": "sum(ceph_pg_undersized)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Undersized", + "refId": "F" + }, + { + "expr": "sum(ceph_pg_degraded)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Degraded", + "refId": "C" + }, + { + "expr": "sum(ceph_pg_inconsistent)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Inconsistent", + "refId": "D" + }, + { + "expr": "sum(ceph_pg_down)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Down", + "refId": "E" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "PG States", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "gridPos": { + "h": 6, + "w": 9, + "x": 15, + "y": 6 + }, + "id": 66, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Avg Apply Latency", + "color": "#7eb26d" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "quantile(0.95, ceph_osd_apply_latency_ms)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Apply Latency P_95", + "refId": "A" + }, + { + "expr": "quantile(0.95, ceph_osd_commit_latency_ms)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Commit Latency P_95", + "refId": "B" + }, + { + "expr": "avg(ceph_osd_apply_latency_ms)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Avg Apply Latency", + "refId": "C" + }, + { + "expr": "avg(ceph_osd_commit_latency_ms)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Avg Commit Latency", + "refId": "D" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "OSD Latencies", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 9 + }, + "id": 45, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 0.5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "Reads", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(ceph_osd_op_w_in_bytes[1m]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Writes", + "refId": "A" + }, + { + "expr": "sum(irate(ceph_osd_op_r_out_bytes[1m]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Reads", + "refId": "B" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Cluster I/O", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 9 + }, + "id": 62, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(deriv(ceph_pool_stored[1m]))", + "format": "time_series", + "intervalFactor": 1, + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "In-/Egress", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "Bps", + "label": " Egress (-) / Ingress (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "cards": { + "cardPadding": null, + "cardRound": 1 + }, + "color": { + "cardColor": "rgb(0, 254, 255)", + "colorScale": "sqrt", + "colorScheme": "interpolateBlues", + "exponent": 0.5, + "min": null, + "mode": "spectrum" + }, + "dataFormat": "timeseries", + "datasource": "$datasource", + "gridPos": { + "h": 9, + "w": 6, + "x": 0, + "y": 15 + }, + "heatmap": {}, + "highlightCards": true, + "id": 55, + "legend": { + "show": true + }, + "links": [], + "span": 12, + "targets": [ + { + "expr": "ceph_osd_stat_bytes_used / ceph_osd_stat_bytes", + "format": "time_series", + "interval": "1m", + "intervalFactor": 1, + "legendFormat": "Util (%)", + "refId": "A", + "step": 60 + } + ], + "timeFrom": null, + "title": "OSD Capacity Utilization", + "tooltip": { + "show": true, + "showHistogram": false + }, + "type": "heatmap", + "xAxis": { + "show": true + }, + "xBucketNumber": null, + "xBucketSize": "", + "yAxis": { + "decimals": 2, + "format": "percentunit", + "logBase": 1, + "max": null, + "min": null, + "show": true, + "splitFactor": null + }, + "yBucketNumber": null, + "yBucketSize": null + }, + { + "cards": { + "cardPadding": null, + "cardRound": 1 + }, + "color": { + "cardColor": "#b4ff00", + "colorScale": "sqrt", + "colorScheme": "interpolateBlues", + "exponent": 0.5, + "mode": "spectrum" + }, + "dataFormat": "timeseries", + "datasource": "$datasource", + "gridPos": { + "h": 9, + "w": 6, + "x": 6, + "y": 15 + }, + "heatmap": {}, + "highlightCards": true, + "id": 59, + "legend": { + "show": true + }, + "links": [], + "targets": [ + { + "expr": "ceph_osd_numpg", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "#PGs", + "refId": "A" + } + ], + "title": "PGs per OSD", + "tooltip": { + "show": true, + "showHistogram": false + }, + "type": "heatmap", + "xAxis": { + "show": true + }, + "xBucketNumber": null, + "xBucketSize": "", + "yAxis": { + "decimals": null, + "format": "none", + "logBase": 1, + "max": null, + "min": null, + "show": true, + "splitFactor": null + }, + "yBucketNumber": null, + "yBucketSize": null + }, + { + "aliasColors": {}, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 15 + }, + "id": 64, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": false, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(ceph_osd_recovery_ops[1m]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Op/s", + "refId": "A" + } + ], + "thresholds": [], + "timeFrom": null, + "timeShift": null, + "title": "Recovery Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [] + }, + "yaxes": [ + { + "format": "ops", + "label": "Recovery Ops/s", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "refresh": "30s", + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph", + "cluster" + ], + "templating": { + "list": [ + { + "hide": 0, + "label": null, + "name": "datasource", + "options": [], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "auto": true, + "auto_count": 10, + "auto_min": "1m", + "current": { + "text": "auto", + "value": "$__auto_interval_interval" + }, + "datasource": null, + "hide": 0, + "includeAll": false, + "label": "Interval", + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "auto", + "value": "$__auto_interval_interval" + }, + { + "selected": false, + "text": "1m", + "value": "1m" + }, + { + "selected": false, + "text": "10m", + "value": "10m" + }, + { + "selected": false, + "text": "30m", + "value": "30m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + }, + { + "selected": false, + "text": "6h", + "value": "6h" + }, + { + "selected": false, + "text": "12h", + "value": "12h" + }, + { + "selected": false, + "text": "1d", + "value": "1d" + }, + { + "selected": false, + "text": "7d", + "value": "7d" + }, + { + "selected": false, + "text": "14d", + "value": "14d" + }, + { + "selected": false, + "text": "30d", + "value": "30d" + } + ], + "query": "1m,10m,30m,1h,6h,12h,1d,7d,14d,30d", + "refresh": 2, + "type": "interval" + } + ] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Ceph - Cluster", + "version": 13 + } diff --git a/monitoring/ceph-mixin/dashboards_out/cephfs-overview.json b/monitoring/ceph-mixin/dashboards_out/cephfs-overview.json new file mode 100644 index 000000000..3e7aeef45 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/cephfs-overview.json @@ -0,0 +1,362 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.3.2" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "MDS Performance", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*Reads/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(ceph_objecter_op_r{job=~\"$job\", ceph_daemon=~\"($mds_servers).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Read Ops", + "refId": "A" + }, + { + "expr": "sum(rate(ceph_objecter_op_w{job=~\"$job\", ceph_daemon=~\"($mds_servers).*\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Write Ops", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "MDS Workload - $mds_servers", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "none", + "label": "Reads(-) / Writes (+)", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "ceph_mds_server_handle_client_request{job=~\"$job\", ceph_daemon=~\"($mds_servers).*\"}", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ceph_daemon}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Client Request Load - $mds_servers", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "none", + "label": "Client Requests", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "MDS Server", + "multi": false, + "name": "mds_servers", + "options": [ ], + "query": "label_values(ceph_mds_inodes{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "MDS Performance", + "uid": "tbO9LAiZz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/host-details.json b/monitoring/ceph-mixin/dashboards_out/host-details.json new file mode 100644 index 000000000..7a5ac2591 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/host-details.json @@ -0,0 +1,1328 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.3.2" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + }, + { + "id": "singlestat", + "name": "Singlestat", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "$ceph_hosts System Overview", + "titleSize": "h6", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 3, + "x": 0, + "y": 1 + }, + "id": 3, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(sum by (ceph_daemon) (ceph_osd_metadata{job=~\"$job\", hostname='$ceph_hosts'}))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "OSDs", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "aliasColors": { + "interrupt": "#447EBC", + "steal": "#6D1F62", + "system": "#890F02", + "user": "#3F6833", + "wait": "#C15C17" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Shows the CPU breakdown. When multiple servers are selected, only the first host's cpu data is shown", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 6, + "x": 3, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (mode) (\n rate(node_cpu{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\", mode=~\"(irq|nice|softirq|steal|system|user|iowait)\"}[$__rate_interval]) or\n rate(node_cpu_seconds_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\", mode=~\"(irq|nice|softirq|steal|system|user|iowait)\"}[$__rate_interval])\n) / (\n scalar(\n sum(rate(node_cpu{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_cpu_seconds_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]))\n ) * 100\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{mode}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilization", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percent", + "label": "% Utilization", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + "Available": "#508642", + "Free": "#508642", + "Total": "#bf1b00", + "Used": "#bf1b00", + "total": "#bf1b00", + "used": "#0a50a1" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 6, + "x": 9, + "y": 1 + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "total", + "color": "#bf1b00", + "fill": 0, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_MemFree{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_MemFree_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Free", + "refId": "A" + }, + { + "expr": "node_memory_MemTotal{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_MemTotal_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "total", + "refId": "B" + }, + { + "expr": "(\n node_memory_Cached{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_Cached_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n) + (\n node_memory_Buffers{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_Buffers_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n) + (\n node_memory_Slab{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_Slab_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "buffers/cache", + "refId": "C" + }, + { + "expr": "(\n node_memory_MemTotal{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_MemTotal_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n) - (\n (\n node_memory_MemFree{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_MemFree_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n ) + (\n node_memory_Cached{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_Cached_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n ) + (\n node_memory_Buffers{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_Buffers_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n ) +\n (\n node_memory_Slab{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"} or\n node_memory_Slab_bytes{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}\n )\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "used", + "refId": "D" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "RAM Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": "RAM used", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Show the network load (rx,tx) across all interfaces (excluding loopback 'lo')", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 6, + "x": 15, + "y": 1 + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*tx/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (device) (\n rate(\n node_network_receive_bytes{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\",device!=\"lo\"}[$__rate_interval]) or\n rate(node_network_receive_bytes_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\",device!=\"lo\"}[$__rate_interval]\n )\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}.rx", + "refId": "A" + }, + { + "expr": "sum by (device) (\n rate(node_network_transmit_bytes{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\",device!=\"lo\"}[$__rate_interval]) or\n rate(node_network_transmit_bytes_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\",device!=\"lo\"}[$__rate_interval])\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}.tx", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Network Load", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "decbytes", + "label": "Send (-) / Receive (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 5, + "w": 3, + "x": 21, + "y": 1 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*tx/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_receive_drop{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_network_receive_drop_total{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}.rx", + "refId": "A" + }, + { + "expr": "rate(node_network_transmit_drop{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_network_transmit_drop_total{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}.tx", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Network drop rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "pps", + "label": "Send (-) / Receive (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Each OSD consists of a Journal/WAL partition and a data partition. The RAW Capacity shown is the sum of the data partitions across all OSDs on the selected OSD hosts.", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 3, + "x": 0, + "y": 6 + }, + "id": 8, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(\n ceph_osd_stat_bytes{job=~\"$job\"} and\n on (ceph_daemon) ceph_disk_occupation{job=~\"$job\", instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Raw Capacity", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 5, + "w": 3, + "x": 21, + "y": 6 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*tx/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_receive_errs{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_network_receive_errs_total{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}.rx", + "refId": "A" + }, + { + "expr": "rate(node_network_transmit_errs{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_network_transmit_errs_total{instance=~\"$ceph_hosts([\\\\\\\\.:].*)?\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}.tx", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Network error rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "pps", + "label": "Send (-) / Receive (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 11 + }, + "id": 10, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "OSD Disk Performance Statistics", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "For any OSD devices on the host, this chart shows the iops per physical device. Each device is shown by it's name and corresponding OSD id value", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 11, + "x": 0, + "y": 12 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*reads/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n (\n rate(node_disk_writes_completed{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_disk_writes_completed_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval])\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) * on(instance, device) group_left(ceph_daemon) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}({{ceph_daemon}}) writes", + "refId": "A" + }, + { + "expr": "label_replace(\n (\n rate(node_disk_reads_completed{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_disk_reads_completed_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval])\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) * on(instance, device) group_left(ceph_daemon) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\"},\"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}({{ceph_daemon}}) reads", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$ceph_hosts Disk IOPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "For OSD hosts, this chart shows the disk bandwidth (read bytes/sec + write bytes/sec) of the physical OSD device. Each device is shown by device name, and corresponding OSD id", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 11, + "x": 12, + "y": 12 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*read/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n (\n rate(node_disk_bytes_written{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_disk_written_bytes_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval])\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device)\n group_left(ceph_daemon) label_replace(\n label_replace(ceph_disk_occupation_human{job=~\"$job\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n )\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}({{ceph_daemon}}) write", + "refId": "A" + }, + { + "expr": "label_replace(\n (\n rate(node_disk_bytes_read{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]) or\n rate(node_disk_read_bytes_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval])\n ),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") * on(instance, device)\n group_left(ceph_daemon) label_replace(\n label_replace(ceph_disk_occupation_human{job=~\"$job\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n )\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}({{ceph_daemon}}) read", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$ceph_hosts Throughput by Disk", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "For OSD hosts, this chart shows the latency at the physical drive. Each drive is shown by device name, with it's corresponding OSD id", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 11, + "x": 0, + "y": 21 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "max by(instance, device) (label_replace(\n (rate(node_disk_write_time_seconds_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval])) /\n clamp_min(rate(node_disk_writes_completed_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]), 0.001) or\n (rate(node_disk_read_time_seconds_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval])) /\n clamp_min(rate(node_disk_reads_completed_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]), 0.001),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)) * on(instance, device) group_left(ceph_daemon) label_replace(\n label_replace(\n ceph_disk_occupation_human{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}({{ceph_daemon}})", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$ceph_hosts Disk Latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": "", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Show disk utilization % (util) of any OSD devices on the host by the physical device name and associated OSD id.", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 11, + "x": 12, + "y": 21 + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n (\n (rate(node_disk_io_time_ms{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]) / 10) or\n rate(node_disk_io_time_seconds_total{instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"}[$__rate_interval]) * 100\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) * on(instance, device) group_left(ceph_daemon) label_replace(\n label_replace(ceph_disk_occupation_human{job=~\"$job\", instance=~\"($ceph_hosts)([\\\\\\\\.:].*)?\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}({{ceph_daemon}})", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$ceph_hosts Disk utilization", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percent", + "label": "%Util", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "This table shows the 10 hosts with the highest number of slow ops", + "gridPos": { + "h": 8, + "w": 4, + "x": 0, + "y": 40 + }, + "id": 15, + "links": [ ], + "sort": { + "col": 2, + "desc": true + }, + "styles": [ + { + "alias": "Instance", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "instance", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Slow Ops", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n (sum by (instance)(ceph_daemon_health_metrics{type=\"SLOW_OPS\", ceph_daemon=~\"osd.*\"}))\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Top Slow Ops per Host", + "transform": "table", + "type": "table" + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin", + "overview" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Hostname", + "multi": false, + "name": "ceph_hosts", + "options": [ ], + "query": "label_values(instance)", + "refresh": 1, + "regex": "([^.:]*).*", + "sort": 3, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Host Details", + "uid": "rtOg0AiWz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/hosts-overview.json b/monitoring/ceph-mixin/dashboards_out/hosts-overview.json new file mode 100644 index 000000000..f1cd4c499 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/hosts-overview.json @@ -0,0 +1,894 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.3.2" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + }, + { + "id": "singlestat", + "name": "Singlestat", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 0, + "y": 0 + }, + "id": 2, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(sum by (hostname) (ceph_osd_metadata{job=~\"$job\"}))", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "OSD Hosts", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Average CPU busy across all hosts (OSD, RGW, MON etc) within the cluster", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 4, + "y": 0 + }, + "id": 3, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg(1 - (\n avg by(instance) (\n rate(node_cpu_seconds_total{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[$__rate_interval]) or\n rate(node_cpu{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[$__rate_interval])\n )\n))\n", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "AVG CPU Busy", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Average Memory Usage across all hosts in the cluster (excludes buffer/cache usage)", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 8, + "y": 0 + }, + "id": 4, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg ((\n (\n node_memory_MemTotal{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or\n node_memory_MemTotal_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}\n ) - ((\n node_memory_MemFree{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or\n node_memory_MemFree_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}) +\n (\n node_memory_Cached{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or\n node_memory_Cached_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}\n ) + (\n node_memory_Buffers{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or\n node_memory_Buffers_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}\n ) + (\n node_memory_Slab{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or\n node_memory_Slab_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}\n )\n )\n) / (\n node_memory_MemTotal{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"} or\n node_memory_MemTotal_bytes{instance=~\"($osd_hosts|$rgw_hosts|$mon_hosts|$mds_hosts).*\"}\n))\n", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "AVG RAM Utilization", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "IOPS Load at the device as reported by the OS on all OSD hosts", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 12, + "y": 0 + }, + "id": 5, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum ((\n rate(node_disk_reads_completed{instance=~\"($osd_hosts).*\"}[$__rate_interval]) or\n rate(node_disk_reads_completed_total{instance=~\"($osd_hosts).*\"}[$__rate_interval])\n) + (\n rate(node_disk_writes_completed{instance=~\"($osd_hosts).*\"}[$__rate_interval]) or\n rate(node_disk_writes_completed_total{instance=~\"($osd_hosts).*\"}[$__rate_interval])\n))\n", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Physical IOPS", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Average Disk utilization for all OSD data devices (i.e. excludes journal/WAL)", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 16, + "y": 0 + }, + "id": 6, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "avg (\n label_replace(\n (rate(node_disk_io_time_ms[$__rate_interval]) / 10 ) or\n (rate(node_disk_io_time_seconds_total[$__rate_interval]) * 100),\n \"instance\", \"$1\", \"instance\", \"([^.:]*).*\"\n ) * on(instance, device) group_left(ceph_daemon) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", instance=~\"($osd_hosts).*\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^.:]*).*\"\n )\n)\n", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "AVG Disk Utilization", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Total send/receive network load across all hosts in the ceph cluster", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 5, + "w": 4, + "x": 20, + "y": 0 + }, + "id": 7, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum (\n (\n rate(node_network_receive_bytes{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[$__rate_interval]) or\n rate(node_network_receive_bytes_total{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[$__rate_interval])\n ) unless on (device, instance)\n label_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\")\n) +\nsum (\n (\n rate(node_network_transmit_bytes{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[$__rate_interval]) or\n rate(node_network_transmit_bytes_total{instance=~\"($osd_hosts|mon_hosts|mds_hosts|rgw_hosts).*\",device!=\"lo\"}[$__rate_interval])\n ) unless on (device, instance)\n label_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\")\n)\n", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Network Load", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Show the top 10 busiest hosts by cpu", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 5 + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "topk(10,\n 100 * (\n 1 - (\n avg by(instance) (\n rate(node_cpu_seconds_total{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[$__rate_interval]) or\n rate(node_cpu{mode='idle',instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\"}[$__rate_interval])\n )\n )\n )\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Busy - Top 10 Hosts", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percent", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Top 10 hosts by network load", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 5 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "topk(10, (sum by(instance) (\n(\n rate(node_network_receive_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[$__rate_interval]) or\n rate(node_network_receive_bytes_total{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[$__rate_interval])\n) +\n(\n rate(node_network_transmit_bytes{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[$__rate_interval]) or\n rate(node_network_transmit_bytes_total{instance=~\"($osd_hosts|$mon_hosts|$mds_hosts|$rgw_hosts).*\",device!=\"lo\"}[$__rate_interval])\n) unless on (device, instance)\n label_replace((bonding_slaves > 0), \"device\", \"$1\", \"master\", \"(.+)\"))\n))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Network Load - Top 10 Hosts", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "osd_hosts", + "options": [ ], + "query": "label_values(ceph_disk_occupation{job=~\"$job\"}, exported_instance)", + "refresh": 1, + "regex": "([^.]*).*", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "mon_hosts", + "options": [ ], + "query": "label_values(ceph_mon_metadata{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "mon.(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "mds_hosts", + "options": [ ], + "query": "label_values(ceph_mds_inodes{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "mds.(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "rgw_hosts", + "options": [ ], + "query": "label_values(ceph_rgw_metadata{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "rgw.(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Host Overview", + "uid": "y0KGL0iZz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/osd-device-details.json b/monitoring/ceph-mixin/dashboards_out/osd-device-details.json new file mode 100644 index 000000000..384516fb0 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/osd-device-details.json @@ -0,0 +1,871 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.3.2" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "OSD Performance", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "read", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_osd_op_r_latency_sum{job=~\"$job\", ceph_daemon=~\"$osd\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{job=~\"$job\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "read", + "refId": "A" + }, + { + "expr": "rate(ceph_osd_op_w_latency_sum{job=~\"$job\", ceph_daemon=~\"$osd\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{job=~\"$job\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "write", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$osd Latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 6, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "Reads", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_osd_op_r{job=~\"$job\", ceph_daemon=~\"$osd\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Reads", + "refId": "A" + }, + { + "expr": "rate(ceph_osd_op_w{job=~\"$job\", ceph_daemon=~\"$osd\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Writes", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$osd R/W IOPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 12, + "y": 1 + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "Read Bytes", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_osd_op_r_out_bytes{job=~\"$job\", ceph_daemon=~\"$osd\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Read Bytes", + "refId": "A" + }, + { + "expr": "rate(ceph_osd_op_w_in_bytes{job=~\"$job\", ceph_daemon=~\"$osd\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Write Bytes", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$osd R/W Bytes", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 6, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Physical Device Performance", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 0, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*Reads/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "(\n label_replace(\n rate(node_disk_read_time_seconds_total{}[$__rate_interval]) /\n rate(node_disk_reads_completed_total{}[$__rate_interval]),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n ) and on (instance, device) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", ceph_daemon=~\"$osd\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n )\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}}/{{device}} Reads", + "refId": "A" + }, + { + "expr": "(\n label_replace(\n rate(node_disk_write_time_seconds_total{}[$__rate_interval]) /\n rate(node_disk_writes_completed_total{}[$__rate_interval]),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\") and on (instance, device)\n label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n )\n )\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}}/{{device}} Writes", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Physical Device Latency for $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 6, + "y": 11 + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*Reads/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n rate(node_disk_writes_completed_total{}[$__rate_interval]),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) and on (instance, device) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", ceph_daemon=~\"$osd\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} on {{instance}} Writes", + "refId": "A" + }, + { + "expr": "label_replace(\n rate(node_disk_reads_completed_total{}[$__rate_interval]),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) and on (instance, device) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", ceph_daemon=~\"$osd\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} on {{instance}} Reads", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Physical Device R/W IOPS for $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 12, + "y": 11 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/.*Reads/", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n rate(node_disk_read_bytes_total{}[$__rate_interval]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) and on (instance, device) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", ceph_daemon=~\"$osd\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}} {{device}} Reads", + "refId": "A" + }, + { + "expr": "label_replace(\n rate(node_disk_written_bytes_total{}[$__rate_interval]), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) and on (instance, device) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", ceph_daemon=~\"$osd\"},\n \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}} {{device}} Writes", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Physical Device R/W Bytes for $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 6, + "x": 18, + "y": 11 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n rate(node_disk_io_time_seconds_total{}[$__rate_interval]),\n \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n) and on (instance, device) label_replace(\n label_replace(\n ceph_disk_occupation_human{job=~\"$job\", ceph_daemon=~\"$osd\"}, \"device\", \"$1\", \"device\", \"/dev/(.*)\"\n ), \"instance\", \"$1\", \"instance\", \"([^:.]*).