summaryrefslogtreecommitdiffstats
path: root/health/health.d
diff options
context:
space:
mode:
Diffstat (limited to 'health/health.d')
-rw-r--r--health/health.d/dbengine.conf44
-rw-r--r--health/health.d/gearman.conf22
-rw-r--r--health/health.d/hdfs.conf75
-rw-r--r--health/health.d/mysql.conf34
-rw-r--r--health/health.d/vcsa.conf122
-rw-r--r--health/health.d/zookeeper.conf14
6 files changed, 289 insertions, 22 deletions
diff --git a/health/health.d/dbengine.conf b/health/health.d/dbengine.conf
index 956abf294..ce6427cd2 100644
--- a/health/health.d/dbengine.conf
+++ b/health/health.d/dbengine.conf
@@ -1,26 +1,26 @@
# you can disable an alarm notification by setting the 'to' line to: silent
- alarm: 10min_dbengine_global_fs_errors
- on: netdata.dbengine_global_errors
- os: linux freebsd macos
- hosts: *
- lookup: sum -10m unaligned of FS errors
- units: errors
- every: 10s
- crit: $this > 0
- delay: down 15m multiplier 1.5 max 1h
- info: number of File-System errors dbengine came across the last 10 minutes (too many open files, wrong permissions etc)
- to: sysadmin
+ alarm: 10min_dbengine_global_fs_errors
+ on: netdata.dbengine_global_errors
+ os: linux freebsd macos
+ hosts: *
+lookup: sum -10m unaligned of FS errors
+ units: errors
+ every: 10s
+ crit: $this > 0
+ delay: down 15m multiplier 1.5 max 1h
+ info: number of File-System errors dbengine came across the last 10 minutes (too many open files, wrong permissions etc)
+ to: sysadmin
- alarm: 10min_dbengine_global_io_errors
- on: netdata.dbengine_global_errors
- os: linux freebsd macos
- hosts: *
- lookup: sum -10m unaligned of I/O errors
- units: errors
- every: 10s
- crit: $this > 0
- delay: down 1h multiplier 1.5 max 3h
- info: number of IO errors dbengine came across the last 10 minutes (CRC errors, out of space, bad disk etc)
- to: sysadmin
+ alarm: 10min_dbengine_global_io_errors
+ on: netdata.dbengine_global_errors
+ os: linux freebsd macos
+ hosts: *
+lookup: sum -10m unaligned of I/O errors
+ units: errors
+ every: 10s
+ crit: $this > 0
+ delay: down 1h multiplier 1.5 max 3h
+ info: number of IO errors dbengine came across the last 10 minutes (CRC errors, out of space, bad disk etc)
+ to: sysadmin \ No newline at end of file
diff --git a/health/health.d/gearman.conf b/health/health.d/gearman.conf
new file mode 100644
index 000000000..e3863ae5e
--- /dev/null
+++ b/health/health.d/gearman.conf
@@ -0,0 +1,22 @@
+# make sure Gearman is running
+template: gearman_last_collected_secs
+ on: gearman.total_jobs
+ calc: $now - $last_collected_t
+ units: seconds ago
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: sysadmin
+
+template: gearman_workers_queued
+ on: gearman.single_job
+ lookup: average -10m unaligned match-names of Queued
+ units: workers
+ every: 10s
+ warn: $this > 30000
+ crit: $this > 100000
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of queued jobs
+ to: sysadmin \ No newline at end of file
diff --git a/health/health.d/hdfs.conf b/health/health.d/hdfs.conf
new file mode 100644
index 000000000..678faab4c
--- /dev/null
+++ b/health/health.d/hdfs.conf
@@ -0,0 +1,75 @@
+
+# make sure hdfs is running
+
+template: hdfs_last_collected_secs
+ on: hdfs.heap_memory
+ calc: $now - $last_collected_t
+ units: seconds ago
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: webmaster
+
+
+# Common
+
+template: hdfs_capacity_usage
+ on: hdfs.capacity
+ calc: ($used) * 100 / ($used + $remaining)
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (70) : (80))
+ crit: $this > (($status == $CRITICAL) ? (80) : (98))
+ delay: down 15m multiplier 1.5 max 1h
+ info: used capacity
+ to: sysadmin
+
+
+# NameNode
+
+template: hdfs_missing_blocks
+ on: hdfs.blocks
+ calc: $missing
+ units: missing blocks
+ every: 10s
+ warn: $this > 0
+ delay: down 15m multiplier 1.5 max 1h
+ info: missing blocks
+ to: sysadmin
+
+
+template: hdfs_stale_nodes
+ on: hdfs.data_nodes
+ calc: $stale
+ units: dead nodes
+ every: 10s
+ warn: $this > 0
+ delay: down 15m multiplier 1.5 max 1h
+ info: stale data nodes
+ to: sysadmin
+
+
+template: hdfs_dead_nodes
+ on: hdfs.data_nodes
+ calc: $dead
+ units: dead nodes
+ every: 10s
+ crit: $this > 0
+ delay: down 15m multiplier 1.5 max 1h
+ info: dead data nodes
+ to: sysadmin