*\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} on {{instance}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Physical Device Util% for $osd", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "OSD", + "multi": false, + "name": "osd", + "options": [ ], + "query": "label_values(ceph_osd_metadata{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-3h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "OSD device details", + "uid": "CrAHE0iZz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/osds-overview.json b/monitoring/ceph-mixin/dashboards_out/osds-overview.json new file mode 100644 index 000000000..b34c66422 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/osds-overview.json @@ -0,0 +1,1048 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.0.0" + }, + { + "id": "grafana-piechart-panel", + "name": "Pie Chart", + "type": "panel", + "version": "1.3.3" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + }, + { + "id": "table", + "name": "Table", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "aliasColors": { + "@95%ile": "#e0752d" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 8, + "x": 0, + "y": 0 + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg (\n rate(ceph_osd_op_r_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{job=~\"$job\"}[$__rate_interval]) * 1000\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "AVG read", + "refId": "A" + }, + { + "expr": "max(\n rate(ceph_osd_op_r_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{job=~\"$job\"}[$__rate_interval]) * 1000\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "MAX read", + "refId": "B" + }, + { + "expr": "quantile(0.95,\n (\n rate(ceph_osd_op_r_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{job=~\"$job\"}[$__rate_interval])\n * 1000\n )\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "@95%ile", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "OSD Read Latencies", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + } + ] + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "This table shows the osd's that are delivering the 10 highest read latencies within the cluster", + "gridPos": { + "h": 8, + "w": 4, + "x": 8, + "y": 0 + }, + "id": 3, + "links": [ ], + "sort": { + "col": 2, + "desc": true + }, + "styles": [ + { + "alias": "OSD ID", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "ceph_daemon", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Latency (ms)", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n (sort(\n (\n rate(ceph_osd_op_r_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{job=~\"$job\"}[$__rate_interval]) *\n 1000\n )\n ))\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest READ Latencies", + "transform": "table", + "type": "table" + }, + { + "aliasColors": { + "@95%ile write": "#e0752d" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 8, + "x": 12, + "y": 0 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "avg(\n rate(ceph_osd_op_w_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{job=~\"$job\"}[$__rate_interval])\n * 1000\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "AVG write", + "refId": "A" + }, + { + "expr": "max(\n rate(ceph_osd_op_w_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{job=~\"$job\"}[$__rate_interval]) *\n 1000\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "MAX write", + "refId": "B" + }, + { + "expr": "quantile(0.95, (\n rate(ceph_osd_op_w_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{job=~\"$job\"}[$__rate_interval]) *\n 1000\n))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "@95%ile write", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "OSD Write Latencies", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + } + ] + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "This table shows the osd's that are delivering the 10 highest write latencies within the cluster", + "gridPos": { + "h": 8, + "w": 4, + "x": 20, + "y": 0 + }, + "id": 5, + "links": [ ], + "sort": { + "col": 2, + "desc": true + }, + "styles": [ + { + "alias": "OSD ID", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "ceph_daemon", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Latency (ms)", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n (sort(\n (rate(ceph_osd_op_w_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{job=~\"$job\"}[$__rate_interval]) *\n 1000)\n ))\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest WRITE Latencies", + "transform": "table", + "type": "table" + }, + { + "aliasColors": { }, + "datasource": "$datasource", + "description": "", + "gridPos": { + "h": 8, + "w": 4, + "x": 0, + "y": 8 + }, + "id": 6, + "legend": { + "percentage": true, + "show": true, + "values": true + }, + "legendType": "Under graph", + "pieType": "pie", + "targets": [ + { + "expr": "count by (device_class) (ceph_osd_metadata{job=~\"$job\"})", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device_class}}", + "refId": "A" + } + ], + "title": "OSD Types Summary", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { + "Non-Encrypted": "#E5AC0E" + }, + "datasource": "$datasource", + "description": "", + "gridPos": { + "h": 8, + "w": 4, + "x": 4, + "y": 8 + }, + "id": 7, + "legend": { + "percentage": true, + "show": true, + "values": true + }, + "legendType": "Under graph", + "pieType": "pie", + "targets": [ + { + "expr": "count(ceph_bluefs_wal_total_bytes{job=~\"$job\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "bluestore", + "refId": "A" + }, + { + "expr": "absent(ceph_bluefs_wal_total_bytes{job=~\"$job\"}) * count(ceph_osd_metadata{job=~\"$job\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "filestore", + "refId": "B" + } + ], + "title": "OSD Objectstore Types", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { }, + "datasource": "$datasource", + "description": "The pie chart shows the various OSD sizes used within the cluster", + "gridPos": { + "h": 8, + "w": 4, + "x": 8, + "y": 8 + }, + "id": 8, + "legend": { + "percentage": true, + "show": true, + "values": true + }, + "legendType": "Under graph", + "pieType": "pie", + "targets": [ + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} < 1099511627776)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<1TB", + "refId": "A" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 1099511627776 < 2199023255552)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<2TB", + "refId": "B" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 2199023255552 < 3298534883328)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<3TB", + "refId": "C" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 3298534883328 < 4398046511104)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<4TB", + "refId": "D" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 4398046511104 < 6597069766656)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<6TB", + "refId": "E" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 6597069766656 < 8796093022208)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<8TB", + "refId": "F" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 8796093022208 < 10995116277760)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<10TB", + "refId": "G" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 10995116277760 < 13194139533312)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<12TB", + "refId": "H" + }, + { + "expr": "count(ceph_osd_stat_bytes{job=~\"$job\"} >= 13194139533312)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "<12TB+", + "refId": "I" + } + ], + "title": "OSD Size Summary", + "type": "grafana-piechart-panel", + "valueName": "current" + }, + { + "aliasColors": { }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 8, + "x": 12, + "y": 8 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "ceph_osd_numpg{job=~\"$job\"}", + "format": "time_series", + "instant": true, + "intervalFactor": 1, + "legendFormat": "PGs per OSD", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Distribution of PGs per OSD", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": 20, + "mode": "histogram", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "# of OSDs", + "logBase": 1, + "max": null, + "min": "0", + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": "0", + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "This gauge panel shows onode Hits ratio to help determine if increasing RAM per OSD could help improve the performance of the cluster", + "format": "percentunit", + "gauge": { + "maxValue": 1, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 8, + "w": 4, + "x": 20, + "y": 8 + }, + "id": 10, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(ceph_bluestore_onode_hits{job=~\"$job\"}) / (\n sum(ceph_bluestore_onode_hits{job=~\"$job\"}) +\n sum(ceph_bluestore_onode_misses{job=~\"$job\"})\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": ".75", + "title": "OSD onode Hits Ratio", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 16 + }, + "id": 11, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "R/W Profile", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Show the read/write workload profile overtime", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 24, + "x": 0, + "y": 17 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "round(sum(rate(ceph_pool_rd{job=~\"$job\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Reads", + "refId": "A" + }, + { + "expr": "round(sum(rate(ceph_pool_wr{job=~\"$job\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Writes", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Read/Write Profile", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "This table shows the 10 OSDs with the highest number of slow ops", + "gridPos": { + "h": 8, + "w": 4, + "x": 0, + "y": 20 + }, + "id": 13, + "links": [ ], + "sort": { + "col": 2, + "desc": true + }, + "styles": [ + { + "alias": "OSD ID", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "ceph_daemon", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Slow Ops", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n (ceph_daemon_health_metrics{type=\"SLOW_OPS\", ceph_daemon=~\"osd.*\"})\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Top Slow Ops", + "transform": "table", + "type": "table" + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "OSD Overview", + "uid": "lo02I1Aiz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/pool-detail.json b/monitoring/ceph-mixin/dashboards_out/pool-detail.json new file mode 100644 index 000000000..dc8b4152a --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/pool-detail.json @@ -0,0 +1,708 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.3.2" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + }, + { + "id": "singlestat", + "name": "Singlestat", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": true, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "percentunit", + "gauge": { + "maxValue": 1, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 7, + "w": 7, + "x": 0, + "y": 0 + }, + "id": 2, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": true + }, + "tableColumn": "", + "targets": [ + { + "expr": "(ceph_pool_stored{job=~\"$job\"} / (ceph_pool_stored{job=~\"$job\"} + ceph_pool_max_avail{job=~\"$job\"})) *\n on(pool_id) group_left(instance, name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": ".7,.8", + "title": "Capacity used", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": 100, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Time till pool is full assuming the average fill rate of the last 6 hours", + "format": "s", + "gauge": { + "maxValue": false, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 7, + "w": 5, + "x": 7, + "y": 0 + }, + "id": 3, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": "" + }, + "tableColumn": "", + "targets": [ + { + "expr": "(ceph_pool_max_avail{job=~\"$job\"} / deriv(ceph_pool_stored{job=~\"$job\"}[6h])) *\n on(pool_id) group_left(instance, name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"} > 0\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "current", + "title": "Time till full", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": false + }, + { + "aliasColors": { + "read_op_per_sec": "#3F6833", + "write_op_per_sec": "#E5AC0E" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 0 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "deriv(ceph_pool_objects{job=~\"$job\"}[1m]) *\n on(pool_id) group_left(instance, name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Objects per second", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$pool_name Object Ingress/Egress", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ops", + "label": "Objects out(-) / in(+) ", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + "read_op_per_sec": "#3F6833", + "write_op_per_sec": "#E5AC0E" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 7 + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "reads", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_pool_rd{job=~\"$job\"}[$__rate_interval]) *\n on(pool_id) group_left(instance,name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "reads", + "refId": "A" + }, + { + "expr": "rate(ceph_pool_wr{job=~\"$job\"}[$__rate_interval]) *\n on(pool_id) group_left(instance, name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "writes", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$pool_name Client IOPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "iops", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + "read_op_per_sec": "#3F6833", + "write_op_per_sec": "#E5AC0E" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 7 + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "reads", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_pool_rd_bytes{job=~\"$job\"}[$__rate_interval]) +\n on(pool_id) group_left(instance, name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "reads", + "refId": "A" + }, + { + "expr": "rate(ceph_pool_wr_bytes{job=~\"$job\"}[$__rate_interval]) +\n on(pool_id) group_left(instance,name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "writes", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$pool_name Client Throughput", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": "Read (-) / Write (+)", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + "read_op_per_sec": "#3F6833", + "write_op_per_sec": "#E5AC0E" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 14 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "ceph_pool_objects{job=~\"$job\"} *\n on(pool_id) group_left(instance,name) ceph_pool_metadata{job=~\"$job\", name=~\"$pool_name\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Number of Objects", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$pool_name Objects", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "Objects", + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 22, + "style": "dark", + "tags": [ + "ceph-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Pool Name", + "multi": false, + "name": "pool_name", + "options": [ ], + "query": "label_values(ceph_pool_metadata{job=~\"$job\"}, name)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Ceph Pool Details", + "uid": "-xyV8KCiz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/pool-overview.json b/monitoring/ceph-mixin/dashboards_out/pool-overview.json new file mode 100644 index 000000000..7f042aa5b --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/pool-overview.json @@ -0,0 +1,1542 @@ +{ + "__inputs": [ ], + "__requires": [ ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 0, + "y": 0 + }, + "id": 2, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(ceph_pool_metadata{job=~\"$job\"})", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Pools", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Count of the pools that have compression enabled", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 3, + "y": 0 + }, + "id": 3, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "count(ceph_pool_metadata{job=~\"$job\", compression_mode!=\"none\"})", + "format": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Pools with Compression", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Total raw capacity available to the cluster", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 6, + "y": 0 + }, + "id": 4, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(ceph_osd_stat_bytes{job=~\"$job\"})", + "format": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Total Raw Capacity", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Total raw capacity consumed by user data and associated overheads (metadata + redundancy)", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 9, + "y": 0 + }, + "id": 5, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(ceph_pool_bytes_used{job=~\"$job\"})", + "format": "", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Raw Capacity Consumed", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Total of client data stored in the cluster", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 12, + "y": 0 + }, + "id": 6, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(ceph_pool_stored{job=~\"$job\"})", + "format": "", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Logical Stored ", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "A compression saving is determined as the data eligible to be compressed minus the capacity used to store the data after compression", + "format": "bytes", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 15, + "y": 0 + }, + "id": 7, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(\n ceph_pool_compress_under_bytes{job=~\"$job\"} -\n ceph_pool_compress_bytes_used{job=~\"$job\"}\n)\n", + "format": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Compression Savings", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "Indicates how suitable the data is within the pools that are/have been enabled for compression - averaged across all pools holding compressed data", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 18, + "y": 0 + }, + "id": 8, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "(\n sum(ceph_pool_compress_under_bytes{job=~\"$job\"} > 0) /\n sum(ceph_pool_stored_raw{job=~\"$job\"} and ceph_pool_compress_under_bytes{job=~\"$job\"} > 0)\n) * 100\n", + "format": "table", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Compression Eligibility", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "description": "This factor describes the average ratio of data eligible to be compressed divided by the data actually stored. It does not account for data written that was ineligible for compression (too small, or compression yield too low)", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 3, + "w": 3, + "x": 21, + "y": 0 + }, + "id": 9, + "interval": null, + "links": [ ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(\n ceph_pool_compress_under_bytes{job=~\"$job\"} > 0)\n / sum(ceph_pool_compress_bytes_used{job=~\"$job\"} > 0\n)\n", + "format": "", + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Compression Factor", + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "", + "gridPos": { + "h": 6, + "w": 24, + "x": 0, + "y": 3 + }, + "id": 10, + "links": [ ], + "sort": { + "col": 5, + "desc": true + }, + "styles": [ + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Time", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "instance", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "job", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Pool Name", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "name", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Pool ID", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "pool_id", + "thresholds": [ ], + "type": "hidden", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "Compression Factor", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #A", + "thresholds": [ ], + "type": "number", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "% Used", + "colorMode": "value", + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #D", + "thresholds": [ + "70", + "85" + ], + "type": "number", + "unit": "percentunit", + "valueMaps": [ ] + }, + { + "alias": "Usable Free", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #B", + "thresholds": [ ], + "type": "number", + "unit": "bytes", + "valueMaps": [ ] + }, + { + "alias": "Compression Eligibility", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #C", + "thresholds": [ ], + "type": "number", + "unit": "percent", + "valueMaps": [ ] + }, + { + "alias": "Compression Savings", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #E", + "thresholds": [ ], + "type": "number", + "unit": "bytes", + "valueMaps": [ ] + }, + { + "alias": "Growth (5d)", + "colorMode": "value", + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #F", + "thresholds": [ + "0", + "0" + ], + "type": "number", + "unit": "bytes", + "valueMaps": [ ] + }, + { + "alias": "IOPS", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #G", + "thresholds": [ ], + "type": "number", + "unit": "none", + "valueMaps": [ ] + }, + { + "alias": "Bandwidth", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #H", + "thresholds": [ ], + "type": "number", + "unit": "Bps", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "__name__", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "type", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "compression_mode", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Type", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "description", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Stored", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #J", + "thresholds": [ ], + "type": "number", + "unit": "bytes", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #I", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Compression", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value #K", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ + { + "text": "ON", + "value": "1" + } + ] + } + ], + "targets": [ + { + "expr": "(\n ceph_pool_compress_under_bytes{job=~\"$job\"} /\n ceph_pool_compress_bytes_used{job=~\"$job\"} > 0\n) and on(pool_id) (\n (\n (ceph_pool_compress_under_bytes{job=~\"$job\"} > 0) /\n ceph_pool_stored_raw{job=~\"$job\"}\n ) * 100 > 0.5\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "A", + "refId": "A" + }, + { + "expr": "ceph_pool_max_avail{job=~\"$job\"} *\n on(pool_id) group_left(name) ceph_pool_metadata{job=~\"$job\"}\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "B", + "refId": "B" + }, + { + "expr": "(\n (ceph_pool_compress_under_bytes{job=~\"$job\"} > 0) /\n ceph_pool_stored_raw{job=~\"$job\"}\n) * 100\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "C", + "refId": "C" + }, + { + "expr": "ceph_pool_percent_used{job=~\"$job\"} *\n on(pool_id) group_left(name) ceph_pool_metadata{job=~\"$job\"}\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "D", + "refId": "D" + }, + { + "expr": "ceph_pool_compress_under_bytes{job=~\"$job\"} -\n ceph_pool_compress_bytes_used{job=~\"$job\"} > 0\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "E", + "refId": "E" + }, + { + "expr": "delta(ceph_pool_stored{job=~\"$job\"}[5d])", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "F", + "refId": "F" + }, + { + "expr": "rate(ceph_pool_rd{job=~\"$job\"}[$__rate_interval])\n + rate(ceph_pool_wr{job=~\"$job\"}[$__rate_interval])\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "G", + "refId": "G" + }, + { + "expr": "rate(ceph_pool_rd_bytes{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_pool_wr_bytes{job=~\"$job\"}[$__rate_interval])\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "H", + "refId": "H" + }, + { + "expr": "ceph_pool_metadata{job=~\"$job\"}", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "I", + "refId": "I" + }, + { + "expr": "ceph_pool_stored{job=~\"$job\"} * on(pool_id) group_left ceph_pool_metadata{job=~\"$job\"}", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "J", + "refId": "J" + }, + { + "expr": "ceph_pool_metadata{job=~\"$job\", compression_mode!=\"none\"}", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "K", + "refId": "K" + }, + { + "expr": "", + "format": "", + "intervalFactor": "", + "legendFormat": "L", + "refId": "L" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Pool Overview", + "transform": "table", + "type": "table" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "This chart shows the sum of read and write IOPS from all clients by pool", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 9 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "topk($topk,\n round(\n (\n rate(ceph_pool_rd{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_pool_wr{job=~\"$job\"}[$__rate_interval])\n ), 1\n ) * on(pool_id) group_left(instance,name) ceph_pool_metadata{job=~\"$job\"})\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{name}} ", + "refId": "A" + }, + { + "expr": "topk($topk,\n rate(ceph_pool_wr{job=~\"$job\"}[$__rate_interval]) +\n on(pool_id) group_left(instance,name) ceph_pool_metadata{job=~\"$job\"}\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{name}} - write", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $topk Client IOPS by Pool", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "IOPS", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "The chart shows the sum of read and write bytes from all clients, by pool", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 9 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "topk($topk,\n (\n rate(ceph_pool_rd_bytes{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_pool_wr_bytes{job=~\"$job\"}[$__rate_interval])\n ) * on(pool_id) group_left(instance, name) ceph_pool_metadata{job=~\"$job\"}\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{name}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Top $topk Client Bandwidth by Pool", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": "Throughput", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Historical view of capacity usage, to help identify growth and trends in pool consumption", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 17 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "ceph_pool_bytes_used{job=~\"$job\"} * on(pool_id) group_right ceph_pool_metadata{job=~\"$job\"}", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{name}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Pool Capacity Usage (RAW)", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": "Capacity Used", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 22, + "style": "dark", + "tags": [ + "ceph-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "15", + "value": "15" + }, + "hide": 0, + "includeAll": false, + "label": "TopK", + "multi": false, + "name": "topk", + "options": [ + { + "text": "15", + "value": "15" + } + ], + "query": "15", + "refresh": 0, + "type": "custom" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "Ceph Pools Overview", + "uid": "z99hzWtmk", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/radosgw-detail.json b/monitoring/ceph-mixin/dashboards_out/radosgw-detail.json new file mode 100644 index 000000000..a0f8f3537 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/radosgw-detail.json @@ -0,0 +1,542 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.0.0" + }, + { + "id": "grafana-piechart-panel", + "name": "Pie Chart", + "type": "panel", + "version": "1.3.3" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "RGW Host Detail : $rgw_servers", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 6, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (instance_id) (\n rate(ceph_rgw_get_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_get_initial_lat_count{job=~\"$job\"}[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "GET {{ceph_daemon}}", + "refId": "A" + }, + { + "expr": "sum by (instance_id) (\n rate(ceph_rgw_put_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_put_initial_lat_count{job=~\"$job\"}[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "PUT {{ceph_daemon}}", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "$rgw_servers GET/PUT Latencies", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 7, + "x": 6, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_rgw_get_b{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "GETs {{ceph_daemon}}", + "refId": "A" + }, + { + "expr": "rate(ceph_rgw_put_b{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon)\n ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "PUTs {{ceph_daemon}}", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Bandwidth by HTTP Operation", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + "GETs": "#7eb26d", + "Other": "#447ebc", + "PUTs": "#eab839", + "Requests": "#3f2b5b", + "Requests Failed": "#bf1b00" + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 7, + "x": 13, + "y": 1 + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_rgw_failed_req{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\",ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Requests Failed {{ceph_daemon}}", + "refId": "A" + }, + { + "expr": "rate(ceph_rgw_get{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "GETs {{ceph_daemon}}", + "refId": "B" + }, + { + "expr": "rate(ceph_rgw_put{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "PUTs {{ceph_daemon}}", + "refId": "C" + }, + { + "expr": "(\n rate(ceph_rgw_req{job=~\"$job\"}[$__rate_interval]) -\n (\n rate(ceph_rgw_get{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_rgw_put{job=~\"$job\"}[$__rate_interval])\n )\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Other {{ceph_daemon}}", + "refId": "D" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "HTTP Request Breakdown", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + "Failures": "#bf1b00", + "GETs": "#7eb26d", + "Other (HEAD,POST,DELETE)": "#447ebc", + "PUTs": "#eab839", + "Requests": "#3f2b5b" + }, + "datasource": "$datasource", + "description": "", + "gridPos": { + "h": 8, + "w": 4, + "x": 20, + "y": 1 + }, + "id": 6, + "legend": { + "percentage": true, + "show": true, + "values": true + }, + "legendType": "Under graph", + "pieType": "pie", + "targets": [ + { + "expr": "rate(ceph_rgw_failed_req{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Failures {{ceph_daemon}}", + "refId": "A" + }, + { + "expr": "rate(ceph_rgw_get{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "GETs {{ceph_daemon}}", + "refId": "B" + }, + { + "expr": "rate(ceph_rgw_put{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "PUTs {{ceph_daemon}}", + "refId": "C" + }, + { + "expr": "(\n rate(ceph_rgw_req{job=~\"$job\"}[$__rate_interval]) -\n (\n rate(ceph_rgw_get{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_rgw_put{job=~\"$job\"}[$__rate_interval])\n )\n) * on (instance_id) group_left (ceph_daemon)\n ceph_rgw_metadata{job=~\"$job\", ceph_daemon=~\"$rgw_servers\"}\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Other (DELETE,LIST) {{ceph_daemon}}", + "refId": "D" + } + ], + "title": "Workload Breakdown", + "type": "grafana-piechart-panel", + "valueName": "current" + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin", + "overview" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "", + "multi": false, + "name": "rgw_servers", + "options": [ ], + "query": "label_values(ceph_rgw_metadata{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "RGW Instance Detail", + "uid": "x5ARzZtmk", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/radosgw-overview.json b/monitoring/ceph-mixin/dashboards_out/radosgw-overview.json new file mode 100644 index 000000000..77d69e4f3 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/radosgw-overview.json @@ -0,0 +1,1266 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.0.0" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "RGW Overview - All Gateways", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n rate(ceph_rgw_get_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_get_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "GET {{rgw_host}}", + "refId": "A" + }, + { + "expr": "label_replace(\n rate(ceph_rgw_put_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_put_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "PUT {{rgw_host}}", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Average GET/PUT Latencies by RGW Instance", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 7, + "x": 8, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (rgw_host) (\n label_replace(\n rate(ceph_rgw_req{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n )\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{rgw_host}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Total Requests/sec by RGW Instance", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of GET latency imbalance across RGW hosts", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 6, + "x": 15, + "y": 1 + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n rate(ceph_rgw_get_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_get_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{rgw_host}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "GET Latencies by RGW Instance", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Total bytes transferred in/out of all radosgw instances within the cluster", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 6, + "w": 8, + "x": 0, + "y": 8 + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(ceph_rgw_get_b{job=~\"$job\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "GETs", + "refId": "A" + }, + { + "expr": "sum(rate(ceph_rgw_put_b{job=~\"$job\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "PUTs", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Bandwidth Consumed by Type", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Total bytes transferred in/out through get/put operations, by radosgw instance", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 6, + "w": 7, + "x": 8, + "y": 8 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(sum by (instance_id) (\n rate(ceph_rgw_get_b{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_rgw_put_b{job=~\"$job\"}[$__rate_interval])) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{rgw_host}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Bandwidth by RGW Instance", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Latencies are shown stacked, without a yaxis to provide a visual indication of PUT latency imbalance across RGW hosts", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 6, + "w": 6, + "x": 15, + "y": 8 + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "label_replace(\n rate(ceph_rgw_put_initial_lat_sum{job=~\"$job\"}[$__rate_interval]) /\n rate(ceph_rgw_put_initial_lat_count{job=~\"$job\"}[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{job=~\"$job\"},\n \"rgw_host\", \"$1\", \"ceph_daemon\", \"rgw.(.*)\"\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{rgw_host}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "PUT Latencies by RGW Instance", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 12, + "w": 9, + "x": 0, + "y": 12 + }, + "id": 9, + "panels": [ ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "RGW Overview - HAProxy Metrics", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 5, + "x": 0, + "y": 12 + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + [ + { + "alias": "/.*Back.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*1.*/" + }, + { + "alias": "/.*2.*/" + }, + { + "alias": "/.*3.*/" + }, + { + "alias": "/.*4.*/" + }, + { + "alias": "/.*5.*/" + }, + { + "alias": "/.*other.*/" + } + ] + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n haproxy_frontend_http_responses_total{code=~\"$code\", job=~\"$job_haproxy\", instance=~\"$ingress_service\", proxy=~\"frontend\"}[$__rate_interval]\n )\n) by (code)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Frontend {{ code }}", + "refId": "A" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_http_responses_total{code=~\"$code\", job=~\"$job_haproxy\", instance=~\"$ingress_service\", proxy=~\"backend\"}[$__rate_interval]\n )\n) by (code)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Backend {{ code }}", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Total responses by HTTP code", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 5, + "x": 5, + "y": 12 + }, + "id": 11, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + [ + { + "alias": "/.*Response.*/", + "transform": "negative-Y" + }, + { + "alias": "/.*Backend.*/", + "transform": "negative-Y" + } + ] + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n haproxy_frontend_http_requests_total{proxy=~\"frontend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Requests", + "refId": "A" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_response_errors_total{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Response errors", + "refId": "B" + }, + { + "expr": "sum(\n rate(\n haproxy_frontend_request_errors_total{proxy=~\"frontend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Requests errors", + "refId": "C" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_redispatch_warnings_total{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Backend redispatch", + "refId": "D" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_retry_warnings_total{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Backend retry", + "refId": "E" + }, + { + "expr": "sum(\n rate(\n haproxy_frontend_requests_denied_total{proxy=~\"frontend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Request denied", + "refId": "F" + }, + { + "expr": "sum(\n haproxy_backend_current_queue{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Backend Queued", + "refId": "G" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Total requests / responses", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 5, + "x": 10, + "y": 12 + }, + "id": 12, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + [ + { + "alias": "/.*Back.*/", + "transform": "negative-Y" + } + ] + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n haproxy_frontend_connections_total{proxy=~\"frontend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Front", + "refId": "A" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_connection_attempts_total{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Back", + "refId": "B" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_connection_errors_total{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n )\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Back errors", + "refId": "C" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Total number of connections", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 12, + "w": 6, + "x": 15, + "y": 12 + }, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + [ + { + "alias": "/.*OUT.*/", + "transform": "negative-Y" + } + ] + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n rate(\n haproxy_frontend_bytes_in_total{proxy=~\"frontend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n ) * 8\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "IN Front", + "refId": "A" + }, + { + "expr": "sum(\n rate(\n haproxy_frontend_bytes_out_total{proxy=~\"frontend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n ) * 8\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "OUT Front", + "refId": "B" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_bytes_in_total{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n ) * 8\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "IN Back", + "refId": "C" + }, + { + "expr": "sum(\n rate(\n haproxy_backend_bytes_out_total{proxy=~\"backend\", job=~\"$job_haproxy\", instance=~\"$ingress_service\"}[$__rate_interval]\n ) * 8\n) by (instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "OUT Back", + "refId": "D" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Current total of incoming / outgoing bytes", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin", + "overview" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "", + "multi": false, + "name": "rgw_servers", + "options": [ ], + "query": "label_values(ceph_rgw_metadata{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "RGW Server", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "HTTP Code", + "multi": false, + "name": "code", + "options": [ ], + "query": "label_values(haproxy_server_http_responses_total{job=~\"$job_haproxy\", instance=~\"$ingress_service\"}, code)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job haproxy", + "multi": true, + "name": "job_haproxy", + "options": [ ], + "query": "label_values(haproxy_server_status, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "Ingress Service", + "multi": false, + "name": "ingress_service", + "options": [ ], + "query": "label_values(haproxy_server_status{job=~\"$job_haproxy\"}, instance)", + "refresh": 1, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "RGW Overview", + "uid": "WAkugZpiz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/radosgw-sync-overview.json b/monitoring/ceph-mixin/dashboards_out/radosgw-sync-overview.json new file mode 100644 index 000000000..e0c3037d5 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/radosgw-sync-overview.json @@ -0,0 +1,504 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.0.0" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 0 + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_bytes_sum{job=~\"$job\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{source_zone}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Replication (throughput) from Source Zone", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 0 + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_bytes_count{job=~\"$job\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{source_zone}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Replication (objects) from Source Zone", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "Objects/s", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 0 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_poll_latency_sum{job=~\"$job\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{source_zone}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Polling Request Latency from Source Zone", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 7 + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (source_zone) (rate(ceph_data_sync_from_zone_fetch_errors{job=~\"$job\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{source_zone}}", + "refId": "A" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Unsuccessful Object Replications from Source Zone", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": "Count/s", + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin", + "overview" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "", + "multi": false, + "name": "rgw_servers", + "options": [ ], + "query": "label_values(ceph_rgw_metadata{job=~\"$job\"}, ceph_daemon)", + "refresh": 1, + "regex": "RGW Server", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "RGW Sync Overview", + "uid": "rgw-sync-overview", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/rbd-details.json b/monitoring/ceph-mixin/dashboards_out/rbd-details.json new file mode 100644 index 000000000..f64de312a --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/rbd-details.json @@ -0,0 +1,458 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.3.3" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "Detailed Performance of RBD Images (IOPS/Throughput/Latency)", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 8, + "x": 0, + "y": 0 + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_rbd_write_ops{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pool}} Write", + "refId": "A" + }, + { + "expr": "rate(ceph_rbd_read_ops{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pool}} Read", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "iops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "iops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 8, + "x": 8, + "y": 0 + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_rbd_write_bytes{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pool}} Write", + "refId": "A" + }, + { + "expr": "rate(ceph_rbd_read_bytes{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pool}} Read", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Throughput", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 8, + "x": 16, + "y": 0 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(ceph_rbd_write_latency_sum{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval]) /\n rate(ceph_rbd_write_latency_count{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pool}} Write", + "refId": "A" + }, + { + "expr": "rate(ceph_rbd_read_latency_sum{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval]) /\n rate(ceph_rbd_read_latency_count{job=~\"$job\", pool=\"$pool\", image=\"$image\"}[$__rate_interval])\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pool}} Read", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Average Latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ns", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ns", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "", + "multi": false, + "name": "pool", + "options": [ ], + "query": "label_values(pool)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "", + "multi": false, + "name": "image", + "options": [ ], + "query": "label_values(image)", + "refresh": 1, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "RBD Details", + "uid": "YhCYGcuZz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/dashboards_out/rbd-overview.json b/monitoring/ceph-mixin/dashboards_out/rbd-overview.json new file mode 100644 index 000000000..e017280e0 --- /dev/null +++ b/monitoring/ceph-mixin/dashboards_out/rbd-overview.json @@ -0,0 +1,737 @@ +{ + "__inputs": [ ], + "__requires": [ + { + "id": "grafana", + "name": "Grafana", + "type": "grafana", + "version": "5.4.2" + }, + { + "id": "graph", + "name": "Graph", + "type": "panel", + "version": "5.0.0" + }, + { + "id": "prometheus", + "name": "Prometheus", + "type": "datasource", + "version": "5.0.0" + }, + { + "id": "table", + "name": "Table", + "type": "panel", + "version": "5.0.0" + } + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "showIn": 0, + "tags": [ ], + "type": "dashboard" + } + ] + }, + "description": "", + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ ], + "panels": [ + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 0 + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "round(sum(rate(ceph_rbd_write_ops{job=~\"$job\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Writes", + "refId": "A" + }, + { + "expr": "round(sum(rate(ceph_rbd_read_ops{job=~\"$job\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Reads", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 0 + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "round(sum(rate(ceph_rbd_write_bytes{job=~\"$job\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Write", + "refId": "A" + }, + { + "expr": "round(sum(rate(ceph_rbd_read_bytes{job=~\"$job\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Read", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Throughput", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 0 + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "round(\n sum(rate(ceph_rbd_write_latency_sum{job=~\"$job\"}[$__rate_interval])) /\n sum(rate(ceph_rbd_write_latency_count{job=~\"$job\"}[$__rate_interval]))\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Write", + "refId": "A" + }, + { + "expr": "round(\n sum(rate(ceph_rbd_read_latency_sum{job=~\"$job\"}[$__rate_interval])) /\n sum(rate(ceph_rbd_read_latency_count{job=~\"$job\"}[$__rate_interval]))\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Read", + "refId": "B" + } + ], + "thresholds": [ ], + "timeFrom": null, + "timeShift": null, + "title": "Average Latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ ] + }, + "yaxes": [ + { + "format": "ns", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "", + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 7 + }, + "id": 5, + "links": [ ], + "sort": { + "col": 3, + "desc": true + }, + "styles": [ + { + "alias": "Pool", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "pool", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Image", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "image", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "IOPS", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "iops", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n (\n sort((\n rate(ceph_rbd_write_ops{job=~\"$job\"}[$__rate_interval]) +\n on (image, pool, namespace) rate(ceph_rbd_read_ops{job=~\"$job\"}[$__rate_interval])\n ))\n )\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest IOPS", + "transform": "table", + "type": "table" + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "", + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 7 + }, + "id": 6, + "links": [ ], + "sort": { + "col": 3, + "desc": true + }, + "styles": [ + { + "alias": "Pool", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "pool", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Image", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "image", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Throughput", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "Bps", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n sort(\n sum(\n rate(ceph_rbd_read_bytes{job=~\"$job\"}[$__rate_interval]) +\n rate(ceph_rbd_write_bytes{job=~\"$job\"}[$__rate_interval])\n ) by (pool, image, namespace)\n )\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest Throughput", + "transform": "table", + "type": "table" + }, + { + "columns": [ ], + "datasource": "$datasource", + "description": "", + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 7 + }, + "id": 7, + "links": [ ], + "sort": { + "col": 3, + "desc": true + }, + "styles": [ + { + "alias": "Pool", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "pool", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Image", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "image", + "thresholds": [ ], + "type": "string", + "unit": "short", + "valueMaps": [ ] + }, + { + "alias": "Latency", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "Value", + "thresholds": [ ], + "type": "number", + "unit": "ns", + "valueMaps": [ ] + }, + { + "alias": "", + "colorMode": null, + "colors": [ + "rgba(245, 54, 54, 0.9)", + "rgba(237, 129, 40, 0.89)", + "rgba(50, 172, 45, 0.97)" + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "mappingType": 1, + "pattern": "/.*/", + "thresholds": [ ], + "type": "hidden", + "unit": "short", + "valueMaps": [ ] + } + ], + "targets": [ + { + "expr": "topk(10,\n sum(\n rate(ceph_rbd_write_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n clamp_min(rate(ceph_rbd_write_latency_count{job=~\"$job\"}[$__rate_interval]), 1) +\n rate(ceph_rbd_read_latency_sum{job=~\"$job\"}[$__rate_interval]) /\n clamp_min(rate(ceph_rbd_read_latency_count{job=~\"$job\"}[$__rate_interval]), 1)\n ) by (pool, image, namespace)\n)\n", + "format": "table", + "instant": true, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest Latency", + "transform": "table", + "type": "table" + } + ], + "refresh": "30s", + "rows": [ ], + "schemaVersion": 16, + "style": "dark", + "tags": [ + "ceph-mixin", + "overview" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": "cluster", + "multi": true, + "name": "cluster", + "options": [ ], + "query": "label_values(ceph_osd_metadata, cluster)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ ], + "query": "label_values(ceph_osd_metadata{}, job)", + "refresh": 1, + "regex": "(.*)", + "sort": 1, + "tagValuesQuery": "", + "tags": [ ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "", + "title": "RBD Overview", + "uid": "41FrpeUiz", + "version": 0 +} diff --git a/monitoring/ceph-mixin/jsonnet-bundler-build.sh b/monitoring/ceph-mixin/jsonnet-bundler-build.sh new file mode 100755 index 000000000..d713cffb8 --- /dev/null +++ b/monitoring/ceph-mixin/jsonnet-bundler-build.sh @@ -0,0 +1,8 @@ +#!/bin/sh -ex + +JSONNET_VERSION="v0.4.0" +OUTPUT_DIR=${1:-$(pwd)} + +git clone -b ${JSONNET_VERSION} --depth 1 https://github.com/jsonnet-bundler/jsonnet-bundler +make -C jsonnet-bundler build +mv jsonnet-bundler/_output/jb ${OUTPUT_DIR} diff --git a/monitoring/ceph-mixin/jsonnetfile.json b/monitoring/ceph-mixin/jsonnetfile.json new file mode 100644 index 000000000..93f3316ec --- /dev/null +++ b/monitoring/ceph-mixin/jsonnetfile.json @@ -0,0 +1,15 @@ +{ + "version": 1, + "dependencies": [ + { + "source": { + "git": { + "remote": "https://github.com/grafana/grafonnet-lib.git", + "subdir": "grafonnet" + } + }, + "version": "master" + } + ], + "legacyImports": true +} diff --git a/monitoring/ceph-mixin/jsonnetfile.lock.json b/monitoring/ceph-mixin/jsonnetfile.lock.json new file mode 100644 index 000000000..3c9d38d93 --- /dev/null +++ b/monitoring/ceph-mixin/jsonnetfile.lock.json @@ -0,0 +1,16 @@ +{ + "version": 1, + "dependencies": [ + { + "source": { + "git": { + "remote": "https://github.com/grafana/grafonnet-lib.git", + "subdir": "grafonnet" + } + }, + "version": "30280196507e0fe6fa978a3e0eaca3a62844f817", + "sum": "342u++/7rViR/zj2jeJOjshzglkZ1SY+hFNuyCBFMdc=" + } + ], + "legacyImports": false +} diff --git a/monitoring/ceph-mixin/lint-jsonnet.sh b/monitoring/ceph-mixin/lint-jsonnet.sh new file mode 100755 index 000000000..6f7716269 --- /dev/null +++ b/monitoring/ceph-mixin/lint-jsonnet.sh @@ -0,0 +1,5 @@ +#!/bin/sh -e + +JSONNETS_FILES=$(find . -name 'vendor' -prune -o \ + -name '*.jsonnet' -print -o -name '*.libsonnet' -print) +jsonnetfmt "$@" ${JSONNETS_FILES} diff --git a/monitoring/ceph-mixin/mixin.libsonnet b/monitoring/ceph-mixin/mixin.libsonnet new file mode 100644 index 000000000..3c983a300 --- /dev/null +++ b/monitoring/ceph-mixin/mixin.libsonnet @@ -0,0 +1,3 @@ +(import 'config.libsonnet') + +(import 'dashboards.libsonnet') + +(import 'alerts.libsonnet') diff --git a/monitoring/ceph-mixin/prometheus_alerts.libsonnet b/monitoring/ceph-mixin/prometheus_alerts.libsonnet new file mode 100644 index 000000000..b7ec0da2f --- /dev/null +++ b/monitoring/ceph-mixin/prometheus_alerts.libsonnet @@ -0,0 +1,740 @@ +{ + _config:: error 'must provide _config', + + MultiClusterQuery():: + if $._config.showMultiCluster + then 'cluster,' + else '', + + MultiClusterSummary():: + if $._config.showMultiCluster + then ' on cluster {{ $labels.cluster }}' + else '', + + groups+: [ + { + name: 'cluster health', + rules: [ + { + alert: 'CephHealthError', + 'for': '5m', + expr: 'ceph_health_status == 2', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.2.1' }, + annotations: { + summary: 'Ceph is in the ERROR state%(cluster)s' % $.MultiClusterSummary(), + description: "The cluster state has been HEALTH_ERROR for more than 5 minutes%(cluster)s. Please check 'ceph health detail' for more information." % $.MultiClusterSummary(), + }, + }, + { + alert: 'CephHealthWarning', + 'for': '15m', + expr: 'ceph_health_status == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + summary: 'Ceph is in the WARNING state%(cluster)s' % $.MultiClusterSummary(), + description: "The cluster state has been HEALTH_WARN for more than 15 minutes%(cluster)s. Please check 'ceph health detail' for more information." % $.MultiClusterSummary(), + }, + }, + ], + }, + { + name: 'mon', + rules: [ + { + alert: 'CephMonDownQuorumAtRisk', + 'for': '30s', + expr: ||| + ( + (ceph_health_detail{name="MON_DOWN"} == 1) * on() ( + count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1) + ) + ) == 1 + |||, + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.3.1' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down', + summary: 'Monitor quorum is at risk%(cluster)s' % $.MultiClusterSummary(), + description: '{{ $min := query "floor(count(ceph_mon_metadata) / 2) + 1" | first | value }}Quorum requires a majority of monitors (x {{ $min }}) to be active. Without quorum the cluster will become inoperable, affecting all services and connected clients. The following monitors are down: {{- range query "(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)" }} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }}', + }, + }, + { + alert: 'CephMonDown', + 'for': '30s', + expr: ||| + count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1) + |||, + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down', + summary: 'One or more monitors down%(cluster)s' % $.MultiClusterSummary(), + description: ||| + {{ $down := query "count(ceph_mon_quorum_status == 0)" | first | value }}{{ $s := "" }}{{ if gt $down 1.0 }}{{ $s = "s" }}{{ end }}You have {{ $down }} monitor{{ $s }} down. Quorum is still intact, but the loss of an additional monitor will make your cluster inoperable. The following monitors are down: {{- range query "(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)" }} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }} + |||, + }, + }, + { + alert: 'CephMonDiskspaceCritical', + 'for': '1m', + expr: 'ceph_health_detail{name="MON_DISK_CRIT"} == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.3.2' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit', + summary: 'Filesystem space on at least one monitor is critically low%(cluster)s' % $.MultiClusterSummary(), + description: "The free space available to a monitor's store is critically low. You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*. Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; {{- range query \"ceph_mon_metadata\"}} - {{ .Labels.hostname }} {{- end }}", + }, + }, + { + alert: 'CephMonDiskspaceLow', + 'for': '5m', + expr: 'ceph_health_detail{name="MON_DISK_LOW"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low', + summary: 'Drive space on at least one monitor is approaching full%(cluster)s' % $.MultiClusterSummary(), + description: "The space available to a monitor's store is approaching full (>70% is the default). You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*. Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; {{- range query \"ceph_mon_metadata\"}} - {{ .Labels.hostname }} {{- end }}", + }, + }, + { + alert: 'CephMonClockSkew', + 'for': '1m', + expr: 'ceph_health_detail{name="MON_CLOCK_SKEW"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew', + summary: 'Clock skew detected among monitors%(cluster)s' % $.MultiClusterSummary(), + description: "Ceph monitors rely on closely synchronized time to maintain quorum and cluster consistency. This event indicates that the time on at least one mon has drifted too far from the lead mon. Review cluster status with ceph -s. This will show which monitors are affected. Check the time sync status on each monitor host with 'ceph time-sync-status' and the state and peers of your ntpd or chrony daemon.", + }, + }, + ], + }, + { + name: 'osd', + rules: [ + { + alert: 'CephOSDDownHigh', + expr: 'count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.1' }, + annotations: { + summary: 'More than 10%% of OSDs are down%(cluster)s' % $.MultiClusterSummary(), + description: '{{ $value | humanize }}% or {{ with query "count(ceph_osd_up == 0)" }}{{ . | first | value }}{{ end }} of {{ with query "count(ceph_osd_up)" }}{{ . | first | value }}{{ end }} OSDs are down (>= 10%). The following OSDs are down: {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0" }} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }}', + }, + }, + { + alert: 'CephOSDHostDown', + 'for': '5m', + expr: 'ceph_health_detail{name="OSD_HOST_DOWN"} == 1', + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.8' }, + annotations: { + summary: 'An OSD host is offline%(cluster)s' % $.MultiClusterSummary(), + description: 'The following OSDs are down: {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0" }} - {{ .Labels.hostname }} : {{ .Labels.ceph_daemon }} {{- end }}', + }, + }, + { + alert: 'CephOSDDown', + 'for': '5m', + expr: 'ceph_health_detail{name="OSD_DOWN"} == 1', + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.2' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down', + summary: 'An OSD has been marked down%(cluster)s' % $.MultiClusterSummary(), + description: ||| + {{ $num := query "count(ceph_osd_up == 0)" | first | value }}{{ $s := "" }}{{ if gt $num 1.0 }}{{ $s = "s" }}{{ end }}{{ $num }} OSD{{ $s }} down for over 5mins. The following OSD{{ $s }} {{ if eq $s "" }}is{{ else }}are{{ end }} down: {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0"}} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }} + |||, + }, + }, + { + alert: 'CephOSDNearFull', + 'for': '5m', + expr: 'ceph_health_detail{name="OSD_NEARFULL"} == 1', + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.3' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull', + summary: 'OSD(s) running low on free space (NEARFULL)%(cluster)s' % $.MultiClusterSummary(), + description: "One or more OSDs have reached the NEARFULL threshold. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data.", + }, + }, + { + alert: 'CephOSDFull', + 'for': '1m', + expr: 'ceph_health_detail{name="OSD_FULL"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.6' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full', + summary: 'OSD full, writes blocked%(cluster)s' % $.MultiClusterSummary(), + description: "An OSD has reached the FULL threshold. Writes to pools that share the affected OSD will be blocked. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data.", + }, + }, + { + alert: 'CephOSDBackfillFull', + 'for': '1m', + expr: 'ceph_health_detail{name="OSD_BACKFILLFULL"} > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull', + summary: 'OSD(s) too full for backfill operations%(cluster)s' % $.MultiClusterSummary(), + description: "An OSD has reached the BACKFILL FULL threshold. This will prevent rebalance operations from completing. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data.", + }, + }, + { + alert: 'CephOSDTooManyRepairs', + 'for': '30s', + expr: 'ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs', + summary: 'OSD reports a high number of read errors%(cluster)s' % $.MultiClusterSummary(), + description: 'Reads from an OSD have used a secondary PG to return data to the client, indicating a potential failing drive.', + }, + }, + { + alert: 'CephOSDTimeoutsPublicNetwork', + 'for': '1m', + expr: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + summary: 'Network issues delaying OSD heartbeats (public network)%(cluster)s' % $.MultiClusterSummary(), + description: "OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network for latency or loss issues. Use 'ceph health detail' to show the affected OSDs.", + }, + }, + { + alert: 'CephOSDTimeoutsClusterNetwork', + 'for': '1m', + expr: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + summary: 'Network issues delaying OSD heartbeats (cluster network)%(cluster)s' % $.MultiClusterSummary(), + description: "OSD heartbeats on the cluster's 'cluster' network (backend) are slow. Investigate the network for latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs.", + }, + }, + { + alert: 'CephOSDInternalDiskSizeMismatch', + 'for': '1m', + expr: 'ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch', + summary: 'OSD size inconsistency error%(cluster)s' % $.MultiClusterSummary(), + description: 'One or more OSDs have an internal inconsistency between metadata and the size of the device. This could lead to the OSD(s) crashing in future. You should redeploy the affected OSDs.', + }, + }, + { + alert: 'CephDeviceFailurePredicted', + 'for': '1m', + expr: 'ceph_health_detail{name="DEVICE_HEALTH"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#id2', + summary: 'Device(s) predicted to fail soon%(cluster)s' % $.MultiClusterSummary(), + description: "The device health module has determined that one or more devices will fail soon. To review device status use 'ceph device ls'. To show a specific device use 'ceph device info <dev id>'. Mark the OSD out so that data may migrate to other OSDs. Once the OSD has drained, destroy the OSD, replace the device, and redeploy the OSD.", + }, + }, + { + alert: 'CephDeviceFailurePredictionTooHigh', + 'for': '1m', + expr: 'ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"} == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.7' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany', + summary: 'Too many devices are predicted to fail, unable to resolve%(cluster)s' % $.MultiClusterSummary(), + description: 'The device health module has determined that devices predicted to fail can not be remediated automatically, since too many OSDs would be removed from the cluster to ensure performance and availabililty. Prevent data integrity issues by adding new OSDs so that data may be relocated.', + }, + }, + { + alert: 'CephDeviceFailureRelocationIncomplete', + 'for': '1m', + expr: 'ceph_health_detail{name="DEVICE_HEALTH_IN_USE"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use', + summary: 'Device failure is predicted, but unable to relocate data%(cluster)s' % $.MultiClusterSummary(), + description: 'The device health module has determined that one or more devices will fail soon, but the normal process of relocating the data on the device to other OSDs in the cluster is blocked. \nEnsure that the cluster has available free space. It may be necessary to add capacity to the cluster to allow data from the failing device to successfully migrate, or to enable the balancer.', + }, + }, + { + alert: 'CephOSDFlapping', + expr: '(rate(ceph_osd_up[5m]) * on(%(cluster)sceph_daemon) group_left(hostname) ceph_osd_metadata) * 60 > 1' % $.MultiClusterQuery(), + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.4' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds', + summary: 'Network issues are causing OSDs to flap (mark each other down)%(cluster)s' % $.MultiClusterSummary(), + description: 'OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} was marked down and back up {{ $value | humanize }} times once a minute for 5 minutes. This may indicate a network issue (latency, packet loss, MTU mismatch) on the cluster network, or the public network if no cluster network is deployed. Check the network stats on the listed host(s).', + }, + }, + { + alert: 'CephOSDReadErrors', + 'for': '30s', + expr: 'ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors', + summary: 'Device read errors detected%(cluster)s' % $.MultiClusterSummary(), + description: 'An OSD has encountered read errors, but the OSD has recovered by retrying the reads. This may indicate an issue with hardware or the kernel.', + }, + }, + { + alert: 'CephPGImbalance', + 'for': '5m', + expr: ||| + abs( + ((ceph_osd_numpg > 0) - on (%(cluster)sjob) group_left avg(ceph_osd_numpg > 0) by (%(cluster)sjob)) / + on (job) group_left avg(ceph_osd_numpg > 0) by (job) + ) * on (%(cluster)sceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30 + ||| % [$.MultiClusterQuery(), $.MultiClusterQuery(), $.MultiClusterQuery()], + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.4.5' }, + annotations: { + summary: 'PGs are not balanced across OSDs%(cluster)s' % $.MultiClusterSummary(), + description: 'OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} deviates by more than 30% from average PG count.', + }, + }, + ], + }, + { + name: 'mds', + rules: [ + { + alert: 'CephFilesystemDamaged', + 'for': '1m', + expr: 'ceph_health_detail{name="MDS_DAMAGE"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.5.1' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages', + summary: 'CephFS filesystem is damaged%(cluster)s.' % $.MultiClusterSummary(), + description: 'Filesystem metadata has been corrupted. Data may be inaccessible. Analyze metrics from the MDS daemon admin socket, or escalate to support.', + }, + }, + { + alert: 'CephFilesystemOffline', + 'for': '1m', + expr: 'ceph_health_detail{name="MDS_ALL_DOWN"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.5.3' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down', + summary: 'CephFS filesystem is offline%(cluster)s' % $.MultiClusterSummary(), + description: 'All MDS ranks are unavailable. The MDS daemons managing metadata are down, rendering the filesystem offline.', + }, + }, + { + alert: 'CephFilesystemDegraded', + 'for': '1m', + expr: 'ceph_health_detail{name="FS_DEGRADED"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.5.4' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded', + summary: 'CephFS filesystem is degraded%(cluster)s' % $.MultiClusterSummary(), + description: 'One or more metadata daemons (MDS ranks) are failed or in a damaged state. At best the filesystem is partially available, at worst the filesystem is completely unusable.', + }, + }, + { + alert: 'CephFilesystemMDSRanksLow', + 'for': '1m', + expr: 'ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"} > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max', + summary: 'Ceph MDS daemon count is lower than configured%(cluster)s' % $.MultiClusterSummary(), + description: "The filesystem's 'max_mds' setting defines the number of MDS ranks in the filesystem. The current number of active MDS daemons is less than this value.", + }, + }, + { + alert: 'CephFilesystemInsufficientStandby', + 'for': '1m', + expr: 'ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"} > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby', + summary: 'Ceph filesystem standby daemons too few%(cluster)s' % $.MultiClusterSummary(), + description: 'The minimum number of standby daemons required by standby_count_wanted is less than the current number of standby daemons. Adjust the standby count or increase the number of MDS daemons.', + }, + }, + { + alert: 'CephFilesystemFailureNoStandby', + 'for': '1m', + expr: 'ceph_health_detail{name="FS_WITH_FAILED_MDS"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.5.5' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds', + summary: 'MDS daemon failed, no further standby available%(cluster)s' % $.MultiClusterSummary(), + description: 'An MDS daemon has failed, leaving only one active rank and no available standby. Investigate the cause of the failure or add a standby MDS.', + }, + }, + { + alert: 'CephFilesystemReadOnly', + 'for': '1m', + expr: 'ceph_health_detail{name="MDS_HEALTH_READ_ONLY"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.5.2' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages', + summary: 'CephFS filesystem in read only mode due to write error(s)%(cluster)s' % $.MultiClusterSummary(), + description: 'The filesystem has switched to READ ONLY due to an unexpected error when writing to the metadata pool. Either analyze the output from the MDS daemon admin socket, or escalate to support.', + }, + }, + ], + }, + { + name: 'mgr', + rules: [ + { + alert: 'CephMgrModuleCrash', + 'for': '5m', + expr: 'ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"} == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.6.1' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash', + summary: 'A manager module has recently crashed%(cluster)s' % $.MultiClusterSummary(), + description: "One or more mgr modules have crashed and have yet to be acknowledged by an administrator. A crashed module may impact functionality within the cluster. Use the 'ceph crash' command to determine which module has failed, and archive it to acknowledge the failure.", + }, + }, + { + alert: 'CephMgrPrometheusModuleInactive', + 'for': '1m', + expr: 'up{job="ceph"} == 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.6.2' }, + annotations: { + summary: 'The mgr/prometheus module is not available%(cluster)s' % $.MultiClusterSummary(), + description: "The mgr/prometheus module at {{ $labels.instance }} is unreachable. This could mean that the module has been disabled or the mgr daemon itself is down. Without the mgr/prometheus module metrics and alerts will no longer function. Open a shell to an admin node or toolbox pod and use 'ceph -s' to to determine whether the mgr is active. If the mgr is not active, restart it, otherwise you can determine module status with 'ceph mgr module ls'. If it is not listed as enabled, enable it with 'ceph mgr module enable prometheus'.", + }, + }, + ], + }, + { + name: 'pgs', + rules: [ + { + alert: 'CephPGsInactive', + 'for': '5m', + expr: 'ceph_pool_metadata * on(%(cluster)spool_id,instance) group_left() (ceph_pg_total - ceph_pg_active) > 0' % $.MultiClusterQuery(), + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.7.1' }, + annotations: { + summary: 'One or more placement groups are inactive%(cluster)s' % $.MultiClusterSummary(), + description: '{{ $value }} PGs have been inactive for more than 5 minutes in pool {{ $labels.name }}. Inactive placement groups are not able to serve read/write requests.', + }, + }, + { + alert: 'CephPGsUnclean', + 'for': '15m', + expr: 'ceph_pool_metadata * on(%(cluster)spool_id,instance) group_left() (ceph_pg_total - ceph_pg_clean) > 0' % $.MultiClusterQuery(), + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.7.2' }, + annotations: { + summary: 'One or more placement groups are marked unclean%(cluster)s' % $.MultiClusterSummary(), + description: '{{ $value }} PGs have been unclean for more than 15 minutes in pool {{ $labels.name }}. Unclean PGs have not recovered from a previous failure.', + }, + }, + { + alert: 'CephPGsDamaged', + 'for': '5m', + expr: 'ceph_health_detail{name=~"PG_DAMAGED|OSD_SCRUB_ERRORS"} == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.7.4' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged', + summary: 'Placement group damaged, manual intervention needed%(cluster)s' % $.MultiClusterSummary(), + description: "During data consistency checks (scrub), at least one PG has been flagged as being damaged or inconsistent. Check to see which PG is affected, and attempt a manual repair if necessary. To list problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use the 'ceph pg repair <pg_num>' command.", + }, + }, + { + alert: 'CephPGRecoveryAtRisk', + 'for': '1m', + expr: 'ceph_health_detail{name="PG_RECOVERY_FULL"} == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.7.5' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full', + summary: 'OSDs are too full for recovery%(cluster)s' % $.MultiClusterSummary(), + description: "Data redundancy is at risk since one or more OSDs are at or above the 'full' threshold. Add more capacity to the cluster, restore down/out OSDs, or delete unwanted data.", + }, + }, + { + alert: 'CephPGUnavilableBlockingIO', + 'for': '1m', + expr: '((ceph_health_detail{name="PG_AVAILABILITY"} == 1) - scalar(ceph_health_detail{name="OSD_DOWN"})) == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.7.3' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability', + summary: 'PG is unavailable%(cluster)s, blocking I/O' % $.MultiClusterSummary(), + description: "Data availability is reduced, impacting the cluster's ability to service I/O. One or more placement groups (PGs) are in a state that blocks I/O.", + }, + }, + { + alert: 'CephPGBackfillAtRisk', + 'for': '1m', + expr: 'ceph_health_detail{name="PG_BACKFILL_FULL"} == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.7.6' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full', + summary: 'Backfill operations are blocked due to lack of free space%(cluster)s' % $.MultiClusterSummary(), + description: "Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs have reached the 'backfillfull' threshold. Add more capacity, or delete unwanted data.", + }, + }, + { + alert: 'CephPGNotScrubbed', + 'for': '5m', + expr: 'ceph_health_detail{name="PG_NOT_SCRUBBED"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed', + summary: 'Placement group(s) have not been scrubbed%(cluster)s' % $.MultiClusterSummary(), + description: "One or more PGs have not been scrubbed recently. Scrubs check metadata integrity, protecting against bit-rot. They check that metadata is consistent across data replicas. When PGs miss their scrub interval, it may indicate that the scrub window is too small, or PGs were not in a 'clean' state during the scrub window. You can manually initiate a scrub with: ceph pg scrub <pgid>", + }, + }, + { + alert: 'CephPGsHighPerOSD', + 'for': '1m', + expr: 'ceph_health_detail{name="TOO_MANY_PGS"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs', + summary: 'Placement groups per OSD is too high%(cluster)s' % $.MultiClusterSummary(), + description: "The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).\n Check that the pg_autoscaler has not been disabled for any pools with 'ceph osd pool autoscale-status', and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide the autoscaler based on the expected relative size of the pool ('ceph osd pool set cephfs.cephfs.meta target_size_ratio .1') or set the pg_autoscaler mode to 'warn' and adjust pg_num appropriately for one or more pools.", + }, + }, + { + alert: 'CephPGNotDeepScrubbed', + 'for': '5m', + expr: 'ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"} == 1', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed', + summary: 'Placement group(s) have not been deep scrubbed%(cluster)s' % $.MultiClusterSummary(), + description: "One or more PGs have not been deep scrubbed recently. Deep scrubs protect against bit-rot. They compare data replicas to ensure consistency. When PGs miss their deep scrub interval, it may indicate that the window is too small or PGs were not in a 'clean' state during the deep-scrub window.", + }, + }, + ], + }, + { + name: 'nodes', + rules: [ + { + alert: 'CephNodeRootFilesystemFull', + 'for': '5m', + expr: 'node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"} * 100 < 5', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.8.1' }, + annotations: { + summary: 'Root filesystem is dangerously full%(cluster)s' % $.MultiClusterSummary(), + description: 'Root volume is dangerously full: {{ $value | humanize }}% free.', + }, + }, + { + alert: 'CephNodeNetworkPacketDrops', + expr: ||| + ( + rate(node_network_receive_drop_total{device!="lo"}[1m]) + + rate(node_network_transmit_drop_total{device!="lo"}[1m]) + ) / ( + rate(node_network_receive_packets_total{device!="lo"}[1m]) + + rate(node_network_transmit_packets_total{device!="lo"}[1m]) + ) >= %(CephNodeNetworkPacketDropsThreshold)s and ( + rate(node_network_receive_drop_total{device!="lo"}[1m]) + + rate(node_network_transmit_drop_total{device!="lo"}[1m]) + ) >= %(CephNodeNetworkPacketDropsPerSec)s + ||| % $._config, + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.8.2' }, + annotations: { + summary: 'One or more NICs reports packet drops%(cluster)s' % $.MultiClusterSummary(), + description: 'Node {{ $labels.instance }} experiences packet drop > %(CephNodeNetworkPacketDropsThreshold)s%% or > %(CephNodeNetworkPacketDropsPerSec)s packets/s on interface {{ $labels.device }}.' % { CephNodeNetworkPacketDropsThreshold: $._config.CephNodeNetworkPacketDropsThreshold * 100, CephNodeNetworkPacketDropsPerSec: $._config.CephNodeNetworkPacketDropsPerSec }, + }, + }, + { + alert: 'CephNodeNetworkPacketErrors', + expr: ||| + ( + rate(node_network_receive_errs_total{device!="lo"}[1m]) + + rate(node_network_transmit_errs_total{device!="lo"}[1m]) + ) / ( + rate(node_network_receive_packets_total{device!="lo"}[1m]) + + rate(node_network_transmit_packets_total{device!="lo"}[1m]) + ) >= 0.0001 or ( + rate(node_network_receive_errs_total{device!="lo"}[1m]) + + rate(node_network_transmit_errs_total{device!="lo"}[1m]) + ) >= 10 + |||, + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.8.3' }, + annotations: { + summary: 'One or more NICs reports packet errors%(cluster)s' % $.MultiClusterSummary(), + description: 'Node {{ $labels.instance }} experiences packet errors > 0.01% or > 10 packets/s on interface {{ $labels.device }}.', + }, + }, + { + alert: 'CephNodeNetworkBondDegraded', + expr: ||| + node_bonding_slaves - node_bonding_active != 0 + |||, + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + summary: 'Degraded Bond on Node {{ $labels.instance }}%(cluster)s' % $.MultiClusterSummary(), + description: 'Bond {{ $labels.master }} is degraded on Node {{ $labels.instance }}.', + }, + }, + { + alert: 'CephNodeDiskspaceWarning', + expr: 'predict_linear(node_filesystem_free_bytes{device=~"/.*"}[2d], 3600 * 24 * 5) *on(instance) group_left(nodename) node_uname_info < 0', + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.8.4' }, + annotations: { + summary: 'Host filesystem free space is getting low%(cluster)s' % $.MultiClusterSummary(), + description: 'Mountpoint {{ $labels.mountpoint }} on {{ $labels.nodename }} will be full in less than 5 days based on the 48 hour trailing fill rate.', + }, + }, + { + alert: 'CephNodeInconsistentMTU', + expr: 'node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) == scalar( max by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) != quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) )or node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) == scalar( min by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) != quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) )', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + summary: 'MTU settings across Ceph hosts are inconsistent%(cluster)s' % $.MultiClusterSummary(), + description: 'Node {{ $labels.instance }} has a different MTU size ({{ $value }}) than the median of devices named {{ $labels.device }}.', + }, + }, + ], + }, + { + name: 'pools', + rules: [ + { + alert: 'CephPoolGrowthWarning', + expr: '(predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(%(cluster)spool_id) group_right ceph_pool_metadata) >= 95' % $.MultiClusterQuery(), + labels: { severity: 'warning', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.9.2' }, + annotations: { + summary: 'Pool growth rate may soon exceed capacity%(cluster)s' % $.MultiClusterSummary(), + description: "Pool '{{ $labels.name }}' will be full in less than 5 days assuming the average fill-up rate of the past 48 hours.", + }, + }, + { + alert: 'CephPoolBackfillFull', + expr: 'ceph_health_detail{name="POOL_BACKFILLFULL"} > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + summary: 'Free space in a pool is too low for recovery/backfill%(cluster)s' % $.MultiClusterSummary(), + description: 'A pool is approaching the near full threshold, which will prevent recovery/backfill operations from completing. Consider adding more capacity.', + }, + }, + { + alert: 'CephPoolFull', + 'for': '1m', + expr: 'ceph_health_detail{name="POOL_FULL"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.9.1' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full', + summary: 'Pool is full - writes are blocked%(cluster)s' % $.MultiClusterSummary(), + description: "A pool has reached its MAX quota, or OSDs supporting the pool have reached the FULL threshold. Until this is resolved, writes to the pool will be blocked. Pool Breakdown (top 5) {{- range query \"topk(5, sort_desc(ceph_pool_percent_used * on(pool_id) group_right ceph_pool_metadata))\" }} - {{ .Labels.name }} at {{ .Value }}% {{- end }} Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)", + }, + }, + { + alert: 'CephPoolNearFull', + 'for': '5m', + expr: 'ceph_health_detail{name="POOL_NEAR_FULL"} > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + summary: 'One or more Ceph pools are nearly full%(cluster)s' % $.MultiClusterSummary(), + description: "A pool has exceeded the warning (percent full) threshold, or OSDs supporting the pool have reached the NEARFULL threshold. Writes may continue, but you are at risk of the pool going read-only if more capacity isn't made available. Determine the affected pool with 'ceph df detail', looking at QUOTA BYTES and STORED. Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>). Also ensure that the balancer is active.", + }, + }, + ], + }, + { + name: 'healthchecks', + rules: [ + { + alert: 'CephSlowOps', + 'for': '30s', + expr: 'ceph_healthcheck_slow_ops > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops', + summary: 'OSD operations are slow to complete%(cluster)s' % $.MultiClusterSummary(), + description: '{{ $value }} OSD requests are taking too long to process (osd_op_complaint_time exceeded)', + }, + }, + { + alert: 'CephDaemonSlowOps', + 'for': '30s', + expr: 'ceph_daemon_health_metrics{type="SLOW_OPS"} > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops', + summary: '{{ $labels.ceph_daemon }} operations are slow to complete', + description: '{{ $labels.ceph_daemon }} operations are taking too long to process (complaint time exceeded)', + }, + }, + ], + }, + { + name: 'cephadm', + rules: [ + { + alert: 'CephadmUpgradeFailed', + 'for': '30s', + expr: 'ceph_health_detail{name="UPGRADE_EXCEPTION"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.11.2' }, + annotations: { + summary: 'Ceph version upgrade has failed%(cluster)s' % $.MultiClusterSummary(), + description: 'The cephadm cluster upgrade process has failed. The cluster remains in an undetermined state. Please review the cephadm logs, to understand the nature of the issue', + }, + }, + { + alert: 'CephadmDaemonFailed', + 'for': '30s', + expr: 'ceph_health_detail{name="CEPHADM_FAILED_DAEMON"} > 0', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.11.1' }, + annotations: { + summary: 'A ceph daemon manged by cephadm is down%(cluster)s' % $.MultiClusterSummary(), + description: "A daemon managed by cephadm is no longer active. Determine, which daemon is down with 'ceph health detail'. you may start daemons with the 'ceph orch daemon start <daemon_id>'", + }, + }, + { + alert: 'CephadmPaused', + 'for': '1m', + expr: 'ceph_health_detail{name="CEPHADM_PAUSED"} > 0', + labels: { severity: 'warning', type: 'ceph_default' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused', + summary: 'Orchestration tasks via cephadm are PAUSED%(cluster)s' % $.MultiClusterSummary(), + description: "Cluster management has been paused manually. This will prevent the orchestrator from service management and reconciliation. If this is not intentional, resume cephadm operations with 'ceph orch resume'", + }, + }, + ], + }, + { + name: 'PrometheusServer', + rules: [ + { + alert: 'PrometheusJobMissing', + 'for': '30s', + expr: 'absent(up{job="ceph"})', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.12.1' }, + annotations: { + summary: 'The scrape job for Ceph is missing from Prometheus%(cluster)s' % $.MultiClusterSummary(), + description: "The prometheus job that scrapes from Ceph is no longer defined, this will effectively mean you'll have no metrics or alerts for the cluster. Please review the job definitions in the prometheus.yml file of the prometheus instance.", + }, + }, + ], + }, + { + name: 'rados', + rules: [ + { + alert: 'CephObjectMissing', + 'for': '30s', + expr: '(ceph_health_detail{name="OBJECT_UNFOUND"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.10.1' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound', + summary: 'Object(s) marked UNFOUND%(cluster)s' % $.MultiClusterSummary(), + description: 'The latest version of a RADOS object can not be found, even though all OSDs are up. I/O requests for this object from clients will block (hang). Resolving this issue may require the object to be rolled back to a prior version manually, and manually verified.', + }, + }, + ], + }, + { + name: 'generic', + rules: [ + { + alert: 'CephDaemonCrash', + 'for': '1m', + expr: 'ceph_health_detail{name="RECENT_CRASH"} == 1', + labels: { severity: 'critical', type: 'ceph_default', oid: '1.3.6.1.4.1.50495.1.2.1.1.2' }, + annotations: { + documentation: 'https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash', + summary: 'One or more Ceph daemons have crashed, and are pending acknowledgement%(cluster)s' % $.MultiClusterSummary(), + description: "One or more daemons have crashed recently, and need to be acknowledged. This notification ensures that software crashes do not go unseen. To acknowledge a crash, use the 'ceph crash archive <id>' command.", + }, + }, + ], + }, + ], +} diff --git a/monitoring/ceph-mixin/prometheus_alerts.yml b/monitoring/ceph-mixin/prometheus_alerts.yml new file mode 100644 index 000000000..4a3e6acf3 --- /dev/null +++ b/monitoring/ceph-mixin/prometheus_alerts.yml @@ -0,0 +1,654 @@ +groups: + - name: "cluster health" + rules: + - alert: "CephHealthError" + annotations: + description: "The cluster state has been HEALTH_ERROR for more than 5 minutes. Please check 'ceph health detail' for more information." + summary: "Ceph is in the ERROR state" + expr: "ceph_health_status == 2" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.2.1" + severity: "critical" + type: "ceph_default" + - alert: "CephHealthWarning" + annotations: + description: "The cluster state has been HEALTH_WARN for more than 15 minutes. Please check 'ceph health detail' for more information." + summary: "Ceph is in the WARNING state" + expr: "ceph_health_status == 1" + for: "15m" + labels: + severity: "warning" + type: "ceph_default" + - name: "mon" + rules: + - alert: "CephMonDownQuorumAtRisk" + annotations: + description: "{{ $min := query \"floor(count(ceph_mon_metadata) / 2) + 1\" | first | value }}Quorum requires a majority of monitors (x {{ $min }}) to be active. Without quorum the cluster will become inoperable, affecting all services and connected clients. The following monitors are down: {{- range query \"(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)\" }} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }}" + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down" + summary: "Monitor quorum is at risk" + expr: | + ( + (ceph_health_detail{name="MON_DOWN"} == 1) * on() ( + count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1) + ) + ) == 1 + for: "30s" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.3.1" + severity: "critical" + type: "ceph_default" + - alert: "CephMonDown" + annotations: + description: | + {{ $down := query "count(ceph_mon_quorum_status == 0)" | first | value }}{{ $s := "" }}{{ if gt $down 1.0 }}{{ $s = "s" }}{{ end }}You have {{ $down }} monitor{{ $s }} down. Quorum is still intact, but the loss of an additional monitor will make your cluster inoperable. The following monitors are down: {{- range query "(ceph_mon_quorum_status == 0) + on(ceph_daemon) group_left(hostname) (ceph_mon_metadata * 0)" }} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }} + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down" + summary: "One or more monitors down" + expr: | + count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1) + for: "30s" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephMonDiskspaceCritical" + annotations: + description: "The free space available to a monitor's store is critically low. You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*. Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; {{- range query \"ceph_mon_metadata\"}} - {{ .Labels.hostname }} {{- end }}" + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit" + summary: "Filesystem space on at least one monitor is critically low" + expr: "ceph_health_detail{name=\"MON_DISK_CRIT\"} == 1" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.3.2" + severity: "critical" + type: "ceph_default" + - alert: "CephMonDiskspaceLow" + annotations: + description: "The space available to a monitor's store is approaching full (>70% is the default). You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*. Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; {{- range query \"ceph_mon_metadata\"}} - {{ .Labels.hostname }} {{- end }}" + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low" + summary: "Drive space on at least one monitor is approaching full" + expr: "ceph_health_detail{name=\"MON_DISK_LOW\"} == 1" + for: "5m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephMonClockSkew" + annotations: + description: "Ceph monitors rely on closely synchronized time to maintain quorum and cluster consistency. This event indicates that the time on at least one mon has drifted too far from the lead mon. Review cluster status with ceph -s. This will show which monitors are affected. Check the time sync status on each monitor host with 'ceph time-sync-status' and the state and peers of your ntpd or chrony daemon." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew" + summary: "Clock skew detected among monitors" + expr: "ceph_health_detail{name=\"MON_CLOCK_SKEW\"} == 1" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - name: "osd" + rules: + - alert: "CephOSDDownHigh" + annotations: + description: "{{ $value | humanize }}% or {{ with query \"count(ceph_osd_up == 0)\" }}{{ . | first | value }}{{ end }} of {{ with query \"count(ceph_osd_up)\" }}{{ . | first | value }}{{ end }} OSDs are down (>= 10%). The following OSDs are down: {{- range query \"(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0\" }} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }}" + summary: "More than 10% of OSDs are down" + expr: "count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.1" + severity: "critical" + type: "ceph_default" + - alert: "CephOSDHostDown" + annotations: + description: "The following OSDs are down: {{- range query \"(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0\" }} - {{ .Labels.hostname }} : {{ .Labels.ceph_daemon }} {{- end }}" + summary: "An OSD host is offline" + expr: "ceph_health_detail{name=\"OSD_HOST_DOWN\"} == 1" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.8" + severity: "warning" + type: "ceph_default" + - alert: "CephOSDDown" + annotations: + description: | + {{ $num := query "count(ceph_osd_up == 0)" | first | value }}{{ $s := "" }}{{ if gt $num 1.0 }}{{ $s = "s" }}{{ end }}{{ $num }} OSD{{ $s }} down for over 5mins. The following OSD{{ $s }} {{ if eq $s "" }}is{{ else }}are{{ end }} down: {{- range query "(ceph_osd_up * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) == 0"}} - {{ .Labels.ceph_daemon }} on {{ .Labels.hostname }} {{- end }} + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down" + summary: "An OSD has been marked down" + expr: "ceph_health_detail{name=\"OSD_DOWN\"} == 1" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.2" + severity: "warning" + type: "ceph_default" + - alert: "CephOSDNearFull" + annotations: + description: "One or more OSDs have reached the NEARFULL threshold. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull" + summary: "OSD(s) running low on free space (NEARFULL)" + expr: "ceph_health_detail{name=\"OSD_NEARFULL\"} == 1" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.3" + severity: "warning" + type: "ceph_default" + - alert: "CephOSDFull" + annotations: + description: "An OSD has reached the FULL threshold. Writes to pools that share the affected OSD will be blocked. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full" + summary: "OSD full, writes blocked" + expr: "ceph_health_detail{name=\"OSD_FULL\"} > 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.6" + severity: "critical" + type: "ceph_default" + - alert: "CephOSDBackfillFull" + annotations: + description: "An OSD has reached the BACKFILL FULL threshold. This will prevent rebalance operations from completing. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull" + summary: "OSD(s) too full for backfill operations" + expr: "ceph_health_detail{name=\"OSD_BACKFILLFULL\"} > 0" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephOSDTooManyRepairs" + annotations: + description: "Reads from an OSD have used a secondary PG to return data to the client, indicating a potential failing drive." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs" + summary: "OSD reports a high number of read errors" + expr: "ceph_health_detail{name=\"OSD_TOO_MANY_REPAIRS\"} == 1" + for: "30s" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephOSDTimeoutsPublicNetwork" + annotations: + description: "OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network for latency or loss issues. Use 'ceph health detail' to show the affected OSDs." + summary: "Network issues delaying OSD heartbeats (public network)" + expr: "ceph_health_detail{name=\"OSD_SLOW_PING_TIME_FRONT\"} == 1" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephOSDTimeoutsClusterNetwork" + annotations: + description: "OSD heartbeats on the cluster's 'cluster' network (backend) are slow. Investigate the network for latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs." + summary: "Network issues delaying OSD heartbeats (cluster network)" + expr: "ceph_health_detail{name=\"OSD_SLOW_PING_TIME_BACK\"} == 1" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephOSDInternalDiskSizeMismatch" + annotations: + description: "One or more OSDs have an internal inconsistency between metadata and the size of the device. This could lead to the OSD(s) crashing in future. You should redeploy the affected OSDs." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch" + summary: "OSD size inconsistency error" + expr: "ceph_health_detail{name=\"BLUESTORE_DISK_SIZE_MISMATCH\"} == 1" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephDeviceFailurePredicted" + annotations: + description: "The device health module has determined that one or more devices will fail soon. To review device status use 'ceph device ls'. To show a specific device use 'ceph device info <dev id>'. Mark the OSD out so that data may migrate to other OSDs. Once the OSD has drained, destroy the OSD, replace the device, and redeploy the OSD." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#id2" + summary: "Device(s) predicted to fail soon" + expr: "ceph_health_detail{name=\"DEVICE_HEALTH\"} == 1" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephDeviceFailurePredictionTooHigh" + annotations: + description: "The device health module has determined that devices predicted to fail can not be remediated automatically, since too many OSDs would be removed from the cluster to ensure performance and availabililty. Prevent data integrity issues by adding new OSDs so that data may be relocated." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany" + summary: "Too many devices are predicted to fail, unable to resolve" + expr: "ceph_health_detail{name=\"DEVICE_HEALTH_TOOMANY\"} == 1" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.7" + severity: "critical" + type: "ceph_default" + - alert: "CephDeviceFailureRelocationIncomplete" + annotations: + description: "The device health module has determined that one or more devices will fail soon, but the normal process of relocating the data on the device to other OSDs in the cluster is blocked. \nEnsure that the cluster has available free space. It may be necessary to add capacity to the cluster to allow data from the failing device to successfully migrate, or to enable the balancer." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use" + summary: "Device failure is predicted, but unable to relocate data" + expr: "ceph_health_detail{name=\"DEVICE_HEALTH_IN_USE\"} == 1" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephOSDFlapping" + annotations: + description: "OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} was marked down and back up {{ $value | humanize }} times once a minute for 5 minutes. This may indicate a network issue (latency, packet loss, MTU mismatch) on the cluster network, or the public network if no cluster network is deployed. Check the network stats on the listed host(s)." + documentation: "https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds" + summary: "Network issues are causing OSDs to flap (mark each other down)" + expr: "(rate(ceph_osd_up[5m]) * on(ceph_daemon) group_left(hostname) ceph_osd_metadata) * 60 > 1" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.4" + severity: "warning" + type: "ceph_default" + - alert: "CephOSDReadErrors" + annotations: + description: "An OSD has encountered read errors, but the OSD has recovered by retrying the reads. This may indicate an issue with hardware or the kernel." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors" + summary: "Device read errors detected" + expr: "ceph_health_detail{name=\"BLUESTORE_SPURIOUS_READ_ERRORS\"} == 1" + for: "30s" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephPGImbalance" + annotations: + description: "OSD {{ $labels.ceph_daemon }} on {{ $labels.hostname }} deviates by more than 30% from average PG count." + summary: "PGs are not balanced across OSDs" + expr: | + abs( + ((ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0) by (job)) / + on (job) group_left avg(ceph_osd_numpg > 0) by (job) + ) * on (ceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30 + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.4.5" + severity: "warning" + type: "ceph_default" + - name: "mds" + rules: + - alert: "CephFilesystemDamaged" + annotations: + description: "Filesystem metadata has been corrupted. Data may be inaccessible. Analyze metrics from the MDS daemon admin socket, or escalate to support." + documentation: "https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages" + summary: "CephFS filesystem is damaged." + expr: "ceph_health_detail{name=\"MDS_DAMAGE\"} > 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.5.1" + severity: "critical" + type: "ceph_default" + - alert: "CephFilesystemOffline" + annotations: + description: "All MDS ranks are unavailable. The MDS daemons managing metadata are down, rendering the filesystem offline." + documentation: "https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down" + summary: "CephFS filesystem is offline" + expr: "ceph_health_detail{name=\"MDS_ALL_DOWN\"} > 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.5.3" + severity: "critical" + type: "ceph_default" + - alert: "CephFilesystemDegraded" + annotations: + description: "One or more metadata daemons (MDS ranks) are failed or in a damaged state. At best the filesystem is partially available, at worst the filesystem is completely unusable." + documentation: "https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded" + summary: "CephFS filesystem is degraded" + expr: "ceph_health_detail{name=\"FS_DEGRADED\"} > 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.5.4" + severity: "critical" + type: "ceph_default" + - alert: "CephFilesystemMDSRanksLow" + annotations: + description: "The filesystem's 'max_mds' setting defines the number of MDS ranks in the filesystem. The current number of active MDS daemons is less than this value." + documentation: "https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max" + summary: "Ceph MDS daemon count is lower than configured" + expr: "ceph_health_detail{name=\"MDS_UP_LESS_THAN_MAX\"} > 0" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephFilesystemInsufficientStandby" + annotations: + description: "The minimum number of standby daemons required by standby_count_wanted is less than the current number of standby daemons. Adjust the standby count or increase the number of MDS daemons." + documentation: "https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby" + summary: "Ceph filesystem standby daemons too few" + expr: "ceph_health_detail{name=\"MDS_INSUFFICIENT_STANDBY\"} > 0" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephFilesystemFailureNoStandby" + annotations: + description: "An MDS daemon has failed, leaving only one active rank and no available standby. Investigate the cause of the failure or add a standby MDS." + documentation: "https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds" + summary: "MDS daemon failed, no further standby available" + expr: "ceph_health_detail{name=\"FS_WITH_FAILED_MDS\"} > 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.5.5" + severity: "critical" + type: "ceph_default" + - alert: "CephFilesystemReadOnly" + annotations: + description: "The filesystem has switched to READ ONLY due to an unexpected error when writing to the metadata pool. Either analyze the output from the MDS daemon admin socket, or escalate to support." + documentation: "https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages" + summary: "CephFS filesystem in read only mode due to write error(s)" + expr: "ceph_health_detail{name=\"MDS_HEALTH_READ_ONLY\"} > 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.5.2" + severity: "critical" + type: "ceph_default" + - name: "mgr" + rules: + - alert: "CephMgrModuleCrash" + annotations: + description: "One or more mgr modules have crashed and have yet to be acknowledged by an administrator. A crashed module may impact functionality within the cluster. Use the 'ceph crash' command to determine which module has failed, and archive it to acknowledge the failure." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash" + summary: "A manager module has recently crashed" + expr: "ceph_health_detail{name=\"RECENT_MGR_MODULE_CRASH\"} == 1" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.6.1" + severity: "critical" + type: "ceph_default" + - alert: "CephMgrPrometheusModuleInactive" + annotations: + description: "The mgr/prometheus module at {{ $labels.instance }} is unreachable. This could mean that the module has been disabled or the mgr daemon itself is down. Without the mgr/prometheus module metrics and alerts will no longer function. Open a shell to an admin node or toolbox pod and use 'ceph -s' to to determine whether the mgr is active. If the mgr is not active, restart it, otherwise you can determine module status with 'ceph mgr module ls'. If it is not listed as enabled, enable it with 'ceph mgr module enable prometheus'." + summary: "The mgr/prometheus module is not available" + expr: "up{job=\"ceph\"} == 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.6.2" + severity: "critical" + type: "ceph_default" + - name: "pgs" + rules: + - alert: "CephPGsInactive" + annotations: + description: "{{ $value }} PGs have been inactive for more than 5 minutes in pool {{ $labels.name }}. Inactive placement groups are not able to serve read/write requests." + summary: "One or more placement groups are inactive" + expr: "ceph_pool_metadata * on(pool_id,instance) group_left() (ceph_pg_total - ceph_pg_active) > 0" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.7.1" + severity: "critical" + type: "ceph_default" + - alert: "CephPGsUnclean" + annotations: + description: "{{ $value }} PGs have been unclean for more than 15 minutes in pool {{ $labels.name }}. Unclean PGs have not recovered from a previous failure." + summary: "One or more placement groups are marked unclean" + expr: "ceph_pool_metadata * on(pool_id,instance) group_left() (ceph_pg_total - ceph_pg_clean) > 0" + for: "15m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.7.2" + severity: "warning" + type: "ceph_default" + - alert: "CephPGsDamaged" + annotations: + description: "During data consistency checks (scrub), at least one PG has been flagged as being damaged or inconsistent. Check to see which PG is affected, and attempt a manual repair if necessary. To list problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use the 'ceph pg repair <pg_num>' command." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged" + summary: "Placement group damaged, manual intervention needed" + expr: "ceph_health_detail{name=~\"PG_DAMAGED|OSD_SCRUB_ERRORS\"} == 1" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.7.4" + severity: "critical" + type: "ceph_default" + - alert: "CephPGRecoveryAtRisk" + annotations: + description: "Data redundancy is at risk since one or more OSDs are at or above the 'full' threshold. Add more capacity to the cluster, restore down/out OSDs, or delete unwanted data." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full" + summary: "OSDs are too full for recovery" + expr: "ceph_health_detail{name=\"PG_RECOVERY_FULL\"} == 1" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.7.5" + severity: "critical" + type: "ceph_default" + - alert: "CephPGUnavilableBlockingIO" + annotations: + description: "Data availability is reduced, impacting the cluster's ability to service I/O. One or more placement groups (PGs) are in a state that blocks I/O." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability" + summary: "PG is unavailable, blocking I/O" + expr: "((ceph_health_detail{name=\"PG_AVAILABILITY\"} == 1) - scalar(ceph_health_detail{name=\"OSD_DOWN\"})) == 1" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.7.3" + severity: "critical" + type: "ceph_default" + - alert: "CephPGBackfillAtRisk" + annotations: + description: "Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs have reached the 'backfillfull' threshold. Add more capacity, or delete unwanted data." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full" + summary: "Backfill operations are blocked due to lack of free space" + expr: "ceph_health_detail{name=\"PG_BACKFILL_FULL\"} == 1" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.7.6" + severity: "critical" + type: "ceph_default" + - alert: "CephPGNotScrubbed" + annotations: + description: "One or more PGs have not been scrubbed recently. Scrubs check metadata integrity, protecting against bit-rot. They check that metadata is consistent across data replicas. When PGs miss their scrub interval, it may indicate that the scrub window is too small, or PGs were not in a 'clean' state during the scrub window. You can manually initiate a scrub with: ceph pg scrub <pgid>" + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed" + summary: "Placement group(s) have not been scrubbed" + expr: "ceph_health_detail{name=\"PG_NOT_SCRUBBED\"} == 1" + for: "5m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephPGsHighPerOSD" + annotations: + description: "The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).\n Check that the pg_autoscaler has not been disabled for any pools with 'ceph osd pool autoscale-status', and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide the autoscaler based on the expected relative size of the pool ('ceph osd pool set cephfs.cephfs.meta target_size_ratio .1') or set the pg_autoscaler mode to 'warn' and adjust pg_num appropriately for one or more pools." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs" + summary: "Placement groups per OSD is too high" + expr: "ceph_health_detail{name=\"TOO_MANY_PGS\"} == 1" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephPGNotDeepScrubbed" + annotations: + description: "One or more PGs have not been deep scrubbed recently. Deep scrubs protect against bit-rot. They compare data replicas to ensure consistency. When PGs miss their deep scrub interval, it may indicate that the window is too small or PGs were not in a 'clean' state during the deep-scrub window." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed" + summary: "Placement group(s) have not been deep scrubbed" + expr: "ceph_health_detail{name=\"PG_NOT_DEEP_SCRUBBED\"} == 1" + for: "5m" + labels: + severity: "warning" + type: "ceph_default" + - name: "nodes" + rules: + - alert: "CephNodeRootFilesystemFull" + annotations: + description: "Root volume is dangerously full: {{ $value | humanize }}% free." + summary: "Root filesystem is dangerously full" + expr: "node_filesystem_avail_bytes{mountpoint=\"/\"} / node_filesystem_size_bytes{mountpoint=\"/\"} * 100 < 5" + for: "5m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.8.1" + severity: "critical" + type: "ceph_default" + - alert: "CephNodeNetworkPacketDrops" + annotations: + description: "Node {{ $labels.instance }} experiences packet drop > 0.5% or > 10 packets/s on interface {{ $labels.device }}." + summary: "One or more NICs reports packet drops" + expr: | + ( + rate(node_network_receive_drop_total{device!="lo"}[1m]) + + rate(node_network_transmit_drop_total{device!="lo"}[1m]) + ) / ( + rate(node_network_receive_packets_total{device!="lo"}[1m]) + + rate(node_network_transmit_packets_total{device!="lo"}[1m]) + ) >= 0.0050000000000000001 and ( + rate(node_network_receive_drop_total{device!="lo"}[1m]) + + rate(node_network_transmit_drop_total{device!="lo"}[1m]) + ) >= 10 + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.8.2" + severity: "warning" + type: "ceph_default" + - alert: "CephNodeNetworkPacketErrors" + annotations: + description: "Node {{ $labels.instance }} experiences packet errors > 0.01% or > 10 packets/s on interface {{ $labels.device }}." + summary: "One or more NICs reports packet errors" + expr: | + ( + rate(node_network_receive_errs_total{device!="lo"}[1m]) + + rate(node_network_transmit_errs_total{device!="lo"}[1m]) + ) / ( + rate(node_network_receive_packets_total{device!="lo"}[1m]) + + rate(node_network_transmit_packets_total{device!="lo"}[1m]) + ) >= 0.0001 or ( + rate(node_network_receive_errs_total{device!="lo"}[1m]) + + rate(node_network_transmit_errs_total{device!="lo"}[1m]) + ) >= 10 + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.8.3" + severity: "warning" + type: "ceph_default" + - alert: "CephNodeNetworkBondDegraded" + annotations: + summary: "Degraded Bond on Node {{ $labels.instance }}" + description: "Bond {{ $labels.master }} is degraded on Node {{ $labels.instance }}." + expr: | + node_bonding_slaves - node_bonding_active != 0 + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephNodeDiskspaceWarning" + annotations: + description: "Mountpoint {{ $labels.mountpoint }} on {{ $labels.nodename }} will be full in less than 5 days based on the 48 hour trailing fill rate." + summary: "Host filesystem free space is getting low" + expr: "predict_linear(node_filesystem_free_bytes{device=~\"/.*\"}[2d], 3600 * 24 * 5) *on(instance) group_left(nodename) node_uname_info < 0" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.8.4" + severity: "warning" + type: "ceph_default" + - alert: "CephNodeInconsistentMTU" + annotations: + description: "Node {{ $labels.instance }} has a different MTU size ({{ $value }}) than the median of devices named {{ $labels.device }}." + summary: "MTU settings across Ceph hosts are inconsistent" + expr: "node_network_mtu_bytes * (node_network_up{device!=\"lo\"} > 0) == scalar( max by (device) (node_network_mtu_bytes * (node_network_up{device!=\"lo\"} > 0)) != quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!=\"lo\"} > 0)) )or node_network_mtu_bytes * (node_network_up{device!=\"lo\"} > 0) == scalar( min by (device) (node_network_mtu_bytes * (node_network_up{device!=\"lo\"} > 0)) != quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!=\"lo\"} > 0)) )" + labels: + severity: "warning" + type: "ceph_default" + - name: "pools" + rules: + - alert: "CephPoolGrowthWarning" + annotations: + description: "Pool '{{ $labels.name }}' will be full in less than 5 days assuming the average fill-up rate of the past 48 hours." + summary: "Pool growth rate may soon exceed capacity" + expr: "(predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id, instance) group_right() ceph_pool_metadata) >= 95" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.9.2" + severity: "warning" + type: "ceph_default" + - alert: "CephPoolBackfillFull" + annotations: + description: "A pool is approaching the near full threshold, which will prevent recovery/backfill operations from completing. Consider adding more capacity." + summary: "Free space in a pool is too low for recovery/backfill" + expr: "ceph_health_detail{name=\"POOL_BACKFILLFULL\"} > 0" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephPoolFull" + annotations: + description: "A pool has reached its MAX quota, or OSDs supporting the pool have reached the FULL threshold. Until this is resolved, writes to the pool will be blocked. Pool Breakdown (top 5) {{- range query \"topk(5, sort_desc(ceph_pool_percent_used * on(pool_id) group_right ceph_pool_metadata))\" }} - {{ .Labels.name }} at {{ .Value }}% {{- end }} Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)" + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full" + summary: "Pool is full - writes are blocked" + expr: "ceph_health_detail{name=\"POOL_FULL\"} > 0" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.9.1" + severity: "critical" + type: "ceph_default" + - alert: "CephPoolNearFull" + annotations: + description: "A pool has exceeded the warning (percent full) threshold, or OSDs supporting the pool have reached the NEARFULL threshold. Writes may continue, but you are at risk of the pool going read-only if more capacity isn't made available. Determine the affected pool with 'ceph df detail', looking at QUOTA BYTES and STORED. Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>). Also ensure that the balancer is active." + summary: "One or more Ceph pools are nearly full" + expr: "ceph_health_detail{name=\"POOL_NEAR_FULL\"} > 0" + for: "5m" + labels: + severity: "warning" + type: "ceph_default" + - name: "healthchecks" + rules: + - alert: "CephSlowOps" + annotations: + description: "{{ $value }} OSD requests are taking too long to process (osd_op_complaint_time exceeded)" + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops" + summary: "OSD operations are slow to complete" + expr: "ceph_healthcheck_slow_ops > 0" + for: "30s" + labels: + severity: "warning" + type: "ceph_default" + - alert: "CephDaemonSlowOps" + for: "30s" + expr: "ceph_daemon_health_metrics{type=\"SLOW_OPS\"} > 0" + labels: + severity: 'warning' + type: 'ceph_default' + annotations: + summary: "{{ $labels.ceph_daemon }} operations are slow to complete" + description: "{{ $labels.ceph_daemon }} operations are taking too long to process (complaint time exceeded)" + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops" + - name: "cephadm" + rules: + - alert: "CephadmUpgradeFailed" + annotations: + description: "The cephadm cluster upgrade process has failed. The cluster remains in an undetermined state. Please review the cephadm logs, to understand the nature of the issue" + summary: "Ceph version upgrade has failed" + expr: "ceph_health_detail{name=\"UPGRADE_EXCEPTION\"} > 0" + for: "30s" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.11.2" + severity: "critical" + type: "ceph_default" + - alert: "CephadmDaemonFailed" + annotations: + description: "A daemon managed by cephadm is no longer active. Determine, which daemon is down with 'ceph health detail'. you may start daemons with the 'ceph orch daemon start <daemon_id>'" + summary: "A ceph daemon manged by cephadm is down" + expr: "ceph_health_detail{name=\"CEPHADM_FAILED_DAEMON\"} > 0" + for: "30s" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.11.1" + severity: "critical" + type: "ceph_default" + - alert: "CephadmPaused" + annotations: + description: "Cluster management has been paused manually. This will prevent the orchestrator from service management and reconciliation. If this is not intentional, resume cephadm operations with 'ceph orch resume'" + documentation: "https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused" + summary: "Orchestration tasks via cephadm are PAUSED" + expr: "ceph_health_detail{name=\"CEPHADM_PAUSED\"} > 0" + for: "1m" + labels: + severity: "warning" + type: "ceph_default" + - name: "PrometheusServer" + rules: + - alert: "PrometheusJobMissing" + annotations: + description: "The prometheus job that scrapes from Ceph is no longer defined, this will effectively mean you'll have no metrics or alerts for the cluster. Please review the job definitions in the prometheus.yml file of the prometheus instance." + summary: "The scrape job for Ceph is missing from Prometheus" + expr: "absent(up{job=\"ceph\"})" + for: "30s" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.12.1" + severity: "critical" + type: "ceph_default" + - name: "rados" + rules: + - alert: "CephObjectMissing" + annotations: + description: "The latest version of a RADOS object can not be found, even though all OSDs are up. I/O requests for this object from clients will block (hang). Resolving this issue may require the object to be rolled back to a prior version manually, and manually verified." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound" + summary: "Object(s) marked UNFOUND" + expr: "(ceph_health_detail{name=\"OBJECT_UNFOUND\"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1" + for: "30s" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.10.1" + severity: "critical" + type: "ceph_default" + - name: "generic" + rules: + - alert: "CephDaemonCrash" + annotations: + description: "One or more daemons have crashed recently, and need to be acknowledged. This notification ensures that software crashes do not go unseen. To acknowledge a crash, use the 'ceph crash archive <id>' command." + documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash" + summary: "One or more Ceph daemons have crashed, and are pending acknowledgement" + expr: "ceph_health_detail{name=\"RECENT_CRASH\"} == 1" + for: "1m" + labels: + oid: "1.3.6.1.4.1.50495.1.2.1.1.2" + severity: "critical" + type: "ceph_default" diff --git a/monitoring/ceph-mixin/requirements-alerts.txt b/monitoring/ceph-mixin/requirements-alerts.txt new file mode 100644 index 000000000..e518e6964 --- /dev/null +++ b/monitoring/ceph-mixin/requirements-alerts.txt @@ -0,0 +1,2 @@ +pyyaml==6.0 +bs4 diff --git a/monitoring/ceph-mixin/requirements-grafonnet.txt b/monitoring/ceph-mixin/requirements-grafonnet.txt new file mode 100644 index 000000000..9891d5590 --- /dev/null +++ b/monitoring/ceph-mixin/requirements-grafonnet.txt @@ -0,0 +1 @@ +jsondiff diff --git a/monitoring/ceph-mixin/requirements-lint.txt b/monitoring/ceph-mixin/requirements-lint.txt new file mode 100644 index 000000000..f9a3c772f --- /dev/null +++ b/monitoring/ceph-mixin/requirements-lint.txt @@ -0,0 +1,18 @@ +attrs==21.2.0 +behave==1.2.6 +py==1.10.0 +pyparsing==2.4.7 +PyYAML==6.0 +types-PyYAML==6.0.0 +typing-extensions==3.10.0.2 +termcolor==1.1.0 +types-termcolor==1.1.2 +dataclasses==0.6 +types-dataclasses==0.6.1 +six==1.16.0 +toml==0.10.2 +pylint==2.6.0 +isort==5.10.0 +mypy==0.910 +mypy-extensions==0.4.3 +prettytable==2.4.0 diff --git a/monitoring/ceph-mixin/test-jsonnet.sh b/monitoring/ceph-mixin/test-jsonnet.sh new file mode 100755 index 000000000..87c533892 --- /dev/null +++ b/monitoring/ceph-mixin/test-jsonnet.sh @@ -0,0 +1,35 @@ +#!/bin/sh -e + +TEMPDIR=$(mktemp -d) +BASEDIR=$(dirname "$0") + +jsonnet -J vendor -m ${TEMPDIR} $BASEDIR/dashboards.jsonnet + +truncate -s 0 ${TEMPDIR}/json_difference.log +for file in ${BASEDIR}/dashboards_out/*.json +do + file_name="$(basename $file)" + for generated_file in ${TEMPDIR}/*.json + do + generated_file_name="$(basename $generated_file)" + if [ "$file_name" == "$generated_file_name" ]; then + jsondiff --indent 2 "${generated_file}" "${file}" \ + | tee -a ${TEMPDIR}/json_difference.log + fi + done +done + +jsonnet -J vendor -S alerts.jsonnet -o ${TEMPDIR}/prometheus_alerts.yml +jsondiff --indent 2 "prometheus_alerts.yml" "${TEMPDIR}/prometheus_alerts.yml" \ + | tee -a ${TEMPDIR}/json_difference.log + +err=0 +if [ $(wc -l < ${TEMPDIR}/json_difference.log) -eq 0 ] +then + rm -rf ${TEMPDIR} + echo "Congratulations! Grafonnet Check Passed" +else + rm -rf ${TEMPDIR} + echo "Grafonnet Check Failed, failed comparing generated file with existing" + exit 1 +fi diff --git a/monitoring/ceph-mixin/tests_alerts/README.md b/monitoring/ceph-mixin/tests_alerts/README.md new file mode 100644 index 000000000..cf95fa636 --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/README.md @@ -0,0 +1,92 @@ + +## Alert Rule Standards + +The alert rules should adhere to the following principles +- each alert must have a unique name +- each alert should define a common structure + - labels : must contain severity and type + - annotations : must provide description + - expr : must define the promql expression + - alert : defines the alert name +- alerts that have a corresponding section within docs.ceph.com must include a + documentation field in the annotations section +- critical alerts should declare an oid in the labels section +- critical alerts should have a corresponding entry in the Ceph MIB + + +## Testing Prometheus Rules +Once you have updated the `ceph_default_alerts.yml` file, you should use the +`validate_rules.py` script directly, or via `tox` to ensure the format of any update +or change aligns to our rule structure guidelines. The validate_rules.py script will +process the rules and look for any configuration anomalies and output a report if +problems are detected. + +Here's an example run, to illustrate the format and the kinds of issues detected. + +``` +[paul@myhost tests]$ ./validate_rules.py + +Checking rule groups + cluster health : .. + mon : E.W.. + osd : E...W......W.E.. + mds : WW + mgr : WW + pgs : ..WWWW.. + nodes : .EEEE + pools : EEEW. + healthchecks : . + cephadm : WW. + prometheus : W + rados : W + +Summary + +Rule file : ../alerts/ceph_default_alerts.yml +Unit Test file : test_alerts.yml + +Rule groups processed : 12 +Rules processed : 51 +Rule errors : 10 +Rule warnings : 16 +Rule name duplicates : 0 +Unit tests missing : 4 + +Problem Report + + Group Severity Alert Name Problem Description + ----- -------- ---------- ------------------- + cephadm Warning Cluster upgrade has failed critical level alert is missing an SNMP oid entry + cephadm Warning A daemon managed by cephadm is down critical level alert is missing an SNMP oid entry + mds Warning Ceph Filesystem damage detected critical level alert is missing an SNMP oid entry + mds Warning Ceph Filesystem switched to READ ONLY critical level alert is missing an SNMP oid entry + mgr Warning mgr module failure critical level alert is missing an SNMP oid entry + mgr Warning mgr prometheus module is not active critical level alert is missing an SNMP oid entry + mon Error Monitor down, quorum is at risk documentation link error: #mon-downwah not found on the page + mon Warning Ceph mon disk space critically low critical level alert is missing an SNMP oid entry + nodes Error network packets dropped invalid alert structure. Missing field: for + nodes Error network packet errors invalid alert structure. Missing field: for + nodes Error storage filling up invalid alert structure. Missing field: for + nodes Error MTU Mismatch invalid alert structure. Missing field: for + osd Error 10% OSDs down invalid alert structure. Missing field: for + osd Error Flapping OSD invalid alert structure. Missing field: for + osd Warning OSD Full critical level alert is missing an SNMP oid entry + osd Warning Too many devices predicted to fail critical level alert is missing an SNMP oid entry + pgs Warning Placement Group (PG) damaged critical level alert is missing an SNMP oid entry + pgs Warning Recovery at risk, cluster too full critical level alert is missing an SNMP oid entry + pgs Warning I/O blocked to some data critical level alert is missing an SNMP oid entry + pgs Warning Cluster too full, automatic data recovery impaired critical level alert is missing an SNMP oid entry + pools Error pool full invalid alert structure. Missing field: for + pools Error pool filling up (growth forecast) invalid alert structure. Missing field: for + pools Error Ceph pool is too full for recovery/rebalance invalid alert structure. Missing field: for + pools Warning Ceph pool is full - writes blocked critical level alert is missing an SNMP oid entry + prometheus Warning Scrape job is missing critical level alert is missing an SNMP oid entry + rados Warning Data not found/missing critical level alert is missing an SNMP oid entry + +Unit tests are incomplete. Tests missing for the following alerts; + - Placement Group (PG) damaged + - OSD Full + - storage filling up + - pool filling up (growth forecast) + +``` diff --git a/monitoring/ceph-mixin/tests_alerts/__init__.py b/monitoring/ceph-mixin/tests_alerts/__init__.py new file mode 100644 index 000000000..e69de29bb --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/__init__.py diff --git a/monitoring/ceph-mixin/tests_alerts/settings.py b/monitoring/ceph-mixin/tests_alerts/settings.py new file mode 100644 index 000000000..d99dfdca6 --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/settings.py @@ -0,0 +1,11 @@ +import os + +ALERTS_FILE = '../prometheus_alerts.yml' +UNIT_TESTS_FILE = 'test_alerts.yml' +MIB_FILE = '../../snmp/CEPH-MIB.txt' + +current_dir = os.path.dirname(os.path.abspath(__file__)) + +ALERTS_FILE = os.path.join(current_dir, ALERTS_FILE) +UNIT_TESTS_FILE = os.path.join(current_dir, UNIT_TESTS_FILE) +MIB_FILE = os.path.join(current_dir, MIB_FILE) diff --git a/monitoring/ceph-mixin/tests_alerts/test_alerts.yml b/monitoring/ceph-mixin/tests_alerts/test_alerts.yml new file mode 100644 index 000000000..1aaea88e7 --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/test_alerts.yml @@ -0,0 +1,1888 @@ +rule_files: + - ../prometheus_alerts.yml +evaluation_interval: 5m +tests: + # health error + - interval: 5m + input_series: + - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}' + values: '2 2 2 2 2 2 2' + promql_expr_test: + - expr: ceph_health_status == 2 + eval_time: 5m + exp_samples: + - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}' + value: 2 + alert_rule_test: + - eval_time: 1m + alertname: CephHealthError + - eval_time: 6m + alertname: CephHealthError + exp_alerts: + - exp_labels: + instance: ceph:9283 + job: ceph + oid: 1.3.6.1.4.1.50495.1.2.1.2.1 + type: ceph_default + severity: critical + exp_annotations: + summary: Ceph is in the ERROR state + description: The cluster state has been HEALTH_ERROR for more than 5 minutes. Please check 'ceph health detail' for more information. + + # health warning + - interval: 5m + input_series: + - series: 'ceph_health_status{instance="ceph:9283",job="ceph"}' + values: '1 1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_status == 1 + eval_time: 15m + exp_samples: + - labels: 'ceph_health_status{instance="ceph:9283",job="ceph"}' + value: 1 + alert_rule_test: + - eval_time: 10m + alertname: CephHealthWarning + - eval_time: 20m + alertname: CephHealthWarning + exp_alerts: + - exp_labels: + instance: ceph:9283 + job: ceph + type: ceph_default + severity: warning + exp_annotations: + summary: Ceph is in the WARNING state + description: The cluster state has been HEALTH_WARN for more than 15 minutes. Please check 'ceph health detail' for more information. + + # 10% OSDs down + - interval: 1m + input_series: + - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}' + values: '1 1 1 1 1' + - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}' + values: '0 0 0 0 0' + - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}' + values: '1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1' + promql_expr_test: + - expr: count(ceph_osd_up == 0) / count(ceph_osd_up) * 100 >= 10 + eval_time: 1m + exp_samples: + - labels: '{}' + value: 3.333333333333333E+01 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDDownHigh + exp_alerts: + - exp_labels: + oid: 1.3.6.1.4.1.50495.1.2.1.4.1 + type: ceph_default + severity: critical + exp_annotations: + summary: More than 10% of OSDs are down + description: "33.33% or 1 of 3 OSDs are down (>= 10%). The following OSDs are down: - osd.1 on ceph" + + # flapping OSD + - interval: 1s + input_series: + - series: 'ceph_osd_up{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"}' + values: '1+1x100' + - series: 'ceph_osd_up{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"}' + values: '1+0x100' + - series: 'ceph_osd_up{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"}' + values: '1+0x100' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1 1' + promql_expr_test: + - expr: | + ( + rate(ceph_osd_up[5m]) + * on(ceph_daemon) group_left(hostname) ceph_osd_metadata + ) * 60 > 1 + eval_time: 1m + exp_samples: + - labels: '{ceph_daemon="osd.0", hostname="ceph", instance="ceph:9283", + job="ceph"}' + value: 1.2200000000000001E+01 + alert_rule_test: + - eval_time: 5m + alertname: CephOSDFlapping + exp_alerts: + - exp_labels: + ceph_daemon: osd.0 + hostname: ceph + instance: ceph:9283 + job: ceph + oid: 1.3.6.1.4.1.50495.1.2.1.4.4 + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/troubleshooting/troubleshooting-osd#flapping-osds + summary: Network issues are causing OSDs to flap (mark each other down) + description: "OSD osd.0 on ceph was marked down and back up 20.1 times once a minute for 5 minutes. This may indicate a network issue (latency, packet loss, MTU mismatch) on the cluster network, or the public network if no cluster network is deployed. Check the network stats on the listed host(s)." + + # high pg count deviation + - interval: 1m + input_series: + - series: 'ceph_osd_numpg{ceph_daemon="osd.0",instance="ceph:9283", + job="ceph"}' + values: '100 100 100 100 100 160' + - series: 'ceph_osd_numpg{ceph_daemon="osd.1",instance="ceph:9283", + job="ceph"}' + values: '100 100 100 100 100 320' + - series: 'ceph_osd_numpg{ceph_daemon="osd.2",instance="ceph:9283", + job="ceph"}' + values: '100 100 100 100 100 160' + - series: 'ceph_osd_numpg{ceph_daemon="osd.3",instance="ceph:9283", + job="ceph"}' + values: '100 100 100 100 100 160' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.0", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.1", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.2", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1 1' + - series: 'ceph_osd_metadata{back_iface="eth0",ceph_daemon="osd.3", + ceph_version="ceph version 17.0.0-189-g3558fd72 + (3558fd7291855971aa6481a2ade468ad61fbb346) pacific (dev)", + cluster_addr="172.20.0.2",device_class="hdd",front_iface="eth0", + hostname="ceph",instance="ceph:9283",job="ceph",objectstore="bluestore", + public_addr="172.20.0.2"}' + values: '1 1 1 1 1 1' + promql_expr_test: + - expr: | + abs( + ( + (ceph_osd_numpg > 0) - on (job) group_left avg(ceph_osd_numpg > 0) + by (job) + ) / on (job) group_left avg(ceph_osd_numpg > 0) by (job) + ) * on(ceph_daemon) group_left(hostname) ceph_osd_metadata > 0.30 + + eval_time: 5m + exp_samples: + - labels: '{ceph_daemon="osd.1", hostname="ceph", instance="ceph:9283", + job="ceph"}' + value: 6E-01 + alert_rule_test: + - eval_time: 10m + alertname: CephPGImbalance + exp_alerts: + - exp_labels: + ceph_daemon: osd.1 + hostname: ceph + instance: ceph:9283 + job: ceph + oid: 1.3.6.1.4.1.50495.1.2.1.4.5 + severity: warning + type: ceph_default + exp_annotations: + summary: PGs are not balanced across OSDs + description: "OSD osd.1 on ceph deviates by more than 30% from average PG count." + + # pgs inactive + - interval: 1m + input_series: + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="device_health_metrics",pool_id="1"}' + values: '1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="device_health_metrics",pool_id="2"}' + values: '1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="device_health_metrics",pool_id="3"}' + values: '1 1 1 1 1 1 1 1' + - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}' + values: '1 1 1 1 1 1 1 1' + - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}' + values: '32 32 32 32 32 32 32 32' + - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}' + values: '33 32 32 32 32 33 33 32' + - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="1"}' + values: '1 1 1 1 1 1 1 1 1' + - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="2"}' + values: '32 32 32 32 32 32 32 32' + - series: 'ceph_pg_active{instance="ceph:9283",job="ceph",pool_id="3"}' + values: '32 32 32 32 32 32 32 32' + promql_expr_test: + - expr: ceph_pool_metadata * on(pool_id,instance) group_left() + (ceph_pg_total - ceph_pg_active) > 0 + eval_time: 5m + exp_samples: + - labels: '{instance="ceph:9283", job="ceph", + name="device_health_metrics", + pool_id="3"}' + value: 1 + alert_rule_test: + - eval_time: 5m + alertname: CephPGsInactive + exp_alerts: + - exp_labels: + instance: ceph:9283 + job: ceph + name: device_health_metrics + oid: 1.3.6.1.4.1.50495.1.2.1.7.1 + pool_id: 3 + severity: critical + type: ceph_default + exp_annotations: + summary: One or more placement groups are inactive + description: "1 PGs have been inactive for more than 5 minutes in pool device_health_metrics. Inactive placement groups are not able to serve read/write requests." + + #pgs unclean + - interval: 1m + input_series: + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="device_health_metrics",pool_id="1"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="device_health_metrics",pool_id="2"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="device_health_metrics",pool_id="3"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="1"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="2"}' + values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 + 32 32 32' + - series: 'ceph_pg_total{instance="ceph:9283",job="ceph",pool_id="3"}' + values: '33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 + 33 33' + - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="1"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="2"}' + values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 + 32 32' + - series: 'ceph_pg_clean{instance="ceph:9283",job="ceph",pool_id="3"}' + values: '32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 + 32 32' + promql_expr_test: + - expr: ceph_pool_metadata * on(pool_id,instance) group_left() + (ceph_pg_total - ceph_pg_clean) > 0 + eval_time: 15m + exp_samples: + - labels: '{instance="ceph:9283", job="ceph", + name="device_health_metrics", pool_id="3"}' + value: 1 + alert_rule_test: + - eval_time: 16m + alertname: CephPGsUnclean + exp_alerts: + - exp_labels: + instance: ceph:9283 + job: ceph + name: device_health_metrics + oid: 1.3.6.1.4.1.50495.1.2.1.7.2 + pool_id: 3 + severity: warning + type: ceph_default + exp_annotations: + summary: One or more placement groups are marked unclean + description: "1 PGs have been unclean for more than 15 minutes in pool device_health_metrics. Unclean PGs have not recovered from a previous failure." + + # root volume full + - interval: 1m + input_series: + - series: 'node_filesystem_avail_bytes{device="/dev/mapper/fedora_localhost + --live-home",fstype="ext4",instance="node-exporter",job="node-exporter", + mountpoint="/"}' + values: '35336400896 35336400896 35336400896 35336400896 35336400896 + 3525385519.104 3533640089' + - series: 'node_filesystem_size_bytes{device="/dev/mapper/fedora_localhost + --live-home",fstype="ext4",instance="node-exporter",job="node-exporter", + mountpoint="/"}' + values: '73445531648 73445531648 73445531648 73445531648 73445531648 + 73445531648 73445531648' + promql_expr_test: + - expr: node_filesystem_avail_bytes{mountpoint="/"} / + node_filesystem_size_bytes{mountpoint="/"} * 100 < 5 + eval_time: 5m + exp_samples: + - labels: '{device="/dev/mapper/fedora_localhost --live-home", + fstype="ext4", instance="node-exporter", job="node-exporter", + mountpoint="/"}' + value: 4.8E+00 + alert_rule_test: + - eval_time: 10m + alertname: CephNodeRootFilesystemFull + exp_alerts: + - exp_labels: + device: /dev/mapper/fedora_localhost --live-home + fstype: ext4 + instance: node-exporter + job: node-exporter + mountpoint: / + oid: 1.3.6.1.4.1.50495.1.2.1.8.1 + severity: critical + type: ceph_default + exp_annotations: + summary: Root filesystem is dangerously full + description: "Root volume is dangerously full: 4.811% free." + + # network packets dropped + - interval: 1m + input_series: + - series: 'node_network_receive_drop_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+600x10' + - series: 'node_network_transmit_drop_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+600x10' + - series: 'node_network_receive_packets_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+750x10' + - series: 'node_network_transmit_packets_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+750x10' + promql_expr_test: + - expr: | + ( + rate(node_network_receive_drop_total{device!="lo"}[1m]) + + rate(node_network_transmit_drop_total{device!="lo"}[1m]) + ) / ( + rate(node_network_receive_packets_total{device!="lo"}[1m]) + + rate(node_network_transmit_packets_total{device!="lo"}[1m]) + ) >= 0.0050000000000000001 and ( + rate(node_network_receive_drop_total{device!="lo"}[1m]) + + rate(node_network_transmit_drop_total{device!="lo"}[1m]) + ) >= 10 + + eval_time: 5m + exp_samples: + - labels: '{device="eth0", instance="node-exporter", + job="node-exporter"}' + value: 8E-1 + alert_rule_test: + - eval_time: 5m + alertname: CephNodeNetworkPacketDrops + exp_alerts: + - exp_labels: + device: eth0 + instance: node-exporter + job: node-exporter + oid: 1.3.6.1.4.1.50495.1.2.1.8.2 + severity: warning + type: ceph_default + exp_annotations: + summary: One or more NICs reports packet drops + description: "Node node-exporter experiences packet drop > 0.5% or > 10 packets/s on interface eth0." + + # network packets errors + - interval: 1m + input_series: + - series: 'node_network_receive_errs_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+600x10' + - series: 'node_network_transmit_errs_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+600x10' + - series: 'node_network_transmit_packets_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+750x10' + - series: 'node_network_receive_packets_total{device="eth0", + instance="node-exporter",job="node-exporter"}' + values: '0+750x10' + promql_expr_test: + - expr: | + ( + rate(node_network_receive_errs_total{device!="lo"}[1m]) + + rate(node_network_transmit_errs_total{device!="lo"}[1m]) + ) / ( + rate(node_network_receive_packets_total{device!="lo"}[1m]) + + rate(node_network_transmit_packets_total{device!="lo"}[1m]) + ) >= 0.0001 or ( + rate(node_network_receive_errs_total{device!="lo"}[1m]) + + rate(node_network_transmit_errs_total{device!="lo"}[1m]) + ) >= 10 + + eval_time: 5m + exp_samples: + - labels: '{device="eth0", instance="node-exporter", + job="node-exporter"}' + value: 8E-01 + alert_rule_test: + - eval_time: 5m + alertname: CephNodeNetworkPacketErrors + exp_alerts: + - exp_labels: + device: eth0 + instance: node-exporter + job: node-exporter + oid: 1.3.6.1.4.1.50495.1.2.1.8.3 + severity: warning + type: ceph_default + exp_annotations: + summary: One or more NICs reports packet errors + description: "Node node-exporter experiences packet errors > 0.01% or > 10 packets/s on interface eth0." + + # Bond is missing a peer + - interval: 1m + input_series: + - series: 'node_bonding_active{master="bond0", + instance="node-exporter",job="node-exporter"}' + values: '3' + - series: 'node_bonding_slaves{master="bond0", + instance="node-exporter",job="node-exporter"}' + values: '4' + promql_expr_test: + - expr: | + node_bonding_slaves - node_bonding_active != 0 + eval_time: 5m + exp_samples: + - labels: '{master="bond0", instance="node-exporter", + job="node-exporter"}' + value: 1 + alert_rule_test: + - eval_time: 5m + alertname: CephNodeNetworkBondDegraded + exp_alerts: + - exp_labels: + master: bond0 + instance: node-exporter + job: node-exporter + severity: warning + type: ceph_default + exp_annotations: + summary: Degraded Bond on Node node-exporter + description: "Bond bond0 is degraded on Node node-exporter." + +# Node Storage disk space filling up + - interval: 1m + # 20GB = 21474836480, 256MB = 268435456 + input_series: + - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root", + fstype="xfs",instance="node-1",mountpoint="/rootfs"}' + values: '21474836480-268435456x48' + - series: 'node_filesystem_free_bytes{device="/dev/mapper/vg-root", + fstype="xfs",instance="node-2",mountpoint="/rootfs"}' + values: '21474836480+0x48' + - series: 'node_uname_info{instance="node-1", nodename="node-1.unittests.com"}' + values: 1+0x48 + - series: 'node_uname_info{instance="node-2", nodename="node-2.unittests.com"}' + values: 1+0x48 + promql_expr_test: + - expr: | + predict_linear(node_filesystem_free_bytes{device=~"/.*"}[2d], 3600 * 24 * 5) * + on(instance) group_left(nodename) node_uname_info < 0 + eval_time: 5m + exp_samples: + - labels: '{device="/dev/mapper/vg-root",instance="node-1",fstype="xfs", + mountpoint="/rootfs",nodename="node-1.unittests.com"}' + value: -1.912602624E+12 + alert_rule_test: + - eval_time: 5m + alertname: CephNodeDiskspaceWarning + exp_alerts: + - exp_labels: + severity: warning + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.8.4 + device: /dev/mapper/vg-root + fstype: xfs + instance: node-1 + mountpoint: /rootfs + nodename: node-1.unittests.com + exp_annotations: + summary: Host filesystem free space is getting low + description: "Mountpoint /rootfs on node-1.unittests.com will be full in less than 5 days based on the 48 hour trailing fill rate." + # MTU Mismatch + - interval: 1m + input_series: + - series: 'node_network_mtu_bytes{device="eth0",instance="node-exporter", + job="node-exporter"}' + values: '1500 1500 1500 1500 1500' + - series: 'node_network_mtu_bytes{device="eth1",instance="node-exporter", + job="node-exporter"}' + values: '1500 1500 1500 1500 1500' + - series: 'node_network_mtu_bytes{device="eth2",instance="node-exporter", + job="node-exporter"}' + values: '1500 1500 1500 1500 1500' + - series: 'node_network_mtu_bytes{device="eth3",instance="node-exporter", + job="node-exporter"}' + values: '1500 1500 1500 1500 1500' + - series: 'node_network_mtu_bytes{device="eth4",instance="node-exporter", + job="node-exporter"}' + values: '9000 9000 9000 9000 9000' + - series: 'node_network_mtu_bytes{device="eth4",instance="hostname1", + job="node-exporter"}' + values: '2200 2200 2200 2200 2200' + - series: 'node_network_mtu_bytes{device="eth4",instance="hostname2", + job="node-exporter"}' + values: '2400 2400 2400 2400 2400' + - series: 'node_network_up{device="eth0",instance="node-exporter", + job="node-exporter"}' + values: '0 0 0 0 0' + - series: 'node_network_up{device="eth1",instance="node-exporter", + job="node-exporter"}' + values: '0 0 0 0 0' + - series: 'node_network_up{device="eth2",instance="node-exporter", + job="node-exporter"}' + values: '1 1 1 1 1' + - series: 'node_network_up{device="eth3",instance="node-exporter", + job="node-exporter"}' + values: '1 1 1 1 1' + - series: 'node_network_up{device="eth4",instance="node-exporter", + job="node-exporter"}' + values: '1 1 1 1 1' + - series: 'node_network_up{device="eth4",instance="hostname1", + job="node-exporter"}' + values: '1 1 1 1 1' + - series: 'node_network_up{device="eth4",instance="hostname2", + job="node-exporter"}' + values: '0 0 0 0 0' + promql_expr_test: + - expr: | + node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) == + scalar( + max by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) != + quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) + ) + or + node_network_mtu_bytes * (node_network_up{device!="lo"} > 0) == + scalar( + min by (device) (node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) != + quantile by (device) (.5, node_network_mtu_bytes * (node_network_up{device!="lo"} > 0)) + ) + eval_time: 1m + exp_samples: + - labels: '{device="eth4", instance="node-exporter", job="node-exporter"}' + value: 9000 + - labels: '{device="eth4", instance="hostname1", job="node-exporter"}' + value: 2200 + alert_rule_test: + - eval_time: 1m + alertname: CephNodeInconsistentMTU + exp_alerts: + - exp_labels: + device: eth4 + instance: hostname1 + job: node-exporter + severity: warning + type: ceph_default + exp_annotations: + summary: MTU settings across Ceph hosts are inconsistent + description: "Node hostname1 has a different MTU size (2200) than the median of devices named eth4." + - exp_labels: + device: eth4 + instance: node-exporter + job: node-exporter + severity: warning + type: ceph_default + exp_annotations: + summary: MTU settings across Ceph hosts are inconsistent + description: "Node node-exporter has a different MTU size (9000) than the median of devices named eth4." + + # pool full, data series has 6 but using topk(5) so to ensure the + # results are working as expected + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="POOL_FULL"}' + values: '0 0 0 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_percent_used{pool_id="1"}' + values: '32+0x10' + - series: 'ceph_pool_percent_used{pool_id="2"}' + values: '96+0x10' + - series: 'ceph_pool_percent_used{pool_id="3"}' + values: '90+0x10' + - series: 'ceph_pool_percent_used{pool_id="4"}' + values: '72+0x10' + - series: 'ceph_pool_percent_used{pool_id="5"}' + values: '19+0x10' + - series: 'ceph_pool_percent_used{pool_id="6"}' + values: '10+0x10' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="cephfs_data",pool_id="1"}' + values: '1 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="rbd",pool_id="2"}' + values: '1 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="iscsi",pool_id="3"}' + values: '1 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="default.rgw.index",pool_id="4"}' + values: '1 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="default.rgw.log",pool_id="5"}' + values: '1 1 1 1 1 1 1 1 1' + - series: 'ceph_pool_metadata{instance="ceph:9283",job="ceph", + name="dummy",pool_id="6"}' + values: '1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="POOL_FULL"} > 0 + eval_time: 5m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="POOL_FULL"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephPoolFull + - eval_time: 10m + alertname: CephPoolFull + exp_alerts: + - exp_labels: + name: POOL_FULL + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.9.1 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pool-full + summary: Pool is full - writes are blocked + description: "A pool has reached its MAX quota, or OSDs supporting the pool have reached the FULL threshold. Until this is resolved, writes to the pool will be blocked. Pool Breakdown (top 5) - rbd at 96% - iscsi at 90% - default.rgw.index at 72% - cephfs_data at 32% - default.rgw.log at 19% Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>)" + # slow OSD ops + - interval : 1m + input_series: + - series: 'ceph_healthcheck_slow_ops{instance="ceph:9283",job="ceph"}' + values: '1+0x120' + promql_expr_test: + - expr: ceph_healthcheck_slow_ops > 0 + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_healthcheck_slow_ops", instance="ceph:9283", + job="ceph"}' + value: 1 + alert_rule_test: + - eval_time: 20m + alertname: CephSlowOps + exp_alerts: + - exp_labels: + instance: ceph:9283 + job: ceph + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops + summary: OSD operations are slow to complete + description: "1 OSD requests are taking too long to process (osd_op_complaint_time exceeded)" + + # slow daemon ops + - interval : 1m + input_series: + - series: 'ceph_daemon_health_metrics{ceph_daemon="osd.1", instance="ceph:9283",job="ceph", type="SLOW_OPS"}' + values: '1+0x120' + promql_expr_test: + - expr: 'ceph_daemon_health_metrics{type="SLOW_OPS"} > 0' + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_daemon_health_metrics", ceph_daemon="osd.1",instance="ceph:9283", + job="ceph", type="SLOW_OPS"}' + value: 1 + alert_rule_test: + - eval_time: 20m + alertname: CephDaemonSlowOps + exp_alerts: + - exp_labels: + instance: ceph:9283 + ceph_daemon: "osd.1" + job: ceph + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops + summary: osd.1 operations are slow to complete + description: "osd.1 operations are taking too long to process (complaint time exceeded)" + +# CEPHADM orchestrator alert triggers + - interval: 30s + input_series: + - series: 'ceph_health_detail{name="UPGRADE_EXCEPTION"}' + values: '1+0x40' + promql_expr_test: + - expr: ceph_health_detail{name="UPGRADE_EXCEPTION"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="UPGRADE_EXCEPTION"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephadmUpgradeFailed + - eval_time: 5m + alertname: CephadmUpgradeFailed + exp_alerts: + - exp_labels: + name: UPGRADE_EXCEPTION + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.11.2 + exp_annotations: + summary: Ceph version upgrade has failed + description: "The cephadm cluster upgrade process has failed. The cluster remains in an undetermined state. Please review the cephadm logs, to understand the nature of the issue" + - interval: 30s + input_series: + - series: 'ceph_health_detail{name="CEPHADM_FAILED_DAEMON"}' + values: '1+0x40' + promql_expr_test: + - expr: ceph_health_detail{name="CEPHADM_FAILED_DAEMON"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="CEPHADM_FAILED_DAEMON"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephadmDaemonFailed + - eval_time: 5m + alertname: CephadmDaemonFailed + exp_alerts: + - exp_labels: + name: CEPHADM_FAILED_DAEMON + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.11.1 + exp_annotations: + summary: A ceph daemon manged by cephadm is down + description: "A daemon managed by cephadm is no longer active. Determine, which daemon is down with 'ceph health detail'. you may start daemons with the 'ceph orch daemon start <daemon_id>'" + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="CEPHADM_PAUSED"}' + values: '1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="CEPHADM_PAUSED"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="CEPHADM_PAUSED"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephadmPaused + - eval_time: 5m + alertname: CephadmPaused + exp_alerts: + - exp_labels: + name: CEPHADM_PAUSED + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephadm/operations#cephadm-paused + summary: Orchestration tasks via cephadm are PAUSED + description: "Cluster management has been paused manually. This will prevent the orchestrator from service management and reconciliation. If this is not intentional, resume cephadm operations with 'ceph orch resume'" +# MDS + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MDS_DAMAGE"}' + values: '1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="MDS_DAMAGE"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MDS_DAMAGE"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephFilesystemDamaged + - eval_time: 5m + alertname: CephFilesystemDamaged + exp_alerts: + - exp_labels: + name: MDS_DAMAGE + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.5.1 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages + summary: CephFS filesystem is damaged. + description: "Filesystem metadata has been corrupted. Data may be inaccessible. Analyze metrics from the MDS daemon admin socket, or escalate to support." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MDS_HEALTH_READ_ONLY"}' + values: '1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="MDS_HEALTH_READ_ONLY"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MDS_HEALTH_READ_ONLY"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephFilesystemReadOnly + - eval_time: 5m + alertname: CephFilesystemReadOnly + exp_alerts: + - exp_labels: + name: MDS_HEALTH_READ_ONLY + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.5.2 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephfs/health-messages#cephfs-health-messages + summary: CephFS filesystem in read only mode due to write error(s) + description: "The filesystem has switched to READ ONLY due to an unexpected error when writing to the metadata pool. Either analyze the output from the MDS daemon admin socket, or escalate to support." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MDS_ALL_DOWN"}' + values: '0 0 1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="MDS_ALL_DOWN"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MDS_ALL_DOWN"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephFilesystemOffline + - eval_time: 10m + alertname: CephFilesystemOffline + exp_alerts: + - exp_labels: + name: MDS_ALL_DOWN + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.5.3 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-all-down + summary: CephFS filesystem is offline + description: "All MDS ranks are unavailable. The MDS daemons managing metadata are down, rendering the filesystem offline." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="FS_DEGRADED"}' + values: '0 0 1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="FS_DEGRADED"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="FS_DEGRADED"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephFilesystemDegraded + - eval_time: 10m + alertname: CephFilesystemDegraded + exp_alerts: + - exp_labels: + name: FS_DEGRADED + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.5.4 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-degraded + summary: CephFS filesystem is degraded + description: "One or more metadata daemons (MDS ranks) are failed or in a damaged state. At best the filesystem is partially available, at worst the filesystem is completely unusable." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"}' + values: '0 0 1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="MDS_INSUFFICIENT_STANDBY"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MDS_INSUFFICIENT_STANDBY"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephFilesystemInsufficientStandby + - eval_time: 10m + alertname: CephFilesystemInsufficientStandby + exp_alerts: + - exp_labels: + name: MDS_INSUFFICIENT_STANDBY + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-insufficient-standby + summary: Ceph filesystem standby daemons too few + description: "The minimum number of standby daemons required by standby_count_wanted is less than the current number of standby daemons. Adjust the standby count or increase the number of MDS daemons." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="FS_WITH_FAILED_MDS"}' + values: '0 0 1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="FS_WITH_FAILED_MDS"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="FS_WITH_FAILED_MDS"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephFilesystemFailureNoStandby + - eval_time: 10m + alertname: CephFilesystemFailureNoStandby + exp_alerts: + - exp_labels: + name: FS_WITH_FAILED_MDS + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.5.5 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#fs-with-failed-mds + summary: MDS daemon failed, no further standby available + description: "An MDS daemon has failed, leaving only one active rank and no available standby. Investigate the cause of the failure or add a standby MDS." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"}' + values: '0 0 1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="MDS_UP_LESS_THAN_MAX"} > 0 + eval_time: 2m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MDS_UP_LESS_THAN_MAX"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephFilesystemMDSRanksLow + - eval_time: 10m + alertname: CephFilesystemMDSRanksLow + exp_alerts: + - exp_labels: + name: MDS_UP_LESS_THAN_MAX + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/cephfs/health-messages/#mds-up-less-than-max + summary: Ceph MDS daemon count is lower than configured + description: "The filesystem's 'max_mds' setting defines the number of MDS ranks in the filesystem. The current number of active MDS daemons is less than this value." +# MGR + - interval: 1m + input_series: + - series: 'up{job="ceph", instance="ceph-mgr:9283"}' + values: '1+0x2 0+0x10' + promql_expr_test: + - expr: up{job="ceph"} == 0 + eval_time: 3m + exp_samples: + - labels: '{__name__="up", job="ceph", instance="ceph-mgr:9283"}' + value: 0 + alert_rule_test: + - eval_time: 1m + alertname: CephMgrPrometheusModuleInactive + - eval_time: 10m + alertname: CephMgrPrometheusModuleInactive + exp_alerts: + - exp_labels: + instance: ceph-mgr:9283 + job: ceph + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.6.2 + exp_annotations: + summary: The mgr/prometheus module is not available + description: "The mgr/prometheus module at ceph-mgr:9283 is unreachable. This could mean that the module has been disabled or the mgr daemon itself is down. Without the mgr/prometheus module metrics and alerts will no longer function. Open a shell to an admin node or toolbox pod and use 'ceph -s' to to determine whether the mgr is active. If the mgr is not active, restart it, otherwise you can determine module status with 'ceph mgr module ls'. If it is not listed as enabled, enable it with 'ceph mgr module enable prometheus'." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="RECENT_MGR_MODULE_CRASH"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="RECENT_MGR_MODULE_CRASH"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephMgrModuleCrash + - eval_time: 15m + alertname: CephMgrModuleCrash + exp_alerts: + - exp_labels: + name: RECENT_MGR_MODULE_CRASH + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.6.1 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#recent-mgr-module-crash + summary: A manager module has recently crashed + description: "One or more mgr modules have crashed and have yet to be acknowledged by an administrator. A crashed module may impact functionality within the cluster. Use the 'ceph crash' command to determine which module has failed, and archive it to acknowledge the failure." +# MON + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MON_DISK_CRIT"}' + values: '0+0x2 1+0x10' + - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}' + values: '1+0x13' + promql_expr_test: + - expr: ceph_health_detail{name="MON_DISK_CRIT"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MON_DISK_CRIT"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephMonDiskspaceCritical + - eval_time: 10m + alertname: CephMonDiskspaceCritical + exp_alerts: + - exp_labels: + name: "MON_DISK_CRIT" + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.3.2 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-crit + summary: Filesystem space on at least one monitor is critically low + description: "The free space available to a monitor's store is critically low. You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*. Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; - ceph-mon-a" + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MON_DISK_LOW"}' + values: '0+0x2 1+0x10' + - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-a"}' + values: '1+0x13' + promql_expr_test: + - expr: ceph_health_detail{name="MON_DISK_LOW"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MON_DISK_LOW"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephMonDiskspaceLow + - eval_time: 10m + alertname: CephMonDiskspaceLow + exp_alerts: + - exp_labels: + name: "MON_DISK_LOW" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-disk-low + summary: Drive space on at least one monitor is approaching full + description: "The space available to a monitor's store is approaching full (>70% is the default). You should increase the space available to the monitor(s). The default directory is /var/lib/ceph/mon-*/data/store.db on traditional deployments, and /var/lib/rook/mon-*/data/store.db on the mon pod's worker node for Rook. Look for old, rotated versions of *.log and MANIFEST*. Do NOT touch any *.sst files. Also check any other directories under /var/lib/rook and other directories on the same filesystem, often /var/log and /var/tmp are culprits. Your monitor hosts are; - ceph-mon-a" + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MON_CLOCK_SKEW"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="MON_CLOCK_SKEW"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="MON_CLOCK_SKEW"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephMonClockSkew + - eval_time: 10m + alertname: CephMonClockSkew + exp_alerts: + - exp_labels: + name: "MON_CLOCK_SKEW" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-clock-skew + summary: Clock skew detected among monitors + description: "Ceph monitors rely on closely synchronized time to maintain quorum and cluster consistency. This event indicates that the time on at least one mon has drifted too far from the lead mon. Review cluster status with ceph -s. This will show which monitors are affected. Check the time sync status on each monitor host with 'ceph time-sync-status' and the state and peers of your ntpd or chrony daemon." + +# Check 3 mons one down, quorum at risk + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="MON_DOWN"}' + values: '0+0x2 1+0x12' + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}' + values: '1+0x14' + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}' + values: '1+0x14' + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}' + values: '1+0x2 0+0x12' + - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}' + values: '1+0x14' + - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}' + values: '1+0x14' + - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}' + values: '1+0x14' + promql_expr_test: + - expr: ((ceph_health_detail{name="MON_DOWN"} == 1) * on() (count(ceph_mon_quorum_status == 1) == bool (floor(count(ceph_mon_metadata) / 2) + 1))) == 1 + eval_time: 3m + exp_samples: + - labels: '{}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephMonDownQuorumAtRisk + # shouldn't fire + - eval_time: 10m + alertname: CephMonDownQuorumAtRisk + exp_alerts: + - exp_labels: + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.3.1 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down + summary: Monitor quorum is at risk + description: "Quorum requires a majority of monitors (x 2) to be active. Without quorum the cluster will become inoperable, affecting all services and connected clients. The following monitors are down: - mon.c on ceph-mon-3" +# check 5 mons, 1 down - warning only + - interval: 1m + input_series: + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.a"}' + values: '1+0x14' + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.b"}' + values: '1+0x14' + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.c"}' + values: '1+0x14' + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.d"}' + values: '1+0x14' + - series: 'ceph_mon_quorum_status{ceph_daemon="mon.e"}' + values: '1+0x2 0+0x12' + - series: 'ceph_mon_metadata{ceph_daemon="mon.a", hostname="ceph-mon-1"}' + values: '1+0x14' + - series: 'ceph_mon_metadata{ceph_daemon="mon.b", hostname="ceph-mon-2"}' + values: '1+0x14' + - series: 'ceph_mon_metadata{ceph_daemon="mon.c", hostname="ceph-mon-3"}' + values: '1+0x14' + - series: 'ceph_mon_metadata{ceph_daemon="mon.d", hostname="ceph-mon-4"}' + values: '1+0x14' + - series: 'ceph_mon_metadata{ceph_daemon="mon.e", hostname="ceph-mon-5"}' + values: '1+0x14' + promql_expr_test: + - expr: (count(ceph_mon_quorum_status == 0) <= (count(ceph_mon_metadata) - floor(count(ceph_mon_metadata) / 2) + 1)) + eval_time: 3m + exp_samples: + - labels: '{}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephMonDown + - eval_time: 10m + alertname: CephMonDown + exp_alerts: + - exp_labels: + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#mon-down + summary: One or more monitors down + description: "You have 1 monitor down. Quorum is still intact, but the loss of an additional monitor will make your cluster inoperable. The following monitors are down: - mon.e on ceph-mon-5\n" +# Device Health + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="DEVICE_HEALTH"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="DEVICE_HEALTH"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephDeviceFailurePredicted + - eval_time: 10m + alertname: CephDeviceFailurePredicted + exp_alerts: + - exp_labels: + name: "DEVICE_HEALTH" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#id2 + summary: Device(s) predicted to fail soon + description: "The device health module has determined that one or more devices will fail soon. To review device status use 'ceph device ls'. To show a specific device use 'ceph device info <dev id>'. Mark the OSD out so that data may migrate to other OSDs. Once the OSD has drained, destroy the OSD, replace the device, and redeploy the OSD." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="DEVICE_HEALTH_TOOMANY"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_TOOMANY"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephDeviceFailurePredictionTooHigh + - eval_time: 10m + alertname: CephDeviceFailurePredictionTooHigh + exp_alerts: + - exp_labels: + name: "DEVICE_HEALTH_TOOMANY" + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.4.7 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-toomany + summary: Too many devices are predicted to fail, unable to resolve + description: "The device health module has determined that devices predicted to fail can not be remediated automatically, since too many OSDs would be removed from the cluster to ensure performance and availabililty. Prevent data integrity issues by adding new OSDs so that data may be relocated." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="DEVICE_HEALTH_IN_USE"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="DEVICE_HEALTH_IN_USE"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="DEVICE_HEALTH_IN_USE"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephDeviceFailureRelocationIncomplete + - eval_time: 10m + alertname: CephDeviceFailureRelocationIncomplete + exp_alerts: + - exp_labels: + name: "DEVICE_HEALTH_IN_USE" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#device-health-in-use + summary: Device failure is predicted, but unable to relocate data + description: "The device health module has determined that one or more devices will fail soon, but the normal process of relocating the data on the device to other OSDs in the cluster is blocked. \nEnsure that the cluster has available free space. It may be necessary to add capacity to the cluster to allow data from the failing device to successfully migrate, or to enable the balancer." +# OSD + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OSD_HOST_DOWN"}' + values: '0+0x2 1+0x10' + - series: 'ceph_osd_up{ceph_daemon="osd.0"}' + values: '1+0x2 0+0x10' + - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}' + values: '1+0x12' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_HOST_DOWN"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_HOST_DOWN"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDHostDown + - eval_time: 10m + alertname: CephOSDHostDown + exp_alerts: + - exp_labels: + name: "OSD_HOST_DOWN" + severity: warning + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.4.8 + exp_annotations: + summary: An OSD host is offline + description: "The following OSDs are down: - ceph-osd-1 : osd.0" + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_FRONT"} == 0 + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_FRONT"}' + value: 0 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDTimeoutsPublicNetwork + - eval_time: 10m + alertname: CephOSDTimeoutsPublicNetwork + exp_alerts: + - exp_labels: + name: "OSD_SLOW_PING_TIME_FRONT" + severity: warning + type: ceph_default + exp_annotations: + summary: Network issues delaying OSD heartbeats (public network) + description: "OSD heartbeats on the cluster's 'public' network (frontend) are running slow. Investigate the network for latency or loss issues. Use 'ceph health detail' to show the affected OSDs." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_SLOW_PING_TIME_BACK"} == 0 + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_SLOW_PING_TIME_BACK"}' + value: 0 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDTimeoutsClusterNetwork + - eval_time: 10m + alertname: CephOSDTimeoutsClusterNetwork + exp_alerts: + - exp_labels: + name: "OSD_SLOW_PING_TIME_BACK" + severity: warning + type: ceph_default + exp_annotations: + summary: Network issues delaying OSD heartbeats (cluster network) + description: "OSD heartbeats on the cluster's 'cluster' network (backend) are slow. Investigate the network for latency issues on this subnet. Use 'ceph health detail' to show the affected OSDs." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="BLUESTORE_DISK_SIZE_MISMATCH"} == 0 + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="BLUESTORE_DISK_SIZE_MISMATCH"}' + value: 0 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDInternalDiskSizeMismatch + - eval_time: 10m + alertname: CephOSDInternalDiskSizeMismatch + exp_alerts: + - exp_labels: + name: "BLUESTORE_DISK_SIZE_MISMATCH" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-disk-size-mismatch + summary: OSD size inconsistency error + description: "One or more OSDs have an internal inconsistency between metadata and the size of the device. This could lead to the OSD(s) crashing in future. You should redeploy the affected OSDs." + - interval: 30s + input_series: + - series: 'ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="BLUESTORE_SPURIOUS_READ_ERRORS"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="BLUESTORE_SPURIOUS_READ_ERRORS"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDReadErrors + - eval_time: 10m + alertname: CephOSDReadErrors + exp_alerts: + - exp_labels: + name: "BLUESTORE_SPURIOUS_READ_ERRORS" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#bluestore-spurious-read-errors + summary: Device read errors detected + description: "An OSD has encountered read errors, but the OSD has recovered by retrying the reads. This may indicate an issue with hardware or the kernel." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OSD_DOWN"}' + values: '0+0x2 1+0x10' + - series: 'ceph_osd_up{ceph_daemon="osd.0"}' + values: '1+0x12' + - series: 'ceph_osd_up{ceph_daemon="osd.1"}' + values: '1+0x2 0+0x10' + - series: 'ceph_osd_up{ceph_daemon="osd.2"}' + values: '1+0x12' + - series: 'ceph_osd_metadata{ceph_daemon="osd.0", hostname="ceph-osd-1"}' + values: '1+0x12' + - series: 'ceph_osd_metadata{ceph_daemon="osd.1", hostname="ceph-osd-2"}' + values: '1+0x12' + - series: 'ceph_osd_metadata{ceph_daemon="osd.2", hostname="ceph-osd-3"}' + values: '1+0x12' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_DOWN"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_DOWN"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDDown + - eval_time: 10m + alertname: CephOSDDown + exp_alerts: + - exp_labels: + name: "OSD_DOWN" + severity: warning + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.4.2 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-down + summary: An OSD has been marked down + description: "1 OSD down for over 5mins. The following OSD is down: - osd.1 on ceph-osd-2\n" + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OSD_NEARFULL"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_NEARFULL"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_NEARFULL"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDNearFull + - eval_time: 10m + alertname: CephOSDNearFull + exp_alerts: + - exp_labels: + name: "OSD_NEARFULL" + severity: warning + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.4.3 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-nearfull + summary: OSD(s) running low on free space (NEARFULL) + description: One or more OSDs have reached the NEARFULL threshold. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data. + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OSD_FULL"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_FULL"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_FULL"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDFull + - eval_time: 10m + alertname: CephOSDFull + exp_alerts: + - exp_labels: + name: "OSD_FULL" + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.4.6 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-full + summary: OSD full, writes blocked + description: An OSD has reached the FULL threshold. Writes to pools that share the affected OSD will be blocked. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data. + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OSD_BACKFILLFULL"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_BACKFILLFULL"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_BACKFILLFULL"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDBackfillFull + - eval_time: 10m + alertname: CephOSDBackfillFull + exp_alerts: + - exp_labels: + name: "OSD_BACKFILLFULL" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-backfillfull + summary: OSD(s) too full for backfill operations + description: "An OSD has reached the BACKFILL FULL threshold. This will prevent rebalance operations from completing. Use 'ceph health detail' and 'ceph osd df' to identify the problem. To resolve, add capacity to the affected OSD's failure domain, restore down/out OSDs, or delete unwanted data." + - interval: 30s + input_series: + - series: 'ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="OSD_TOO_MANY_REPAIRS"} == 0 + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="OSD_TOO_MANY_REPAIRS"}' + value: 0 + alert_rule_test: + - eval_time: 1m + alertname: CephOSDTooManyRepairs + - eval_time: 10m + alertname: CephOSDTooManyRepairs + exp_alerts: + - exp_labels: + name: "OSD_TOO_MANY_REPAIRS" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#osd-too-many-repairs + summary: OSD reports a high number of read errors + description: Reads from an OSD have used a secondary PG to return data to the client, indicating a potential failing drive. +# Pools + # trigger percent full prediction on pools 1 and 2 only + - interval: 12h + input_series: + - series: 'ceph_pool_percent_used{pool_id="1", instance="9090"}' + values: '1 1 1 1 1' + - series: 'ceph_pool_percent_used{pool_id="1", instance="8090"}' + values: '78 89 79 98 78' + - series: 'ceph_pool_percent_used{pool_id="2", instance="9090"}' + values: '1 1 1 1 1' + - series: 'ceph_pool_percent_used{pool_id="2", instance="8090"}' + values: '22 22 23 23 24' + - series: 'ceph_pool_metadata{pool_id="1" , instance="9090" ,name="rbd",type="replicated"}' + values: '1 1 1 1 1' + - series: 'ceph_pool_metadata{pool_id="1", instance="8090",name="default.rgw.index",type="replicated"}' + values: '1 1 1 1 1' + - series: 'ceph_pool_metadata{pool_id="2" , instance="9090" ,name="rbd",type="replicated"}' + values: '1 1 1 1 1' + - series: 'ceph_pool_metadata{pool_id="2", instance="8090",name="default.rgw.index",type="replicated"}' + values: '1 1 1 1 1' + promql_expr_test: + - expr: | + (predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id, instance) + group_right() ceph_pool_metadata) >= 95 + eval_time: 36h + exp_samples: + - labels: '{instance="8090",name="default.rgw.index",pool_id="1",type="replicated"}' + value: 1.435E+02 # 142% + alert_rule_test: + - eval_time: 48h + alertname: CephPoolGrowthWarning + exp_alerts: + - exp_labels: + instance: 8090 + name: default.rgw.index + pool_id: 1 + severity: warning + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.9.2 + exp_annotations: + summary: Pool growth rate may soon exceed capacity + description: Pool 'default.rgw.index' will be full in less than 5 days assuming the average fill-up rate of the past 48 hours. + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="POOL_BACKFILLFULL"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="POOL_BACKFILLFULL"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="POOL_BACKFILLFULL"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephPoolBackfillFull + - eval_time: 5m + alertname: CephPoolBackfillFull + exp_alerts: + - exp_labels: + name: "POOL_BACKFILLFULL" + severity: warning + type: ceph_default + exp_annotations: + summary: Free space in a pool is too low for recovery/backfill + description: A pool is approaching the near full threshold, which will prevent recovery/backfill operations from completing. Consider adding more capacity. + + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="POOL_NEAR_FULL"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="POOL_NEAR_FULL"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="POOL_NEAR_FULL"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephPoolNearFull + - eval_time: 10m + alertname: CephPoolNearFull + exp_alerts: + - exp_labels: + name: "POOL_NEAR_FULL" + severity: warning + type: ceph_default + exp_annotations: + summary: One or more Ceph pools are nearly full + description: "A pool has exceeded the warning (percent full) threshold, or OSDs supporting the pool have reached the NEARFULL threshold. Writes may continue, but you are at risk of the pool going read-only if more capacity isn't made available. Determine the affected pool with 'ceph df detail', looking at QUOTA BYTES and STORED. Increase the pool's quota, or add capacity to the cluster first then increase the pool's quota (e.g. ceph osd pool set quota <pool_name> max_bytes <bytes>). Also ensure that the balancer is active." + +# PGs + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="PG_NOT_SCRUBBED"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="PG_NOT_SCRUBBED"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="PG_NOT_SCRUBBED"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephPGNotScrubbed + - eval_time: 10m + alertname: CephPGNotScrubbed + exp_alerts: + - exp_labels: + name: "PG_NOT_SCRUBBED" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-scrubbed + summary: Placement group(s) have not been scrubbed + description: "One or more PGs have not been scrubbed recently. Scrubs check metadata integrity, protecting against bit-rot. They check that metadata is consistent across data replicas. When PGs miss their scrub interval, it may indicate that the scrub window is too small, or PGs were not in a 'clean' state during the scrub window. You can manually initiate a scrub with: ceph pg scrub <pgid>" + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="PG_DAMAGED"}' + values: '0+0x4 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name=~"PG_DAMAGED|OSD_SCRUB_ERRORS"} == 1 + eval_time: 5m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="PG_DAMAGED"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephPGsDamaged + - eval_time: 10m + alertname: CephPGsDamaged + exp_alerts: + - exp_labels: + name: "PG_DAMAGED" + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.7.4 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-damaged + summary: Placement group damaged, manual intervention needed + description: During data consistency checks (scrub), at least one PG has been flagged as being damaged or inconsistent. Check to see which PG is affected, and attempt a manual repair if necessary. To list problematic placement groups, use 'rados list-inconsistent-pg <pool>'. To repair PGs use the 'ceph pg repair <pg_num>' command. + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="TOO_MANY_PGS"}' + values: '0+0x4 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="TOO_MANY_PGS"} == 1 + eval_time: 5m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="TOO_MANY_PGS"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephPGsHighPerOSD + - eval_time: 10m + alertname: CephPGsHighPerOSD + exp_alerts: + - exp_labels: + name: "TOO_MANY_PGS" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#too-many-pgs + summary: Placement groups per OSD is too high + description: "The number of placement groups per OSD is too high (exceeds the mon_max_pg_per_osd setting).\n Check that the pg_autoscaler has not been disabled for any pools with 'ceph osd pool autoscale-status', and that the profile selected is appropriate. You may also adjust the target_size_ratio of a pool to guide the autoscaler based on the expected relative size of the pool ('ceph osd pool set cephfs.cephfs.meta target_size_ratio .1') or set the pg_autoscaler mode to 'warn' and adjust pg_num appropriately for one or more pools." + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="PG_RECOVERY_FULL"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="PG_RECOVERY_FULL"} == 0 + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="PG_RECOVERY_FULL"}' + value: 0 + alert_rule_test: + - eval_time: 1m + alertname: CephPGRecoveryAtRisk + - eval_time: 10m + alertname: CephPGRecoveryAtRisk + exp_alerts: + - exp_labels: + name: "PG_RECOVERY_FULL" + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.7.5 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-recovery-full + summary: OSDs are too full for recovery + description: Data redundancy is at risk since one or more OSDs are at or above the 'full' threshold. Add more capacity to the cluster, restore down/out OSDs, or delete unwanted data. + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="PG_BACKFILL_FULL"}' + values: '0+0x2 1+0x20' + promql_expr_test: + - expr: ceph_health_detail{name="PG_BACKFILL_FULL"} == 0 + eval_time: 1m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="PG_BACKFILL_FULL"}' + value: 0 + alert_rule_test: + - eval_time: 1m + alertname: CephPGBackfillAtRisk + - eval_time: 10m + alertname: CephPGBackfillAtRisk + exp_alerts: + - exp_labels: + name: "PG_BACKFILL_FULL" + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.7.6 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-backfill-full + summary: Backfill operations are blocked due to lack of free space + description: Data redundancy may be at risk due to lack of free space within the cluster. One or more OSDs have reached the 'backfillfull' threshold. Add more capacity, or delete unwanted data. + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="PG_AVAILABILITY"}' + values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_health_detail{name="OSD_DOWN"}' + values: '0 0 0 1 1 1 1 1 1 0 0 0 0 0 0 0' + promql_expr_test: + - expr: ((ceph_health_detail{name="PG_AVAILABILITY"} == 1) - scalar(ceph_health_detail{name="OSD_DOWN"})) + eval_time: 1m + # empty set at 1m + exp_samples: + alert_rule_test: + # PG_AVAILABILITY and OSD_DOWN not firing .. no alert + - eval_time: 1m + alertname: CephPGUnavilableBlockingIO + exp_alerts: + # PG_AVAILABILITY firing, but osd_down is active .. no alert + - eval_time: 5m + alertname: CephPGUnavilableBlockingIO + exp_alerts: + # PG_AVAILABILITY firing, AND OSD_DOWN is not active...raise the alert + - eval_time: 15m + alertname: CephPGUnavilableBlockingIO + exp_alerts: + - exp_labels: + name: "PG_AVAILABILITY" + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.7.3 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-availability + summary: PG is unavailable, blocking I/O + description: Data availability is reduced, impacting the cluster's ability to service I/O. One or more placement groups (PGs) are in a state that blocks I/O. + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"}' + values: '0+0x2 1+0x10' + promql_expr_test: + - expr: ceph_health_detail{name="PG_NOT_DEEP_SCRUBBED"} == 1 + eval_time: 3m + exp_samples: + - labels: '{__name__="ceph_health_detail", name="PG_NOT_DEEP_SCRUBBED"}' + value: 1 + alert_rule_test: + - eval_time: 1m + alertname: CephPGNotDeepScrubbed + - eval_time: 10m + alertname: CephPGNotDeepScrubbed + exp_alerts: + - exp_labels: + name: "PG_NOT_DEEP_SCRUBBED" + severity: warning + type: ceph_default + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#pg-not-deep-scrubbed + summary: Placement group(s) have not been deep scrubbed + description: One or more PGs have not been deep scrubbed recently. Deep scrubs protect against bit-rot. They compare data replicas to ensure consistency. When PGs miss their deep scrub interval, it may indicate that the window is too small or PGs were not in a 'clean' state during the deep-scrub window. + +# Prometheus + - interval: 1m + input_series: + - series: 'up{job="myjob"}' + values: '1+0x10' + promql_expr_test: + - expr: absent(up{job="ceph"}) + eval_time: 1m + exp_samples: + - labels: '{job="ceph"}' + value: 1 + alert_rule_test: + - eval_time: 5m + alertname: PrometheusJobMissing + exp_alerts: + - exp_labels: + job: ceph + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.12.1 + exp_annotations: + summary: The scrape job for Ceph is missing from Prometheus + description: The prometheus job that scrapes from Ceph is no longer defined, this will effectively mean you'll have no metrics or alerts for the cluster. Please review the job definitions in the prometheus.yml file of the prometheus instance. +# RADOS + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="OBJECT_UNFOUND"}' + values: '0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_osd_up{ceph_daemon="osd.0"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_osd_up{ceph_daemon="osd.1"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_osd_up{ceph_daemon="osd.2"}' + values: '1 1 1 0 0 0 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_osd_metadata{ceph_daemon="osd.0"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_osd_metadata{ceph_daemon="osd.1"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + - series: 'ceph_osd_metadata{ceph_daemon="osd.2"}' + values: '1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: (ceph_health_detail{name="OBJECT_UNFOUND"} == 1) * on() (count(ceph_osd_up == 1) == bool count(ceph_osd_metadata)) == 1 + eval_time: 1m + exp_samples: + alert_rule_test: + # OBJECT_UNFOUND but osd.2 is down, so don't fire + - eval_time: 5m + alertname: CephObjectMissing + exp_alerts: + # OBJECT_UNFOUND and all osd's are online, so fire + - eval_time: 15m + alertname: CephObjectMissing + exp_alerts: + - exp_labels: + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.10.1 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks#object-unfound + summary: Object(s) marked UNFOUND + description: The latest version of a RADOS object can not be found, even though all OSDs are up. I/O requests for this object from clients will block (hang). Resolving this issue may require the object to be rolled back to a prior version manually, and manually verified. +# Generic Alerts + - interval: 1m + input_series: + - series: 'ceph_health_detail{name="RECENT_CRASH"}' + values: '0 0 0 1 1 1 1 1 1 1 1' + promql_expr_test: + - expr: ceph_health_detail{name="RECENT_CRASH"} == 1 + eval_time: 1m + exp_samples: + alert_rule_test: + # not firing + - eval_time: 1m + alertname: CephDaemonCrash + exp_alerts: + # firing + - eval_time: 10m + alertname: CephDaemonCrash + exp_alerts: + - exp_labels: + name: RECENT_CRASH + severity: critical + type: ceph_default + oid: 1.3.6.1.4.1.50495.1.2.1.1.2 + exp_annotations: + documentation: https://docs.ceph.com/en/latest/rados/operations/health-checks/#recent-crash + summary: One or more Ceph daemons have crashed, and are pending acknowledgement + description: One or more daemons have crashed recently, and need to be acknowledged. This notification ensures that software crashes do not go unseen. To acknowledge a crash, use the 'ceph crash archive <id>' command. diff --git a/monitoring/ceph-mixin/tests_alerts/test_syntax.py b/monitoring/ceph-mixin/tests_alerts/test_syntax.py new file mode 100755 index 000000000..966d768bd --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/test_syntax.py @@ -0,0 +1,42 @@ +import pytest +import os +import yaml +from .utils import promtool_available, call +from .settings import ALERTS_FILE, UNIT_TESTS_FILE + + +def load_yaml(file_name): + yaml_data = None + with open(file_name, 'r') as alert_file: + raw = alert_file.read() + try: + yaml_data = yaml.safe_load(raw) + except yaml.YAMLError as e: + pass + + return yaml_data + + +def test_alerts_present(): + assert os.path.exists(ALERTS_FILE), f"{ALERTS_FILE} not found" + + +def test_unittests_present(): + assert os.path.exists(UNIT_TESTS_FILE), f"{UNIT_TESTS_FILE} not found" + + +@pytest.mark.skipif(not os.path.exists(ALERTS_FILE), reason=f"{ALERTS_FILE} missing") +def test_rules_format(): + assert load_yaml(ALERTS_FILE) + + +@pytest.mark.skipif(not os.path.exists(UNIT_TESTS_FILE), reason=f"{UNIT_TESTS_FILE} missing") +def test_unittests_format(): + assert load_yaml(UNIT_TESTS_FILE) + + +@pytest.mark.skipif(not promtool_available(), reason="promtool is not installed. Unable to check syntax") +def test_rule_syntax(): + completion = call(f"promtool check rules {ALERTS_FILE}") + assert completion.returncode == 0 + assert b"SUCCESS" in completion.stdout diff --git a/monitoring/ceph-mixin/tests_alerts/test_unittests.py b/monitoring/ceph-mixin/tests_alerts/test_unittests.py new file mode 100644 index 000000000..4cfb2b600 --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/test_unittests.py @@ -0,0 +1,19 @@ +import pytest +import os +from .utils import promtool_available, call +from .settings import ALERTS_FILE, UNIT_TESTS_FILE + + +def test_alerts_present(): + assert os.path.exists(ALERTS_FILE), f"{ALERTS_FILE} not found" + + +def test_unittests_present(): + assert os.path.exists(UNIT_TESTS_FILE), f"{UNIT_TESTS_FILE} not found" + + +@pytest.mark.skipif(not promtool_available(), reason="promtool is not installed. Unable to run unit tests") +def test_run_unittests(): + completion = call(f"promtool test rules {UNIT_TESTS_FILE}") + assert completion.returncode == 0 + assert b"SUCCESS" in completion.stdout diff --git a/monitoring/ceph-mixin/tests_alerts/utils.py b/monitoring/ceph-mixin/tests_alerts/utils.py new file mode 100644 index 000000000..842924447 --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/utils.py @@ -0,0 +1,12 @@ +import pytest +import shutil +import subprocess + + +def promtool_available() -> bool: + return shutil.which('promtool') is not None + + +def call(cmd): + completion = subprocess.run(cmd.split(), stdout=subprocess.PIPE) + return completion diff --git a/monitoring/ceph-mixin/tests_alerts/validate_rules.py b/monitoring/ceph-mixin/tests_alerts/validate_rules.py new file mode 100755 index 000000000..c24ce5c59 --- /dev/null +++ b/monitoring/ceph-mixin/tests_alerts/validate_rules.py @@ -0,0 +1,571 @@ +#!/usr/bin/env python3 +# +# Check the Prometheus rules for format, and integration +# with the unit tests. This script has the following exit +# codes: +# 0 .. Everything worked +# 4 .. rule problems or missing unit tests +# 8 .. Missing fields in YAML +# 12 .. Invalid YAML - unable to load +# 16 .. Missing input files +# +# Externals +# snmptranslate .. used to determine the oid's in the MIB to verify the rule -> MIB is correct +# + +import re +import os +import sys +import yaml +import shutil +import string +from bs4 import BeautifulSoup +from typing import List, Any, Dict, Set, Optional, Tuple +import subprocess + +import urllib.request +import urllib.error +from urllib.parse import urlparse + +from settings import ALERTS_FILE, MIB_FILE, UNIT_TESTS_FILE + +DOCLINK_NAME = 'documentation' + + +def isascii(s: str) -> bool: + try: + s.encode('ascii') + except UnicodeEncodeError: + return False + return True + + +def read_file(file_name: str) -> Tuple[str, str]: + try: + with open(file_name, 'r') as input_file: + raw_data = input_file.read() + except OSError: + return '', f"Unable to open {file_name}" + + return raw_data, '' + + +def load_yaml(file_name: str) -> Tuple[Dict[str, Any], str]: + data = {} + errs = '' + + raw_data, err = read_file(file_name) + if not err: + + try: + data = yaml.safe_load(raw_data) + except yaml.YAMLError as e: + errs = f"filename '{file_name} is not a valid YAML file" + + return data, errs + + +def run_command(command: str): + c = command.split() + completion = subprocess.run(c, stdout=subprocess.PIPE, stderr=subprocess.PIPE) + return (completion.returncode, + completion.stdout.decode('utf-8').split('\n'), + completion.stderr.decode('utf-8').split('\n')) + + +class HTMLCache: + def __init__(self) -> None: + self.cache: Dict[str, Tuple[int, str]] = {} + + def fetch(self, url_str: str) -> None: + parsed = urlparse(url_str) + url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}" + + if url in self.cache: + return self.cache[url] + + req = urllib.request.Request(url) + try: + r = urllib.request.urlopen(req) + except urllib.error.HTTPError as e: + self.cache[url] = e.code, e.reason + return self.cache[url] + except urllib.error.URLError as e: + self.cache[url] = 400, e.reason + return self.cache[url] + + if r.status == 200: + html = r.read().decode('utf-8') + self.cache[url] = 200, html + return self.cache[url] + + self.cache[url] = r.status, r.reason + return r.status, r.reason + + @property + def cached_pages(self) -> List[str]: + return self.cache.keys() + + @property + def cached_pages_total(self) -> int: + return len(self.cache.keys()) + +class PrometheusRule: + expected_attrs = [ + 'alert', + 'expr', + 'labels', + 'annotations' + ] + + def __init__(self, rule_group, rule_data: Dict[str, Any]): + + assert 'alert' in rule_data + self.group: RuleGroup = rule_group + self.name = rule_data.get('alert') + self.rule = rule_data + self.errors: List[str] = [] + self.warnings: List[str] = [] + self.validate() + + @property + def has_oid(self): + return True if self.rule.get('labels', {}).get('oid', '') else False + + @property + def labels(self) -> Dict[str, str]: + return self.rule.get('labels', {}) + + @property + def annotations(self) -> Dict[str, str]: + return self.rule.get('annotations', {}) + + def _check_alert_name(self): + # this is simplistic, but works in the context of the alert name + if self.name[0] in string.ascii_uppercase and \ + self.name != self.name.lower() and \ + self.name != self.name.upper() and \ + " " not in self.name and \ + "_" not in self.name: + return + + self.warnings.append("Alert name is not in CamelCase format") + + def _check_structure(self): + rule_attrs = self.rule.keys() + missing_attrs = [a for a in PrometheusRule.expected_attrs if a not in rule_attrs] + + if missing_attrs: + self.errors.append( + f"invalid alert structure. Missing field{'s' if len(missing_attrs) > 1 else ''}" + f": {','.join(missing_attrs)}") + + def _check_labels(self): + for rqd in ['severity', 'type']: + if rqd not in self.labels.keys(): + self.errors.append(f"rule is missing {rqd} label definition") + + def _check_annotations(self): + for rqd in ['summary', 'description']: + if rqd not in self.annotations: + self.errors.append(f"rule is missing {rqd} annotation definition") + + def _check_doclink(self): + doclink = self.annotations.get(DOCLINK_NAME, '') + + if doclink: + url = urlparse(doclink) + status, content = self.group.fetch_html_page(doclink) + if status == 200: + if url.fragment: + soup = BeautifulSoup(content, 'html.parser') + if not soup.find(id=url.fragment): + self.errors.append(f"documentation link error: {url.fragment} anchor not found on the page") + else: + # catch all + self.errors.append(f"documentation link error: {status} {content}") + + def _check_snmp(self): + oid = self.labels.get('oid', '') + + if self.labels.get('severity', '') == 'critical' and not oid: + self.warnings.append("critical level alert is missing an SNMP oid entry") + if oid and not re.search('^1.3.6.1.4.1.50495.1.2.\\d+.\\d+.\\d+$', oid): + self.errors.append("invalid OID format provided") + if self.group.get_oids(): + if oid and oid not in self.group.get_oids(): + self.errors.append(f"rule defines an OID {oid} that is missing from the MIB file({os.path.basename(MIB_FILE)})") + + def _check_ascii(self): + if 'oid' not in self.labels: + return + + desc = self.annotations.get('description', '') + summary = self.annotations.get('summary', '') + if not isascii(desc): + self.errors.append(f"non-ascii characters found in 'description' field will cause issues in associated snmp trap.") + if not isascii(summary): + self.errors.append(f"non-ascii characters found in 'summary' field will cause issues in associated snmp trap.") + + def validate(self): + + self._check_alert_name() + self._check_structure() + self._check_labels() + self._check_annotations() + self._check_doclink() + self._check_snmp() + self._check_ascii() + char = '.' + + if self.errors: + char = 'E' + self.group.update('error', self.name) + elif self.warnings: + char = 'W' + self.group.update('warning', self.name) + + sys.stdout.write(char) + + +class RuleGroup: + + def __init__(self, rule_file, group_name: str, group_name_width: int): + self.rule_file: RuleFile = rule_file + self.group_name = group_name + self.rules: Dict[str, PrometheusRule] = {} + self.problems = { + "error": [], + "warning": [], + } + + sys.stdout.write(f"\n\t{group_name:<{group_name_width}} : ") + + def add_rule(self, rule_data:Dict[str, Any]): + alert_name = rule_data.get('alert') + self.rules[alert_name] = PrometheusRule(self, rule_data) + + def update(self, problem_type:str, alert_name:str): + assert problem_type in ['error', 'warning'] + + self.problems[problem_type].append(alert_name) + self.rule_file.update(self.group_name) + + def fetch_html_page(self, url): + return self.rule_file.fetch_html_page(url) + + def get_oids(self): + return self.rule_file.oid_list + + @property + def error_count(self): + return len(self.problems['error']) + + def warning_count(self): + return len(self.problems['warning']) + + @property + def count(self): + return len(self.rules) + + +class RuleFile: + + def __init__(self, parent, file_name, rules, oid_list): + self.parent = parent + self.file_name = file_name + self.rules: Dict[str, Any] = rules + self.oid_list = oid_list + self.problems: Set[str] = set() + self.group: Dict[str, RuleGroup] = {} + self.alert_names_seen: Set[str] = set() + self.duplicate_alert_names:List[str] = [] + self.html_cache = HTMLCache() + + assert 'groups' in self.rules + self.max_group_name_width = self.get_max_group_name() + self.load_groups() + + def update(self, group_name): + self.problems.add(group_name) + self.parent.mark_invalid() + + def fetch_html_page(self, url): + return self.html_cache.fetch(url) + + @property + def group_count(self): + return len(self.rules['groups']) + + @property + def rule_count(self): + rule_count = 0 + for _group_name, rule_group in self.group.items(): + rule_count += rule_group.count + return rule_count + + @property + def oid_count(self): + oid_count = 0 + for _group_name, rule_group in self.group.items(): + for _rule_name, rule in rule_group.rules.items(): + if rule.has_oid: + oid_count += 1 + return oid_count + + @property + def group_names(self): + return self.group.keys() + + @property + def problem_count(self): + return len(self.problems) + + def get_max_group_name(self): + group_name_list = [] + for group in self.rules.get('groups'): + group_name_list.append(group['name']) + return max([len(g) for g in group_name_list]) + + def load_groups(self): + sys.stdout.write("\nChecking rule groups") + for group in self.rules.get('groups'): + group_name = group['name'] + rules = group['rules'] + self.group[group_name] = RuleGroup(self, group_name, self.max_group_name_width) + for rule_data in rules: + if 'alert' in rule_data: + alert_name = rule_data.get('alert') + if alert_name in self.alert_names_seen: + self.duplicate_alert_names.append(alert_name) + else: + self.alert_names_seen.add(alert_name) + self.group[group_name].add_rule(rule_data) + else: + # skipped recording rule + pass + + def report(self): + def max_width(item_list: Set[str], min_width: int = 0) -> int: + return max([len(i) for i in item_list] + [min_width]) + + if not self.problems and not self.duplicate_alert_names: + print("\nNo problems detected in the rule file") + return + + print("\nProblem Report\n") + + group_width = max_width(self.problems, 5) + alert_names = set() + for g in self.problems: + group = self.group[g] + alert_names.update(group.problems.get('error', [])) + alert_names.update(group.problems.get('warning', [])) + alert_width = max_width(alert_names, 10) + + template = " {group:<{group_width}} {severity:<8} {alert_name:<{alert_width}} {description}" + + print(template.format( + group="Group", + group_width=group_width, + severity="Severity", + alert_name="Alert Name", + alert_width=alert_width, + description="Problem Description")) + + print(template.format( + group="-----", + group_width=group_width, + severity="--------", + alert_name="----------", + alert_width=alert_width, + description="-------------------")) + + for group_name in sorted(self.problems): + group = self.group[group_name] + rules = group.rules + for alert_name in group.problems.get('error', []): + for desc in rules[alert_name].errors: + print(template.format( + group=group_name, + group_width=group_width, + severity="Error", + alert_name=alert_name, + alert_width=alert_width, + description=desc)) + for alert_name in group.problems.get('warning', []): + for desc in rules[alert_name].warnings: + print(template.format( + group=group_name, + group_width=group_width, + severity="Warning", + alert_name=alert_name, + alert_width=alert_width, + description=desc)) + if self.duplicate_alert_names: + print("Duplicate alert names detected:") + for a in self.duplicate_alert_names: + print(f" - {a}") + + +class UnitTests: + expected_attrs = [ + 'rule_files', + 'tests', + 'evaluation_interval' + ] + def __init__(self, filename): + self.filename = filename + self.unit_test_data: Dict[str, Any] = {} + self.alert_names_seen: Set[str] = set() + self.problems: List[str] = [] + self.load() + + def load(self): + self.unit_test_data, errs = load_yaml(self.filename) + if errs: + print(f"\n\nError in unit tests file: {errs}") + sys.exit(12) + + missing_attr = [a for a in UnitTests.expected_attrs if a not in self.unit_test_data.keys()] + if missing_attr: + print(f"\nMissing attributes in unit tests: {','.join(missing_attr)}") + sys.exit(8) + + def _check_alert_names(self, alert_names: List[str]): + alerts_tested: Set[str] = set() + for t in self.unit_test_data.get('tests'): + test_cases = t.get('alert_rule_test', []) + if not test_cases: + continue + for case in test_cases: + alertname = case.get('alertname', '') + if alertname: + alerts_tested.add(alertname) + + alerts_defined = set(alert_names) + self.problems = list(alerts_defined.difference(alerts_tested)) + + def process(self, defined_alert_names: List[str]): + self._check_alert_names(defined_alert_names) + + def report(self) -> None: + + if not self.problems: + print("\nNo problems detected in unit tests file") + return + + print("\nUnit tests are incomplete. Tests missing for the following alerts;") + for p in self.problems: + print(f" - {p}") + +class RuleChecker: + + def __init__(self, rules_filename: str = None, test_filename: str = None): + self.rules_filename = rules_filename or ALERTS_FILE + self.test_filename = test_filename or UNIT_TESTS_FILE + self.rule_file: Optional[RuleFile] = None + self.unit_tests: Optional[UnitTests] = None + self.rule_file_problems: bool = False + self.errors = {} + self.warnings = {} + self.error_count = 0 + self.warning_count = 0 + self.oid_count = 0 + + self.oid_list = self.build_oid_list() + + def build_oid_list(self) -> List[str]: + + cmd = shutil.which('snmptranslate') + if not cmd: + return [] + + rc, stdout, stderr = run_command(f"{cmd} -Pu -Tz -M ../../snmp:/usr/share/snmp/mibs -m CEPH-MIB") + if rc != 0: + return [] + + oid_list: List[str] = [] + for line in stdout[:-1]: + _label, oid = line.replace('"', '').replace('\t', ' ').split() + oid_list.append(oid) + + return oid_list + + @property + def status(self): + if self.rule_file_problems or self.unit_tests.problems: + return 4 + + return 0 + + def mark_invalid(self): + self.rule_file_problems = True + + def summarise_rule_file(self): + for group_name in self.rule_file.problems: + group = self.rule_file.group[group_name] + self.error_count += len(group.problems['error']) + self.warning_count += len(group.problems['warning']) + + def ready(self): + errs: List[str] = [] + ready_state = True + if not os.path.exists(self.rules_filename): + errs.append(f"rule file '{self.rules_filename}' not found") + ready_state = False + + if not os.path.exists(self.test_filename): + errs.append(f"test file '{self.test_filename}' not found") + ready_state = False + + return ready_state, errs + + def run(self): + + ready, errs = self.ready() + if not ready: + print("Unable to start:") + for e in errs: + print(f"- {e}") + sys.exit(16) + + rules, errs = load_yaml(self.rules_filename) + if errs: + print(errs) + sys.exit(12) + + self.rule_file = RuleFile(self, self.rules_filename, rules, self.oid_list) + self.summarise_rule_file() + + self.unit_tests = UnitTests(self.test_filename) + self.unit_tests.process(self.rule_file.alert_names_seen) + + def report(self): + print("\n\nSummary\n") + print(f"Rule file : {self.rules_filename}") + print(f"Unit Test file : {self.test_filename}") + print(f"\nRule groups processed : {self.rule_file.group_count:>3}") + print(f"Rules processed : {self.rule_file.rule_count:>3}") + print(f"SNMP OIDs declared : {self.rule_file.oid_count:>3} {'(snmptranslate missing, unable to cross check)' if not self.oid_list else ''}") + print(f"Rule errors : {self.error_count:>3}") + print(f"Rule warnings : {self.warning_count:>3}") + print(f"Rule name duplicates : {len(self.rule_file.duplicate_alert_names):>3}") + print(f"Unit tests missing : {len(self.unit_tests.problems):>3}") + + self.rule_file.report() + self.unit_tests.report() + + +def main(): + checker = RuleChecker() + + checker.run() + checker.report() + print() + + sys.exit(checker.status) + + +if __name__ == '__main__': + main() diff --git a/monitoring/ceph-mixin/tests_dashboards/__init__.py b/monitoring/ceph-mixin/tests_dashboards/__init__.py new file mode 100644 index 000000000..45147e5c3 --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/__init__.py @@ -0,0 +1,189 @@ +import re +import subprocess +import sys +import tempfile +from dataclasses import asdict, dataclass, field +from typing import Any, List + +import yaml + +from .util import replace_grafana_expr_variables + + +@dataclass +class InputSeries: + series: str = '' + values: str = '' + +@dataclass +class ExprSample: + labels: str = '' + value: float = -1 + +@dataclass +class PromqlExprTest: + expr: str = '' + eval_time: str = '1m' + exp_samples: List[ExprSample] = field(default_factory=list) + +@dataclass +class Test: + interval: str = '1m' + input_series: List[InputSeries] = field(default_factory=list) + promql_expr_test: List[PromqlExprTest] = field(default_factory=list) + + +@dataclass +class TestFile: + evaluation_interval: str = '1m' + tests: List[Test] = field(default_factory=list) + + +class PromqlTest: + """ + Base class to provide prometheus query test capabilities. After setting up + the query test with its input and expected output it's expected to run promtool. + + https://prometheus.io/docs/prometheus/latest/configuration/unit_testing_rules/#test-yml + + The workflow of testing would be something like: + + # add prometheus query to test + self.set_expression('bonding_slaves > 0') + + # add some prometheus input series + self.add_series('bonding_slaves{master="bond0"}', '2') + self.add_series('bonding_slaves{master="bond1"}', '3') + self.add_series('node_network_receive_bytes{instance="127.0.0.1", + device="eth1"}', "10 100 230 22") + + # expected output of the query + self.add_exp_samples('bonding_slaves{master="bond0"}', 2) + self.add_exp_samples('bonding_slaves{master="bond1"}', 3) + + # at last, always call promtool with: + self.assertTrue(self.run_promtool()) + # assertTrue means it expect promtool to succeed + """ + + def __init__(self): + self.test_output_file = tempfile.NamedTemporaryFile('w+') + + self.test_file = TestFile() + self.test = Test() + self.promql_expr_test = PromqlExprTest() + self.test.promql_expr_test.append(self.promql_expr_test) + self.test_file.tests.append(self.test) + + self.variables = {} + + def __del__(self): + self.test_output_file.close() + + + def set_evaluation_interval(self, interval: int, unit: str = 'm') -> None: + """ + Set the evaluation interval of the time series + + Args: + interval (int): number of units. + unit (str): unit type: 'ms', 's', 'm', etc... + """ + self.test_file.evaluation_interval = f'{interval}{unit}' + + def set_interval(self, interval: int, unit: str = 'm') -> None: + """ + Set the duration of the time series + + Args: + interval (int): number of units. + unit (str): unit type: 'ms', 's', 'm', etc... + """ + self.test.interval = f'{interval}{unit}' + + def set_expression(self, expr: str) -> None: + """ + Set the prometheus expression/query used to filter data. + + Args: + expr(str): expression/query. + """ + self.promql_expr_test.expr = expr + + def add_series(self, series: str, values: str) -> None: + """ + Add a series to the input. + + Args: + series(str): Prometheus series. + Notation: '<metric name>{<label name>=<label value>, ...}' + values(str): Value of the series. + """ + input_series = InputSeries(series=series, values=values) + self.test.input_series.append(input_series) + + def set_eval_time(self, eval_time: int, unit: str = 'm') -> None: + """ + Set the time when the expression will be evaluated + + Args: + interval (int): number of units. + unit (str): unit type: 'ms', 's', 'm', etc... + """ + self.promql_expr_test.eval_time = f'{eval_time}{unit}' + + def add_exp_samples(self, sample: str, values: Any) -> None: + """ + Add an expected sample/output of the query given the series/input + + Args: + sample(str): Expected sample. + Notation: '<metric name>{<label name>=<label value>, ...}' + values(Any): Value of the sample. + """ + expr_sample = ExprSample(labels=sample, value=values) + self.promql_expr_test.exp_samples.append(expr_sample) + + def set_variable(self, variable: str, value: str): + """ + If a query makes use of grafonnet variables, for example + '$osd_hosts', you should change this to a real value. Example: + + + > self.set_expression('bonding_slaves{master="$osd_hosts"} > 0') + > self.set_variable('osd_hosts', '127.0.0.1') + > print(self.query) + > bonding_slaves{master="127.0.0.1"} > 0 + + Args: + variable(str): Variable name + value(str): Value to replace variable with + + """ + self.variables[variable] = value + + def run_promtool(self): + """ + Run promtool to test the query after setting up the input, output + and extra parameters. + + Returns: + bool: True if successful, False otherwise. + """ + + for variable, value in self.variables.items(): + expr = self.promql_expr_test.expr + new_expr = replace_grafana_expr_variables(expr, variable, value) + self.set_expression(new_expr) + + test_as_dict = asdict(self.test_file) + yaml.dump(test_as_dict, self.test_output_file) + + args = f'promtool test rules {self.test_output_file.name}'.split() + try: + subprocess.run(args, check=True) + return True + except subprocess.CalledProcessError as process_error: + print(yaml.dump(test_as_dict)) + print(process_error.stderr) + return False diff --git a/monitoring/ceph-mixin/tests_dashboards/features/__init__.py b/monitoring/ceph-mixin/tests_dashboards/features/__init__.py new file mode 100644 index 000000000..e69de29bb --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/__init__.py diff --git a/monitoring/ceph-mixin/tests_dashboards/features/ceph-cluster.feature b/monitoring/ceph-mixin/tests_dashboards/features/ceph-cluster.feature new file mode 100644 index 000000000..1a446cd2c --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/ceph-cluster.feature @@ -0,0 +1,54 @@ +Feature: Ceph Cluster Dashboard + +Scenario: "Test total PG States" + Given the following series: + | metrics | values | + | ceph_pg_total{foo="var"} | 10 100 | + | ceph_pg_total{foo="bar"} | 20 200 | + Then Grafana panel `PG States` with legend `Total` shows: + | metrics | values | + | {} | 300 | + +Scenario: "Test OSDs in" + Given the following series: + | metrics | values | + | ceph_osd_in{ceph_daemon="osd.0"} | 1.0 | + | ceph_osd_in{ceph_daemon="osd.1"} | 0.0 | + | ceph_osd_in{ceph_daemon="osd.2"} | 1.0 | + When variable `instance` is `.*` + Then Grafana panel `OSDs` with legend `In` shows: + | metrics | values | + | {} | 2 | + +Scenario: "Test OSDs down" + Given the following series: + | metrics | values | + | ceph_osd_up{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 | + | ceph_osd_up{ceph_daemon="osd.1", instance="127.0.0.1"} | 0.0 | + | ceph_osd_up{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 | + When variable `instance` is `127.0.0.1` + Then Grafana panel `OSDs` with legend `Down` shows: + | metrics | values | + | {} | 3 | + +Scenario: "Test OSDs out" + Given the following series: + | metrics | values | + | ceph_osd_in{ceph_daemon="osd.0", instance="127.0.0.1"} | 0.0 | + | ceph_osd_in{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 | + | ceph_osd_in{ceph_daemon="osd.2", instance="127.0.0.1"} | 0.0 | + When variable `instance` is `127.0.0.1` + Then Grafana panel `OSDs` with legend `Out` shows: + | metrics | values | + | {} | 2 | + +Scenario: "Test OSDs all" + Given the following series: + | metrics | values | + | ceph_osd_metadata{ceph_daemon="osd.0", instance="127.0.0.1"} | 1.0 | + | ceph_osd_metadata{ceph_daemon="osd.1", instance="127.0.0.1"} | 1.0 | + | ceph_osd_metadata{ceph_daemon="osd.2", instance="127.0.0.1"} | 1.0 | + When variable `instance` is `127.0.0.1` + Then Grafana panel `OSDs` with legend `All` shows: + | metrics | values | + | {} | 3 | diff --git a/monitoring/ceph-mixin/tests_dashboards/features/environment.py b/monitoring/ceph-mixin/tests_dashboards/features/environment.py new file mode 100644 index 000000000..5dc76a09e --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/environment.py @@ -0,0 +1,135 @@ +# type: ignore[no-redef] +# pylint: disable=E0611,W0613,E0102 +import copy + +from behave import given, then, when +from prettytable import PrettyTable + +from tests_dashboards import PromqlTest +from tests_dashboards.util import get_dashboards_data, resolve_time_and_unit + + +class GlobalContext: + def __init__(self): + self.tested_queries_count = 0 + self.promql_expr_test = None + self.data = get_dashboards_data() + self.query_map = self.data['queries'] + + def reset_promql_test(self): + self.promql_expr_test = PromqlTest() + self.promql_expr_test.variables = copy.copy(self.data['variables']) + + def print_query_stats(self): + total = len(self.query_map) + table = PrettyTable() + table.field_names = ['Name', 'Queries', 'Tested', 'Cover'] + + def percent(tested, total): + return str(round((tested / total) * 100, 2)) + '%' + + def file_name(path): + return path.split('/')[-1] + + total = 0 + tested = 0 + for path, stat in self.data['stats'].items(): + assert stat['total'] + table.add_row([file_name(path), stat['total'], stat['tested'], + percent(stat['tested'], stat['total'])]) + total += stat['total'] + tested += stat['tested'] + + assert total + table.add_row(['Total', total, tested, percent(tested, total)]) + print(table) + + +global_context = GlobalContext() + +# Behave function overloading +# =========================== + + +def before_scenario(context, scenario): + global_context.reset_promql_test() + + +def after_scenario(context, scenario): + assert global_context.promql_expr_test.run_promtool() + + +def after_all(context): + global_context.print_query_stats() + + +@given("the following series") +def step_impl(context): + for row in context.table: + metric = row['metrics'] + value = row['values'] + global_context.promql_expr_test.add_series(metric, value) + + +@when('evaluation interval is `{interval}`') +def step_impl(context, interval): + interval_without_unit, unit = resolve_time_and_unit(interval) + if interval_without_unit is None: + raise ValueError(f'Invalid interval time: {interval_without_unit}. ' + + 'A valid time looks like "1m" where you have a number plus a unit') + global_context.promql_expr_test.set_evaluation_interval(interval_without_unit, unit) + + +@when('interval is `{interval}`') +def step_impl(context, interval): + interval_without_unit, unit = resolve_time_and_unit(interval) + if interval_without_unit is None: + raise ValueError(f'Invalid interval time: {interval_without_unit}. ' + + 'A valid time looks like "1m" where you have a number plus a unit') + global_context.promql_expr_test.set_interval(interval_without_unit, unit) + + +@when('evaluation time is `{eval_time}`') +def step_impl(context, eval_time): + eval_time_without_unit, unit = resolve_time_and_unit(eval_time) + if eval_time_without_unit is None: + raise ValueError(f'Invalid evalution time: {eval_time}. ' + + 'A valid time looks like "1m" where you have a number plus a unit') + global_context.promql_expr_test.set_eval_time(eval_time_without_unit, unit) + + +@when('variable `{variable}` is `{value}`') +def step_impl(context, variable, value): + global_context.promql_expr_test.set_variable(variable, value) + + +@then('Grafana panel `{panel_name}` with legend `{legend}` shows') +def step_impl(context, panel_name, legend): + """ + This step can have an empty legend. As 'behave' doesn't provide a way + to say it's empty we use EMPTY to mark as empty. + """ + if legend == "EMPTY": + legend = '' + query_id = panel_name + '-' + legend + if query_id not in global_context.query_map: + raise KeyError((f'Query with legend {legend} in panel "{panel_name}"' + 'couldn\'t be found')) + + expr = global_context.query_map[query_id]['query'] + global_context.promql_expr_test.set_expression(expr) + for row in context.table: + metric = row['metrics'] + value = row['values'] + global_context.promql_expr_test.add_exp_samples(metric, float(value)) + path = global_context.query_map[query_id]['path'] + global_context.data['stats'][path]['tested'] += 1 + + +@then('query `{query}` produces') +def step_impl(context, query): + global_context.promql_expr_test.set_expression(query) + for row in context.table: + metric = row['metrics'] + value = row['values'] + global_context.promql_expr_test.add_exp_samples(metric, float(value)) diff --git a/monitoring/ceph-mixin/tests_dashboards/features/host-details.feature b/monitoring/ceph-mixin/tests_dashboards/features/host-details.feature new file mode 100644 index 000000000..51e3c5819 --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/host-details.feature @@ -0,0 +1,131 @@ +Feature: Host Details Dashboard + +Scenario: "Test OSD" + Given the following series: + | metrics | values | + | ceph_osd_metadata{job="ceph",back_iface="",ceph_daemon="osd.0",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 | + | ceph_osd_metadata{job="ceph",back_iface="",ceph_daemon="osd.1",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 | + | ceph_osd_metadata{job="ceph",back_iface="",ceph_daemon="osd.2",cluster_addr="192.168.1.12",device_class="hdd",front_iface="",hostname="127.0.0.1",objectstore="bluestore",public_addr="192.168.1.12",ceph_version="ceph version 17.0.0-8967-g6932a4f702a (6932a4f702a0d557fc36df3ca7a3bca70de42667) quincy (dev)"} | 1.0 | + When variable `ceph_hosts` is `127.0.0.1` + Then Grafana panel `OSDs` with legend `EMPTY` shows: + | metrics | values | + | {} | 3 | + +# IOPS Panel - begin + +Scenario: "Test Disk IOPS - Writes - Several OSDs per device" + Given the following series: + | metrics | values | + | node_disk_writes_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_writes_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows: + | metrics | values | + | {job="ceph",ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 | + | {job="ceph",ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 | + +Scenario: "Test Disk IOPS - Writes - Single OSD per device" + Given the following series: + | metrics | values | + | node_disk_writes_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_writes_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) writes` shows: + | metrics | values | + | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 | + | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 | + +Scenario: "Test Disk IOPS - Reads - Several OSDs per device" + Given the following series: + | metrics | values | + | node_disk_reads_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_reads_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0 osd.1 osd.2",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.3 osd.4 osd.5",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows: + | metrics | values | + | {job="ceph",ceph_daemon="osd.0 osd.1 osd.2", device="sda", instance="localhost"} | 1 | + | {job="ceph",ceph_daemon="osd.3 osd.4 osd.5", device="sdb", instance="localhost"} | 1 | + +Scenario: "Test Disk IOPS - Reads - Single OSD per device" + Given the following series: + | metrics | values | + | node_disk_reads_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_reads_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Disk IOPS` with legend `{{device}}({{ceph_daemon}}) reads` shows: + | metrics | values | + | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 | + | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 | + +# IOPS Panel - end + +# Node disk bytes written/read panel - begin + +Scenario: "Test disk throughput - read" + Given the following series: + | metrics | values | + | node_disk_read_bytes_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_read_bytes_total{job="ceph",device="sdb",instance="localhost:9100"} | 100+600x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) read` shows: + | metrics | values | + | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 | + | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 | + +Scenario: "Test disk throughput - write" + Given the following series: + | metrics | values | + | node_disk_written_bytes_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_written_bytes_total{job="ceph",device="sdb",instance="localhost:9100"} | 100+600x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Throughput by Disk` with legend `{{device}}({{ceph_daemon}}) write` shows: + | metrics | values | + | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 | + | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 10 | + +# Node disk bytes written/read panel - end + +Scenario: "Test $ceph_hosts Disk Latency panel" + Given the following series: + | metrics | values | + | node_disk_write_time_seconds_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_write_time_seconds_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | node_disk_writes_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_writes_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | node_disk_read_time_seconds_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_read_time_seconds_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | node_disk_reads_completed_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_reads_completed_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Disk Latency` with legend `{{device}}({{ceph_daemon}})` shows: + | metrics | values | + | {ceph_daemon="osd.0", device="sda", instance="localhost"} | 1 | + | {ceph_daemon="osd.1", device="sdb", instance="localhost"} | 1 | + +Scenario: "Test $ceph_hosts Disk utilization" + Given the following series: + | metrics | values | + | node_disk_io_time_seconds_total{job="ceph",device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_io_time_seconds_total{job="ceph",device="sdb",instance="localhost:9100"} | 10+60x1 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `ceph_hosts` is `localhost` + Then Grafana panel `$ceph_hosts Disk utilization` with legend `{{device}}({{ceph_daemon}})` shows: + | metrics | values | + | {job="ceph",ceph_daemon="osd.0", device="sda", instance="localhost"} | 100 | + | {job="ceph",ceph_daemon="osd.1", device="sdb", instance="localhost"} | 100 | + diff --git a/monitoring/ceph-mixin/tests_dashboards/features/hosts_overview.feature b/monitoring/ceph-mixin/tests_dashboards/features/hosts_overview.feature new file mode 100644 index 000000000..6c5eceaed --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/hosts_overview.feature @@ -0,0 +1,41 @@ +Feature: Hosts Overview Dashboard + +Scenario: "Test network load succeeds" + Given the following series: + | metrics | values | + | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + When variable `osd_hosts` is `127.0.0.1` + Then Grafana panel `Network Load` with legend `EMPTY` shows: + | metrics | values | + | {} | 6 | + +Scenario: "Test network load with bonding succeeds" + Given the following series: + | metrics | values | + | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 | + | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 | + | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 | + | node_network_transmit_bytes{instance="127.0.0.1", device="bond0"} | 20 200 300 | + | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 | + When variable `osd_hosts` is `127.0.0.1` + Then Grafana panel `Network Load` with legend `EMPTY` shows: + | metrics | values | + | {} | 6 | + +Scenario: "Test AVG Disk Utilization" + Given the following series: + | metrics | values | + | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10+60x1 | + | node_disk_io_time_seconds_total{device="sdb",instance="localhost:9100"} | 10+60x1 | + | node_disk_io_time_seconds_total{device="sdc",instance="localhost:9100"} | 10 2000 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd_hosts` is `localhost` + Then Grafana panel `AVG Disk Utilization` with legend `EMPTY` shows: + | metrics | values | + | {} | 100 | diff --git a/monitoring/ceph-mixin/tests_dashboards/features/osd-device-details.feature b/monitoring/ceph-mixin/tests_dashboards/features/osd-device-details.feature new file mode 100644 index 000000000..0d6ca8b17 --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/osd-device-details.feature @@ -0,0 +1,88 @@ +Feature: OSD device details + +Scenario: "Test Physical Device Latency for $osd - Reads" + Given the following series: + | metrics | values | + | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 60 | + | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 60 | + | node_disk_read_time_seconds_total{device="sda",instance="localhost"} | 100 600 | + | node_disk_read_time_seconds_total{device="sdb",instance="localhost"} | 100 600 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd` is `osd.0` + Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Reads` shows: + | metrics | values | + | {device="sda",instance="localhost"} | 10 | + +Scenario: "Test Physical Device Latency for $osd - Writes" + Given the following series: + | metrics | values | + | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 60 | + | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 60 | + | node_disk_write_time_seconds_total{device="sda",instance="localhost"} | 100 600 | + | node_disk_write_time_seconds_total{device="sdb",instance="localhost"} | 100 600 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd` is `osd.0` + Then Grafana panel `Physical Device Latency for $osd` with legend `{{instance}}/{{device}} Writes` shows: + | metrics | values | + | {device="sda",instance="localhost"} | 10 | + +Scenario: "Test Physical Device R/W IOPS for $osd - Writes" + Given the following series: + | metrics | values | + | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 | + | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd` is `osd.0` + Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows: + | metrics | values | + | {device="sda",instance="localhost"} | 1.5 | + +Scenario: "Test Physical Device R/W IOPS for $osd - Reads" + Given the following series: + | metrics | values | + | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 | + | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd` is `osd.0` + Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows: + | metrics | values | + | {device="sda",instance="localhost"} | 1.5 | + +Scenario: "Test Physical Device R/W Bytes for $osd - Reads" + Given the following series: + | metrics | values | + | node_disk_reads_completed_total{device="sda",instance="localhost"} | 10 100 | + | node_disk_reads_completed_total{device="sdb",instance="localhost"} | 10 100 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd` is `osd.0` + Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Reads` shows: + | metrics | values | + | {device="sda",instance="localhost"} | 1.5 | + +Scenario: "Test Physical Device R/W Bytes for $osd - Writes" + Given the following series: + | metrics | values | + | node_disk_writes_completed_total{device="sda",instance="localhost"} | 10 100 | + | node_disk_writes_completed_total{device="sdb",instance="localhost"} | 10 100 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd` is `osd.0` + Then Grafana panel `Physical Device R/W IOPS for $osd` with legend `{{device}} on {{instance}} Writes` shows: + | metrics | values | + | {device="sda",instance="localhost"} | 1.5 | + +Scenario: "Test Physical Device Util% for $osd" + Given the following series: + | metrics | values | + | node_disk_io_time_seconds_total{device="sda",instance="localhost:9100"} | 10 100 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.0",device="/dev/sda",instance="localhost:9283"} | 1.0 | + | ceph_disk_occupation_human{job="ceph",ceph_daemon="osd.1",device="/dev/sdb",instance="localhost:9283"} | 1.0 | + When variable `osd` is `osd.0` + Then Grafana panel `Physical Device Util% for $osd` with legend `{{device}} on {{instance}}` shows: + | metrics | values | + | {device="sda",instance="localhost"} | 1.5 | diff --git a/monitoring/ceph-mixin/tests_dashboards/features/osds-overview.feature b/monitoring/ceph-mixin/tests_dashboards/features/osds-overview.feature new file mode 100644 index 000000000..78d306419 --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/osds-overview.feature @@ -0,0 +1,15 @@ +Feature: OSD Overview + +Scenario: "Test OSD onode Hits Ratio" + Given the following series: + | metrics | values | + | ceph_bluestore_onode_hits{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 5255 | + | ceph_bluestore_onode_hits{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 5419 | + | ceph_bluestore_onode_hits{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 5242 | + | ceph_bluestore_onode_misses{ceph_daemon="osd.0",instance="ceph:9283",job="ceph"} | 202 | + | ceph_bluestore_onode_misses{ceph_daemon="osd.1",instance="ceph:9283",job="ceph"} | 247 | + | ceph_bluestore_onode_misses{ceph_daemon="osd.2",instance="ceph:9283",job="ceph"} | 234 | + Then Grafana panel `OSD onode Hits Ratio` with legend `EMPTY` shows: + | metrics | values | + | {} | 9.588529429483704E-01 | + diff --git a/monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature b/monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature new file mode 100644 index 000000000..e0016c507 --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/radosgw-detail.feature @@ -0,0 +1,139 @@ +Feature: RGW Host Detail Dashboard + +Scenario: "Test $rgw_servers GET/PUT Latencies - GET" + Given the following series: + | metrics | values | + | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 | + | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `GET {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance_id="58892247"} | 1.5 | + +Scenario: "Test $rgw_servers GET/PUT Latencies - PUT" + Given the following series: + | metrics | values | + | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 | + | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `$rgw_servers GET/PUT Latencies` with legend `PUT {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance_id="58892247"} | 1 | + +Scenario: "Test Bandwidth by HTTP Operation - GET" + Given the following series: + | metrics | values | + | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 | + | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.1` + Then Grafana panel `Bandwidth by HTTP Operation` with legend `GETs {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1.5 | + +Scenario: "Test Bandwidth by HTTP Operation - PUT" + Given the following series: + | metrics | values | + | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 | + | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.1` + Then Grafana panel `Bandwidth by HTTP Operation` with legend `PUTs {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.1", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 7.5E-01 | + +Scenario: "Test HTTP Request Breakdown - Requests Failed" + Given the following series: + | metrics | values | + | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `HTTP Request Breakdown` with legend `Requests Failed {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1E-01 | + +Scenario: "Test HTTP Request Breakdown - GET" + Given the following series: + | metrics | values | + | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `HTTP Request Breakdown` with legend `GETs {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.1666666666666667 | + +Scenario: "Test HTTP Request Breakdown - PUT" + Given the following series: + | metrics | values | + | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `HTTP Request Breakdown` with legend `PUTs {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.5 | + +Scenario: "Test HTTP Request Breakdown - Other" + Given the following series: + | metrics | values | + | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 | + | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 | + | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `HTTP Request Breakdown` with legend `Other {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 | + +Scenario: "Test Workload Breakdown - Failures" + Given the following series: + | metrics | values | + | ceph_rgw_failed_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 5 7 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `Workload Breakdown` with legend `Failures {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1E-01 | + +Scenario: "Test Workload Breakdown - GETs" + Given the following series: + | metrics | values | + | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `Workload Breakdown` with legend `GETs {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.1666666666666667 | + +Scenario: "Test Workload Breakdown - PUTs" + Given the following series: + | metrics | values | + | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `Workload Breakdown` with legend `PUTs {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1.5 | + +Scenario: "Test Workload Breakdown - Other" + Given the following series: + | metrics | values | + | ceph_rgw_req{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 175 250 345 | + | ceph_rgw_get{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 100 150 170 | + | ceph_rgw_put{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 70 90 160 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + And variable `rgw_servers` is `rgw.foo` + Then Grafana panel `Workload Breakdown` with legend `Other (DELETE,LIST) {{ceph_daemon}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph"} | .16666666666666652 | diff --git a/monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature b/monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature new file mode 100644 index 000000000..642e43978 --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/radosgw_overview.feature @@ -0,0 +1,250 @@ +Feature: RGW Overview Dashboard + +Scenario: "Test Average GET Latencies" + Given the following series: + | metrics | values | + | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 | + | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + Then Grafana panel `Average GET/PUT Latencies by RGW Instance` with legend `GET {{rgw_host}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1.5 | + +Scenario: "Test Average PUT Latencies" + Given the following series: + | metrics | values | + | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 | + | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + Then Grafana panel `Average GET/PUT Latencies by RGW Instance` with legend `PUT {{rgw_host}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 | + +Scenario: "Test Total Requests/sec by RGW Instance" + Given the following series: + | metrics | values | + | ceph_rgw_req{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 | + | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 | + When interval is `30s` + Then Grafana panel `Total Requests/sec by RGW Instance` with legend `{{rgw_host}}` shows: + | metrics | values | + | {rgw_host="1"} | 1.5 | + +Scenario: "Test GET Latencies by RGW Instance" + Given the following series: + | metrics | values | + | ceph_rgw_get_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 50 100 | + | ceph_rgw_get_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 20 60 80 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When interval is `30s` + Then Grafana panel `GET Latencies by RGW Instance` with legend `{{rgw_host}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1.5 | + +Scenario: "Test Bandwidth Consumed by Type- GET" + Given the following series: + | metrics | values | + | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 | + When evaluation time is `1m` + And interval is `30s` + Then Grafana panel `Bandwidth Consumed by Type` with legend `GETs` shows: + | metrics | values | + | {} | 1.5 | + +Scenario: "Test Bandwidth Consumed by Type- PUT" + Given the following series: + | metrics | values | + | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 | + When evaluation time is `1m` + And interval is `30s` + Then Grafana panel `Bandwidth Consumed by Type` with legend `PUTs` shows: + | metrics | values | + | {} | 7.5E-01 | + +Scenario: "Test Bandwidth by RGW Instance" + Given the following series: + | metrics | values | + | ceph_rgw_get_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 10 50 100 | + | ceph_rgw_put_b{instance="127.0.0.1", instance_id="92806566", job="ceph"} | 5 20 50 | + | ceph_rgw_metadata{ceph_daemon="rgw.1", hostname="localhost", instance="127.0.0.1", instance_id="92806566", job="ceph"} | 1 1 1 | + When evaluation time is `1m` + And interval is `30s` + Then Grafana panel `Bandwidth by RGW Instance` with legend `{{rgw_host}}` shows: + | metrics | values | + | {ceph_daemon="rgw.1", instance_id="92806566", rgw_host="1"} | 2.25 | + +Scenario: "Test PUT Latencies by RGW Instance" + Given the following series: + | metrics | values | + | ceph_rgw_put_initial_lat_sum{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 15 35 55 | + | ceph_rgw_put_initial_lat_count{instance="127.0.0.1", instance_id="58892247", job="ceph"} | 10 30 50 | + | ceph_rgw_metadata{ceph_daemon="rgw.foo", hostname="localhost", instance="127.0.0.1", instance_id="58892247", job="ceph"} | 1 1 1 | + When evaluation time is `1m` + And interval is `30s` + Then Grafana panel `PUT Latencies by RGW Instance` with legend `{{rgw_host}}` shows: + | metrics | values | + | {ceph_daemon="rgw.foo", instance="127.0.0.1", instance_id="58892247", job="ceph", rgw_host="foo"} | 1 | + +Scenario: "Test Total backend responses by HTTP code" + Given the following series: + | metrics | values | + | haproxy_backend_http_responses_total{job="haproxy",code="200",instance="ingress.rgw.1",proxy="backend"} | 10 100 | + | haproxy_backend_http_responses_total{job="haproxy",code="404",instance="ingress.rgw.1",proxy="backend"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + When variable `code` is `200` + Then Grafana panel `Total responses by HTTP code` with legend `Backend {{ code }}` shows: + | metrics | values | + | {code="200"} | 1.5 | + +Scenario: "Test Total frontend responses by HTTP code" + Given the following series: + | metrics | values | + | haproxy_frontend_http_responses_total{job="haproxy",code="200",instance="ingress.rgw.1",proxy="frontend"} | 10 100 | + | haproxy_frontend_http_responses_total{job="haproxy",code="404",instance="ingress.rgw.1",proxy="frontend"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + When variable `code` is `200` + Then Grafana panel `Total responses by HTTP code` with legend `Frontend {{ code }}` shows: + | metrics | values | + | {code="200"} | 1.5 | + +Scenario: "Test Total http frontend requests by instance" + Given the following series: + | metrics | values | + | haproxy_frontend_http_requests_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_frontend_http_requests_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total requests / responses` with legend `Requests` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total backend response errors by instance" + Given the following series: + | metrics | values | + | haproxy_backend_response_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_response_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total requests / responses` with legend `Response errors` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total frontend requests errors by instance" + Given the following series: + | metrics | values | + | haproxy_frontend_request_errors_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_frontend_request_errors_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total requests / responses` with legend `Requests errors` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total backend redispatch warnings by instance" + Given the following series: + | metrics | values | + | haproxy_backend_redispatch_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_redispatch_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total requests / responses` with legend `Backend redispatch` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total backend retry warnings by instance" + Given the following series: + | metrics | values | + | haproxy_backend_retry_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_retry_warnings_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total requests / responses` with legend `Backend retry` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total frontend requests denied by instance" + Given the following series: + | metrics | values | + | haproxy_frontend_requests_denied_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_frontend_requests_denied_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total requests / responses` with legend `Request denied` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total backend current queue by instance" + Given the following series: + | metrics | values | + | haproxy_backend_current_queue{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_current_queue{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total requests / responses` with legend `Backend Queued` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 200 | + +Scenario: "Test Total frontend connections by instance" + Given the following series: + | metrics | values | + | haproxy_frontend_connections_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_frontend_connections_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total number of connections` with legend `Front` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total backend connections attempts by instance" + Given the following series: + | metrics | values | + | haproxy_backend_connection_attempts_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_connection_attempts_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total number of connections` with legend `Back` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total backend connections error by instance" + Given the following series: + | metrics | values | + | haproxy_backend_connection_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_connection_errors_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Total number of connections` with legend `Back errors` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 3 | + +Scenario: "Test Total frontend bytes incoming by instance" + Given the following series: + | metrics | values | + | haproxy_frontend_bytes_in_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_frontend_bytes_in_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Front` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 24 | + +Scenario: "Test Total frontend bytes outgoing by instance" + Given the following series: + | metrics | values | + | haproxy_frontend_bytes_out_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_frontend_bytes_out_total{job="haproxy",proxy="frontend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Front` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 24 | + +Scenario: "Test Total backend bytes incoming by instance" + Given the following series: + | metrics | values | + | haproxy_backend_bytes_in_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_bytes_in_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Current total of incoming / outgoing bytes` with legend `IN Back` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 24 | + +Scenario: "Test Total backend bytes outgoing by instance" + Given the following series: + | metrics | values | + | haproxy_backend_bytes_out_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 10 100 | + | haproxy_backend_bytes_out_total{job="haproxy",proxy="backend",instance="ingress.rgw.1"} | 20 200 | + When variable `ingress_service` is `ingress.rgw.1` + Then Grafana panel `Current total of incoming / outgoing bytes` with legend `OUT Back` shows: + | metrics | values | + | {instance="ingress.rgw.1"} | 24 | diff --git a/monitoring/ceph-mixin/tests_dashboards/features/self.feature b/monitoring/ceph-mixin/tests_dashboards/features/self.feature new file mode 100644 index 000000000..2b44ce0dc --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/self.feature @@ -0,0 +1,68 @@ +Feature: Test tester + +Scenario: "Simple query works" + Given the following series: + | metrics | values | + | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 | + | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 | + | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 | + Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces: + | metrics | values | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 100 | + +Scenario: "Query with evaluation time" + Given the following series: + | metrics | values | + | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 | + | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 | + | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 | + When evaluation time is `0m` + Then query `node_network_transmit_bytes{instance="127.0.0.1"} > 0` produces: + | metrics | values | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 | + +Scenario: "Query with evaluation time and variable value" + Given the following series: + | metrics | values | + | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 | + | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 | + | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 | + | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 | + When evaluation time is `0m` + And variable `osd_hosts` is `127.0.0.1` + Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces: + | metrics | values | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 | + +Scenario: "Query with interval time" + Given the following series: + | metrics | values | + | node_network_receive_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 | + | node_network_receive_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 10 100 200 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 10 100 200 | + | node_network_transmit_bytes{instance="192.168.100.2", device="bond0"} | 20 200 300 | + | node_network_transmit_bytes{instance="192.168.100.1", device="bond0"} | 20 200 300 | + | bonding_slaves{instance="127.0.0.1", master="bond0"} | 2 | + When evaluation time is `2h` + And evaluation interval is `1h` + And interval is `1h` + And variable `osd_hosts` is `127.0.0.1` + Then query `node_network_transmit_bytes{instance="$osd_hosts"} > 0` produces: + | metrics | values | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth1"} | 200 | + | node_network_transmit_bytes{instance="127.0.0.1", device="eth2"} | 200 |
\ No newline at end of file diff --git a/monitoring/ceph-mixin/tests_dashboards/features/steps/__init__.py b/monitoring/ceph-mixin/tests_dashboards/features/steps/__init__.py new file mode 100644 index 000000000..0b90f46f2 --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/features/steps/__init__.py @@ -0,0 +1 @@ +# This file and steps files is needed even if its empty because of 'behave' :( diff --git a/monitoring/ceph-mixin/tests_dashboards/requirements.txt b/monitoring/ceph-mixin/tests_dashboards/requirements.txt new file mode 100644 index 000000000..8ad130e5b --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/requirements.txt @@ -0,0 +1,12 @@ +attrs==21.2.0 +behave==1.2.6 +py==1.10.0 +pyparsing==2.4.7 +PyYAML==6.0 +types-PyYAML==6.0.0 +typing-extensions==3.10.0.2 +termcolor==1.1.0 +types-termcolor==1.1.2 +dataclasses==0.6 +types-dataclasses==0.6.1 +prettytable==2.4.0 diff --git a/monitoring/ceph-mixin/tests_dashboards/util.py b/monitoring/ceph-mixin/tests_dashboards/util.py new file mode 100644 index 000000000..1fce6559d --- /dev/null +++ b/monitoring/ceph-mixin/tests_dashboards/util.py @@ -0,0 +1,109 @@ +import json +import re +from pathlib import Path +from typing import Any, Dict, Tuple, Union + +from termcolor import cprint + +UNITS = ['ms', 's', 'm', 'h', 'd', 'w', 'y'] + + +def resolve_time_and_unit(time: str) -> Union[Tuple[int, str], Tuple[None, None]]: + """ + Divide time with its unit and return a tuple like (10, 'm') + Return None if its and invalid prometheus time + Valid units are inside UNITS. + """ + if time[-1] in UNITS: + return int(time[:-1]), time[-1] + if time[-2:] in UNITS: + return int(time[:-2]), time[-2:] + return None, None + + +def get_dashboards_data() -> Dict[str, Any]: + data: Dict[str, Any] = {'queries': {}, 'variables': {}, 'stats': {}} + for file in Path(__file__).parent.parent \ + .joinpath('dashboards_out').glob('*.json'): + with open(file, 'r') as f: + dashboard_data = json.load(f) + data['stats'][str(file)] = {'total': 0, 'tested': 0} + add_dashboard_queries(data, dashboard_data, str(file)) + add_dashboard_variables(data, dashboard_data) + add_default_dashboards_variables(data) + return data + + +def add_dashboard_queries(data: Dict[str, Any], dashboard_data: Dict[str, Any], path: str) -> None: + """ + Grafana panels can have more than one target/query, in order to identify each + query in the panel we append the "legendFormat" of the target to the panel name. + format: panel_name-legendFormat + """ + if 'panels' not in dashboard_data: + return + error = 0 + for panel in dashboard_data['panels']: + if ( + 'title' in panel + and 'targets' in panel + and len(panel['targets']) > 0 + and 'expr' in panel['targets'][0] + ): + for target in panel['targets']: + title = panel['title'] + legend_format = target['legendFormat'] if 'legendFormat' in target else "" + query_id = f'{title}-{legend_format}' + if query_id in data['queries']: + # NOTE: If two or more panels have the same name and legend it + # might suggest a refactoring is needed or add something else + # to identify each query. + conflict_file = Path(data['queries'][query_id]['path']).name + file = Path(path).name + cprint((f'ERROR: Query in panel "{title}" with legend "{legend_format}"' + f' already exists. Conflict "{conflict_file}" ' + f'with: "{file}"'), 'red') + error = 1 + data['queries'][query_id] = {'query': target['expr'], 'path': path} + data['stats'][path]['total'] += 1 + if error: + raise ValueError('Missing legend_format in queries, please add a proper value.') + + +def add_dashboard_variables(data: Dict[str, Any], dashboard_data: Dict[str, Any]) -> None: + if 'templating' not in dashboard_data or 'list' not in dashboard_data['templating']: + return + for variable in dashboard_data['templating']['list']: + if 'name' in variable: + data['variables'][variable['name']] = 'UNSET VARIABLE' + +def add_default_dashboards_variables(data: Dict[str, Any]) -> None: + data['variables']['job'] = 'ceph' + data['variables']['job_haproxy'] = 'haproxy' + data['variables']['__rate_interval'] = '1m' + +def replace_grafana_expr_variables(expr: str, variable: str, value: Any) -> str: + """ Replace grafana variables in expression with a value + + It should match the whole word, 'osd' musn't match with the 'osd' prefix in 'osd_hosts' + >>> replace_grafana_expr_variables('metric{name~="$osd_hosts|$other|$osd"}', \ + 'osd', 'replacement') + 'metric{name~="$osd_hosts|$other|replacement"}' + + >>> replace_grafana_expr_variables('metric{name~="$osd_hosts|$other|$osd"}', \ + 'other', 'replacement') + 'metric{name~="$osd_hosts|replacement|$osd"}' + + It replaces words with dollar prefix + >>> replace_grafana_expr_variables('metric{name~="no_dollar|$other|$osd"}', \ + 'no_dollar', 'replacement') + 'metric{name~="no_dollar|$other|$osd"}' + + It shouldn't replace the next char after the variable (positive lookahead test). + >>> replace_grafana_expr_variables('metric{name~="$osd"}', \ + 'osd', 'replacement') + 'metric{name~="replacement"}' + """ + regex = fr'\${variable}(?=\W)' + new_expr = re.sub(regex, fr'{value}', expr) + return new_expr diff --git a/monitoring/ceph-mixin/tox.ini b/monitoring/ceph-mixin/tox.ini new file mode 100644 index 000000000..d0d97fc98 --- /dev/null +++ b/monitoring/ceph-mixin/tox.ini @@ -0,0 +1,75 @@ +[tox] +envlist = + lint, + jsonnet-{check,lint,fix}, + jsonnet-bundler-{install,update}, + promql-query-{test,lint}, + alerts-check +skipsdist = true + +[testenv:jsonnet-bundler-{install,update}] +allowlist_externals = + jb +description = + install: Install the jsonnet dependencies + update: Update the jsonnet dependencies +commands = + install: jb install + update: jb update + +[testenv:jsonnet-{check,fix,lint}] +basepython = python3 +allowlist_externals = + find + jb + jsonnet + jsonnetfm + sh +description = + check: Ensure that auto-generated files matches the current version + fix: Update generated files from jsonnet file with latest changes + lint: Test if jsonnet files are linted (without any update) +deps = + -rrequirements-grafonnet.txt +depends = jsonnet-bundler-install +commands = + check: sh test-jsonnet.sh + lint: ./lint-jsonnet.sh --test + fix: jsonnet -J vendor -m dashboards_out dashboards.jsonnet + +[testenv:lint] +description = + Run python linters +deps = + -rrequirements-lint.txt +setenv = +commands = + pylint --rcfile=.pylintrc tests_dashboards + mypy tests_dashboards + isort tests_dashboards + +[testenv:promql-query-test] +description = + lint: Run promtool check on grafana queries + test: Run promtool unit testing on grafana queries. +deps = + -rrequirements-lint.txt +depends = grafonnet-check +setenv = +allowlist_externals = + promtool +commands = + behave tests_dashboards/features + +[testenv:alerts-{fix,check,lint}] +deps = + -rrequirements-alerts.txt + pytest +depends = grafonnet-check +allowlist_externals = + promtool +commands = + fix: jsonnet -J vendor -S alerts.jsonnet -o prometheus_alerts.yml + lint: promtool check rules prometheus_alerts.yml + test: pytest -rA tests_alerts/test_syntax.py tests_alerts/test_unittests.py + python3 ./tests_alerts/validate_rules.py diff --git a/monitoring/grafana/build/Makefile b/monitoring/grafana/build/Makefile new file mode 100755 index 000000000..64f619990 --- /dev/null +++ b/monitoring/grafana/build/Makefile @@ -0,0 +1,84 @@ + +GRAFANA_VERSION ?= 8.3.5-1 +PIECHART_VERSION ?= "1.6.2" +STATUS_PANEL_VERSION ?= "1.0.11" +DASHBOARD_DIR := "../../ceph-mixin/dashboards_out" +DASHBOARD_PROVISIONING := "ceph-dashboard.yml" +IMAGE := "docker.io/redhat/ubi8:8.5" +PKGMGR := "dnf" +GF_CONFIG := "/etc/grafana/grafana.ini" +# clip off "-<whatever> from the end of GRAFANA_VERSION +CONTAINER_VERSION := $(shell /bin/echo $(GRAFANA_VERSION) | /bin/sed 's/-.*//') + +ARCH ?= x86_64 +ifeq "$(ARCH)" "arm64" + override ARCH := aarch64 +endif + +LOCALTAG=ceph-grafana:$(CONTAINER_VERSION)-$(ARCH) +TAG=ceph/ceph-grafana:$(CONTAINER_VERSION)-$(ARCH) + +# Build a grafana instance - preconfigured for use within Ceph's dashboard UI + +build : + echo "Creating base container" + $(eval CONTAINER := $(shell sudo buildah from ${IMAGE})) + # Using upstream grafana build + curl -fLO https://dl.grafana.com/oss/release/grafana-${GRAFANA_VERSION}.${ARCH}.rpm + sudo buildah copy $(CONTAINER) grafana-${GRAFANA_VERSION}.${ARCH}.rpm /tmp/grafana-${GRAFANA_VERSION}.${ARCH}.rpm + sudo buildah run $(CONTAINER) ${PKGMGR} install -y --setopt install_weak_deps=false --setopt=tsflags=nodocs /tmp/grafana-${GRAFANA_VERSION}.${ARCH}.rpm + sudo buildah run $(CONTAINER) ${PKGMGR} clean all + sudo buildah run $(CONTAINER) rm -f /tmp/grafana*.rpm + sudo buildah run $(CONTAINER) grafana-cli plugins install grafana-piechart-panel ${PIECHART_VERSION} + sudo buildah run $(CONTAINER) grafana-cli plugins install vonage-status-panel ${STATUS_PANEL_VERSION} + sudo buildah run $(CONTAINER) mkdir -p /etc/grafana/dashboards/ceph-dashboard + sudo buildah copy $(CONTAINER) ${DASHBOARD_DIR}/*.json /etc/grafana/dashboards/ceph-dashboard + + @/bin/echo -e "\ +apiVersion: 1 \\n\ +providers: \\n\ +- name: 'Ceph Dashboard' \\n\ + torgId: 1 \\n\ + folder: 'ceph-dashboard' \\n\ + type: file \\n\ + disableDeletion: false \\n\ + updateIntervalSeconds: 3 \\n\ + editable: false \\n\ + options: \\n\ + path: '/etc/grafana/dashboards/ceph-dashboard'" >> ${DASHBOARD_PROVISIONING} + + + sudo buildah copy $(CONTAINER) ${DASHBOARD_PROVISIONING} /etc/grafana/provisioning/dashboards/${DASHBOARD_PROVISIONING} + + # expose tcp/3000 for grafana + sudo buildah config --port 3000 $(CONTAINER) + + # set working dir + sudo buildah config --workingdir /usr/share/grafana $(CONTAINER) + + # set environment overrides from the default locations in /usr/share + sudo buildah config --env GF_PATHS_LOGS="/var/log/grafana" $(CONTAINER) + sudo buildah config --env GF_PATHS_PLUGINS="/var/lib/grafana/plugins" $(CONTAINER) + sudo buildah config --env GF_PATHS_PROVISIONING="/etc/grafana/provisioning" $(CONTAINER) + sudo buildah config --env GF_PATHS_DATA="/var/lib/grafana" $(CONTAINER) + + # entrypoint + sudo buildah config --entrypoint "grafana-server --config=${GF_CONFIG}" $(CONTAINER) + + # finalize + sudo buildah config --label maintainer="Paul Cuzner <pcuzner@redhat.com>" $(CONTAINER) + sudo buildah config --label description="Ceph Grafana Container" $(CONTAINER) + sudo buildah config --label summary="Grafana Container configured for Ceph mgr/dashboard integration" $(CONTAINER) + sudo buildah commit --format docker --squash $(CONTAINER) $(LOCALTAG) + +push: + sudo podman tag ${LOCALTAG} quay.io/${TAG} + # sudo podman has issues with auth.json; just override it + sudo podman login --authfile=auth.json -u $(CONTAINER_REPO_USERNAME) -p $(CONTAINER_REPO_PASSWORD) quay.io + sudo podman push --authfile=auth.json --format v2s2 quay.io/${TAG} + +clean: + sudo podman rmi ${LOCALTAG} || true + sudo podman rmi quay.io/${TAG} || true + rm -f grafana-*.rpm* auth.json + rm -f ${DASHBOARD_PROVISIONING} diff --git a/monitoring/grafana/build/README.md b/monitoring/grafana/build/README.md new file mode 100644 index 000000000..f77a40abc --- /dev/null +++ b/monitoring/grafana/build/README.md @@ -0,0 +1,37 @@ +# Building the ceph-grafana container image +From Nautilus onwards, grafana is embedded into the mgr/dashboard UI and uses two discrete grafana plugins to provide visualisations within the UI. To better support disconnected installs, and provide a more tested configuration you may use the Makefile, in this directory, to (re)generate the grafana containers based on each Ceph release. + +The versions of grafana, and the plugins are defined in the script so testing can be done against a known configuration. + +## Container +The current implementation uses buildah with a CentOS8 base image. + +## Dependencies +Ensure you have the following dependencies installed on your system, before attempting to build the image(s) +- podman or docker +- buildah +- jq +- make + +## Build Process +The Makefile supports the following invocations; +``` +# make <-- create container with dashboards from master +# make all +# make ceph_version=octopus +# make ceph_version=nautilus +``` + +Once complete, a ```make all``` execution will provide the following containers on your system. +``` +# podman images +REPOSITORY TAG IMAGE ID CREATED SIZE +localhost/ceph/ceph-grafana master 606fa5444fc6 14 minutes ago 497 MB +localhost/ceph-grafana master 606fa5444fc6 14 minutes ago 497 MB +localhost/ceph-grafana octopus 580b089c14e7 15 minutes ago 497 MB +localhost/ceph/ceph-grafana octopus 580b089c14e7 15 minutes ago 497 MB +localhost/ceph-grafana nautilus 3c91712dd26f 17 minutes ago 497 MB +localhost/ceph/ceph-grafana nautilus 3c91712dd26f 17 minutes ago 497 MB +registry.centos.org/centos 8 29d8fb6c94af 30 hours ago 223 MB + +``` diff --git a/monitoring/grafana/screenshots/ceph-cluster1.png b/monitoring/grafana/screenshots/ceph-cluster1.png Binary files differnew file mode 100644 index 000000000..4c59bd273 --- /dev/null +++ b/monitoring/grafana/screenshots/ceph-cluster1.png diff --git a/monitoring/grafana/screenshots/ceph-cluster2.png b/monitoring/grafana/screenshots/ceph-cluster2.png Binary files differnew file mode 100644 index 000000000..18a64d2dd --- /dev/null +++ b/monitoring/grafana/screenshots/ceph-cluster2.png diff --git a/monitoring/grafana/screenshots/host-details.png b/monitoring/grafana/screenshots/host-details.png Binary files differnew file mode 100644 index 000000000..bf963a9c7 --- /dev/null +++ b/monitoring/grafana/screenshots/host-details.png diff --git a/monitoring/grafana/screenshots/host-details.resized.png b/monitoring/grafana/screenshots/host-details.resized.png Binary files differnew file mode 100644 index 000000000..f18ea23a5 --- /dev/null +++ b/monitoring/grafana/screenshots/host-details.resized.png diff --git a/monitoring/grafana/screenshots/host_overview.png b/monitoring/grafana/screenshots/host_overview.png Binary files differnew file mode 100644 index 000000000..e47afa471 --- /dev/null +++ b/monitoring/grafana/screenshots/host_overview.png diff --git a/monitoring/grafana/screenshots/mds-performance.png b/monitoring/grafana/screenshots/mds-performance.png Binary files differnew file mode 100644 index 000000000..317cd8b19 --- /dev/null +++ b/monitoring/grafana/screenshots/mds-performance.png diff --git a/monitoring/grafana/screenshots/osd-performance.png b/monitoring/grafana/screenshots/osd-performance.png Binary files differnew file mode 100644 index 000000000..9bb7af44e --- /dev/null +++ b/monitoring/grafana/screenshots/osd-performance.png diff --git a/monitoring/grafana/screenshots/osd_overview.png b/monitoring/grafana/screenshots/osd_overview.png Binary files differnew file mode 100644 index 000000000..9e0c1fe68 --- /dev/null +++ b/monitoring/grafana/screenshots/osd_overview.png diff --git a/monitoring/grafana/screenshots/pool-details.png b/monitoring/grafana/screenshots/pool-details.png Binary files differnew file mode 100644 index 000000000..1f300cdab --- /dev/null +++ b/monitoring/grafana/screenshots/pool-details.png diff --git a/monitoring/grafana/screenshots/pool-overview.png b/monitoring/grafana/screenshots/pool-overview.png Binary files differnew file mode 100644 index 000000000..ffdd28ea6 --- /dev/null +++ b/monitoring/grafana/screenshots/pool-overview.png diff --git a/monitoring/grafana/screenshots/rgw-detail.png b/monitoring/grafana/screenshots/rgw-detail.png Binary files differnew file mode 100644 index 000000000..64356ad31 --- /dev/null +++ b/monitoring/grafana/screenshots/rgw-detail.png diff --git a/monitoring/grafana/screenshots/rgw-overview.png b/monitoring/grafana/screenshots/rgw-overview.png Binary files differnew file mode 100644 index 000000000..d6efaf797 --- /dev/null +++ b/monitoring/grafana/screenshots/rgw-overview.png diff --git a/monitoring/snmp/CEPH-MIB.txt b/monitoring/snmp/CEPH-MIB.txt new file mode 100644 index 000000000..f54cb3610 --- /dev/null +++ b/monitoring/snmp/CEPH-MIB.txt @@ -0,0 +1,337 @@ +CEPH-MIB DEFINITIONS ::= BEGIN + +IMPORTS + MODULE-IDENTITY, NOTIFICATION-TYPE, enterprises + FROM SNMPv2-SMI + MODULE-COMPLIANCE, NOTIFICATION-GROUP + FROM SNMPv2-CONF +; + +-- Linting information: +-- +-- # smilint -l 6 -i notification-not-reversible ./CEPH-MIB.txt +-- +-- ignore: notification-not-reversible since our SNMP gateway doesn't use SNMPv1 +-- + +ceph MODULE-IDENTITY + LAST-UPDATED + "202111010000Z" -- Nov 01, 2021 + ORGANIZATION + "The Ceph Project + https://ceph.io" + CONTACT-INFO + "Email: <dev@ceph.io> + + Send comments to: <dev@ceph.io>" + DESCRIPTION + "The MIB module for Ceph. In it's current form it only + supports Notifications, since Ceph itself doesn't provide + any SNMP agent functionality. + + Notifications are provided through a Prometheus/Alertmanager + webhook passing alerts to an external gateway service that is + responsible for formatting, forwarding and authenticating to + the SNMP receiver. + " + REVISION + "202111010000Z" --Nov 01, 2021 + DESCRIPTION + "Latest version including the following updates; + + - MIB restructure to align with linting + - names shortened and simplified (less verbose) + - Simplified structure due to switch to https://github.com/maxwo/snmp_notifier + - objects removed + - notifications updated + - Added module compliance + - Updated to latest prometheus alert rule definitions + " + ::= { enterprises 50495 } + +cephCluster OBJECT IDENTIFIER ::= { ceph 1 } +cephConformance OBJECT IDENTIFIER ::= { ceph 2 } + +-- cephMetadata is a placeholder for possible future expansion via an agent +-- where we could provide an overview of the clusters configuration +cephMetadata OBJECT IDENTIFIER ::= { cephCluster 1 } +cephNotifications OBJECT IDENTIFIER ::= { cephCluster 2 } + +prometheus OBJECT IDENTIFIER ::= { cephNotifications 1 } + +-- +-- Notifications: first we define the notification 'branches' for the +-- different categories of notifications / alerts +promGeneric OBJECT IDENTIFIER ::= { prometheus 1 } +promHealthStatus OBJECT IDENTIFIER ::= { prometheus 2 } +promMon OBJECT IDENTIFIER ::= { prometheus 3 } +promOsd OBJECT IDENTIFIER ::= { prometheus 4 } +promMds OBJECT IDENTIFIER ::= { prometheus 5 } +promMgr OBJECT IDENTIFIER ::= { prometheus 6 } +promPGs OBJECT IDENTIFIER ::= { prometheus 7 } +promNode OBJECT IDENTIFIER ::= { prometheus 8 } +promPool OBJECT IDENTIFIER ::= { prometheus 9 } +promRados OBJECT IDENTIFIER ::= { prometheus 10 } +promCephadm OBJECT IDENTIFIER ::= { prometheus 11 } +promPrometheus OBJECT IDENTIFIER ::= { prometheus 12 } + +promGenericNotification NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Generic alert issued when the Prometheus rule doesn't provide an OID." +::= { promGeneric 1 } + +promGenericDaemonCrash NOTIFICATION-TYPE + STATUS current + DESCRIPTION "One or more daemons have crashed recently, and are yet to be archived" +::= { promGeneric 2 } + +promHealthStatusError NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Ceph in health_error state for too long." +::= { promHealthStatus 1 } + +promHealthStatusWarning NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Ceph in health_warn for too long." +::= { promHealthStatus 2 } + +promMonLowQuorum NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Monitor count in quorum is low." +::= { promMon 1 } + +promMonDiskSpaceCritical NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Monitor diskspace is critically low." +::= { promMon 2 } + +promOsdDownHigh NOTIFICATION-TYPE + STATUS current + DESCRIPTION "A high number of OSDs are down." +::= { promOsd 1 } + +promOsdDown NOTIFICATION-TYPE + STATUS current + DESCRIPTION "One or more Osds down." +::= { promOsd 2 } + +promOsdNearFull NOTIFICATION-TYPE + STATUS current + DESCRIPTION "An OSD is dangerously full." +::= { promOsd 3 } + +promOsdFlapping NOTIFICATION-TYPE + STATUS current + DESCRIPTION "An OSD was marked down at back up at least once a minute for 5 minutes." +::= { promOsd 4 } + +promOsdHighPgDeviation NOTIFICATION-TYPE + STATUS current + DESCRIPTION "An OSD deviates by more then 30% from average PG count." +::= { promOsd 5 } + +promOsdFull NOTIFICATION-TYPE + STATUS current + DESCRIPTION "An OSD has reached its full threshold." +::= { promOsd 6 } + +promOsdHighPredictedFailures NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Normal self healing unable to cope with the number of devices predicted to fail." +::= { promOsd 7 } + +promOsdHostDown NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Ceph OSD host is down." +::= { promOsd 8 } + +promMdsDamaged NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Cephfs filesystem is damaged." +::= { promMds 1 } + +promMdsReadOnly NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Cephfs filesystem marked as READ-ONLY" +::= { promMds 2 } + +promMdsOffline NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Cephfs filesystem is unavailable/offline." +::= { promMds 3 } + +promMdsDegraded NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Cephfs filesystem is in a degraded state." +::= { promMds 4 } + +promMdsNoStandby NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Cephfs MDS daemon failure, no standby available" +::= { promMds 5 } + +promMgrModuleCrash NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Ceph mgr module has crashed recently" +::= { promMgr 1 } + +promMgrPrometheusInactive NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Ceph mgr prometheus module not responding" +::= { promMgr 2 } + +promPGsInactive NOTIFICATION-TYPE + STATUS current + DESCRIPTION "One or more PGs are inactive for more than 5 minutes." +::= { promPGs 1 } + +promPGsUnclean NOTIFICATION-TYPE + STATUS current + DESCRIPTION "One or more PGs are not clean for more than 15 minutes." +::= { promPGs 2 } + +promPGsUnavailable NOTIFICATION-TYPE + STATUS current + DESCRIPTION "One or more PGs is unavailable, blocking I/O to those objects." +::= { promPGs 3 } + +promPGsDamaged NOTIFICATION-TYPE + STATUS current + DESCRIPTION "One or more PGs is damaged." +::= { promPGs 4 } + +promPGsRecoveryFull NOTIFICATION-TYPE + STATUS current + DESCRIPTION "PG recovery is impaired due to full OSDs." +::= { promPGs 5 } + +promPGsBackfillFull NOTIFICATION-TYPE + STATUS current + DESCRIPTION "PG backfill is impaired due to full OSDs." +::= { promPGs 6 } + +promNodeRootVolumeFull NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Root volume (OSD and MON store) is dangerously full (< 5% free)." +::= { promNode 1 } + +promNodeNetworkPacketDrops NOTIFICATION-TYPE + STATUS current + DESCRIPTION "A node experiences packet drop > 1 packet/s on an interface." +::= { promNode 2 } + +promNodeNetworkPacketErrors NOTIFICATION-TYPE + STATUS current + DESCRIPTION "A node experiences packet errors > 1 packet/s on an interface." +::= { promNode 3 } + +promNodeStorageFilling NOTIFICATION-TYPE + STATUS current + DESCRIPTION "A mountpoint will be full in less then 5 days assuming the average fillup rate of the past 48 hours." +::= { promNode 4 } + +promPoolFull NOTIFICATION-TYPE + STATUS current + DESCRIPTION "A pool is at 90% capacity or over." +::= { promPool 1 } + +promPoolFilling NOTIFICATION-TYPE + STATUS current + DESCRIPTION "A pool will be full in less then 5 days assuming the average fillup rate of the past 48 hours." +::= { promPool 2 } + +promRadosUnfound NOTIFICATION-TYPE + STATUS current + DESCRIPTION "A RADOS object can not be found, even though all OSDs are online." +::= { promRados 1 } + +promCephadmDaemonDown NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Cephadm has determined that a daemon is down." +::= { promCephadm 1 } + +promCephadmUpgradeFailure NOTIFICATION-TYPE + STATUS current + DESCRIPTION "Cephadm attempted to upgrade the cluster and encountered a problem." +::= { promCephadm 2 } + +promPrometheusJobMissing NOTIFICATION-TYPE + STATUS current + DESCRIPTION "The prometheus scrape job is not defined." +::= { promPrometheus 1 } +-- ---------------------------------------------------------- -- +-- IEEE 802.1D MIB - Conformance Information +-- ---------------------------------------------------------- -- + +cephAlertGroups OBJECT IDENTIFIER ::= { cephConformance 1 } +cephCompliances OBJECT IDENTIFIER ::= { cephConformance 2 } + +-- ---------------------------------------------------------- -- +-- units of conformance +-- ---------------------------------------------------------- -- + +-- ---------------------------------------------------------- -- +-- The Trap Notification Group +-- ---------------------------------------------------------- -- + +cephNotificationGroup NOTIFICATION-GROUP + NOTIFICATIONS { + promGenericNotification, + promGenericDaemonCrash, + promHealthStatusError, + promHealthStatusWarning, + promMonLowQuorum, + promMonDiskSpaceCritical, + promOsdDownHigh, + promOsdDown, + promOsdNearFull, + promOsdFlapping, + promOsdHighPgDeviation, + promOsdFull, + promOsdHighPredictedFailures, + promOsdHostDown, + promMdsDamaged, + promMdsReadOnly, + promMdsOffline, + promMdsDegraded, + promMdsNoStandby, + promMgrModuleCrash, + promMgrPrometheusInactive, + promPGsInactive, + promPGsUnclean, + promPGsUnavailable, + promPGsDamaged, + promPGsRecoveryFull, + promPGsBackfillFull, + promNodeRootVolumeFull, + promNodeNetworkPacketDrops, + promNodeNetworkPacketErrors, + promNodeStorageFilling, + promPoolFull, + promPoolFilling, + promRadosUnfound, + promCephadmDaemonDown, + promCephadmUpgradeFailure, + promPrometheusJobMissing + } + STATUS current + DESCRIPTION + "A collection of notifications triggered by the Prometheus + rules to convey Ceph cluster state" + ::= { cephAlertGroups 2 } + +-- ---------------------------------------------------------- -- +-- compliance statements +-- ---------------------------------------------------------- -- + +cephCompliance MODULE-COMPLIANCE + STATUS current + DESCRIPTION + "The Compliance statement for the Ceph MIB" + MODULE + MANDATORY-GROUPS { + cephNotificationGroup + } + ::= { cephCompliances 1 } + +END diff --git a/monitoring/snmp/README.md b/monitoring/snmp/README.md new file mode 100644 index 000000000..1a5b60955 --- /dev/null +++ b/monitoring/snmp/README.md @@ -0,0 +1,54 @@ +# SNMP schema +To show the [OID](https://en.wikipedia.org/wiki/Object_identifier)'s supported by the MIB, use the snmptranslate command. Here's an example: +``` +snmptranslate -Pu -Tz -M ~/git/ceph/monitoring/snmp:/usr/share/snmp/mibs -m CEPH-MIB +``` +*The `snmptranslate` command is in the net-snmp-utils package* + +The MIB provides a NOTIFICATION only implementation since ceph doesn't have an SNMP +agent feature. + +## Integration +The SNMP MIB is has been aligned to the Prometheus rules. Any rule that defines a +critical alert should have a corresponding oid in the CEPH-MIB.txt file. To generate +an SNMP notification, you must use an SNMP gateway that the Prometheus Alertmanager +service can forward alerts through to, via it's webhooks feature. + + + +## SNMP Gateway +The recommended SNMP gateway is https://github.com/maxwo/snmp_notifier. This is a widely +used and generic SNMP gateway implementation written in go. It's usage (syntax and +parameters) is very similar to Prometheus, AlertManager and even node-exporter. + + +## SNMP OIDs +The main components of the Ceph MIB is can be broken down into discrete areas + + +``` +internet private enterprise ceph ceph Notifications Prometheus Notification + org cluster (alerts) source Category +1.3.6.1 .4 .1 .50495 .1 .2 .1 .2 (Ceph Health) + .3 (MON) + .4 (OSD) + .5 (MDS) + .6 (MGR) + .7 (PGs) + .8 (Nodes) + .9 (Pools) + .10 (Rados) + .11 (cephadm) + .12 (prometheus) + +``` +Individual alerts are placed within the appropriate alert category. For example, to add +a notification relating to a MGR issue, you would use the oid 1.3.6.1.4.1.50495.1.2.1.6.x + +The SNMP gateway also adds additional components to the SNMP notification ; + +| Suffix | Description | +|--------|-------------| +| .1 | The oid | +| .2 | Severity of the alert. When an alert is resolved, severity is 'info', and the description is set to Status:OK| +| .3 | Text of the alert(s) | |