+
+
+# DataNode
+
+template: hdfs_num_failed_volumes
+ on: hdfs.num_failed_volumes
+ calc: $fsds_num_failed_volumes
+ units: failed volumes
+ every: 10s
+ warn: $this > 0
+ delay: down 15m multiplier 1.5 max 1h
+ info: failed volumes
+ to: sysadmin
diff --git a/health/health.d/mysql.conf b/health/health.d/mysql.conf
index 39c401915..ce7b98a87 100644
--- a/health/health.d/mysql.conf
+++ b/health/health.d/mysql.conf
@@ -98,3 +98,37 @@ template: mysql_replication_lag
info: the number of seconds mysql replication is behind this master
to: dba
+
+# -----------------------------------------------------------------------------
+# galera cluster size
+
+template: mysql_galera_cluster_size_max_2m
+ on: mysql.galera_cluster_size
+ lookup: max -2m absolute
+ units: nodes
+ every: 10s
+ info: max cluster size 2 minute
+ to: dba
+
+template: mysql_galera_cluster_size
+ on: mysql.galera_cluster_size
+ calc: $nodes
+ units: nodes
+ every: 10s
+ warn: $this > $mysql_galera_cluster_size_max_2m
+ crit: $this < $mysql_galera_cluster_size_max_2m
+ delay: up 20s down 5m multiplier 1.5 max 1h
+ info: cluster size has changed
+ to: dba
+
+# galera node state
+
+template: mysql_galera_cluster_state
+ on: mysql.galera_cluster_state
+ calc: $state
+ every: 10s
+ warn: $this < 4
+ crit: $this < 2
+ delay: up 30s down 5m multiplier 1.5 max 1h
+ info: node state (0: undefined, 1: joining, 2: donor/desynced, 3: joined, 4: synced)
+ to: dba
diff --git a/health/health.d/vcsa.conf b/health/health.d/vcsa.conf
new file mode 100644
index 000000000..7bb98a9ba
--- /dev/null
+++ b/health/health.d/vcsa.conf
@@ -0,0 +1,122 @@
+
+# make sure vcsa is running and responding
+
+template: vcsa_last_collected_secs
+ on: vcsa.system_health
+ calc: $now - $last_collected_t
+ units: seconds ago
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: sysadmin
+
+# Overall system health:
+# - 0: all components are healthy.
+# - 1: one or more components might become overloaded soon.
+# - 2: one or more components in the appliance might be degraded.
+# - 3: one or more components might be in an unusable status and the appliance might become unresponsive soon.
+# - 4: no health data is available.
+
+template: vcsa_system_health
+ on: vcsa.system_health
+ lookup: max -10s unaligned of system
+ units: status
+ every: 10s
+ warn: ($this == 1) || ($this == 2)
+ crit: $this == 3
+ delay: down 1m multiplier 1.5 max 1h
+ info: overall system health status
+ to: sysadmin
+
+# Components health:
+# - 0: healthy.
+# - 1: healthy, but may have some problems.
+# - 2: degraded, and may have serious problems.
+# - 3: unavailable, or will stop functioning soon.
+# - 4: no health data is available.
+
+template: vcsa_swap_health
+ on: vcsa.components_health
+ lookup: max -10s unaligned of swap
+ units: status
+ every: 10s
+ warn: $this == 1
+ crit: ($this == 2) || ($this == 3)
+ delay: down 1m multiplier 1.5 max 1h
+ info: swap health status
+ to: sysadmin
+
+template: vcsa_storage_health
+ on: vcsa.components_health
+ lookup: max -10s unaligned of storage
+ units: status
+ every: 10s
+ warn: $this == 1
+ crit: ($this == 2) || ($this == 3)
+ delay: down 1m multiplier 1.5 max 1h
+ info: storage health status
+ to: sysadmin
+
+template: vcsa_mem_health
+ on: vcsa.components_health
+ lookup: max -10s unaligned of mem
+ units: status
+ every: 10s
+ warn: $this == 1
+ crit: ($this == 2) || ($this == 3)
+ delay: down 1m multiplier 1.5 max 1h
+ info: mem health status
+ to: sysadmin
+
+template: vcsa_load_health
+ on: vcsa.components_health
+ lookup: max -10s unaligned of load
+ units: status
+ every: 10s
+ warn: $this == 1
+ crit: ($this == 2) || ($this == 3)
+ delay: down 1m multiplier 1.5 max 1h
+ info: load health status
+ to: sysadmin
+
+template: vcsa_database_storage_health
+ on: vcsa.components_health
+ lookup: max -10s unaligned of database_storage
+ units: status
+ every: 10s
+ warn: $this == 1
+ crit: ($this == 2) || ($this == 3)
+ delay: down 1m multiplier 1.5 max 1h
+ info: database storage health status
+ to: sysadmin
+
+template: vcsa_applmgmt_health
+ on: vcsa.components_health
+ lookup: max -10s unaligned of applmgmt
+ units: status
+ every: 10s
+ warn: $this == 1
+ crit: ($this == 2) || ($this == 3)
+ delay: down 1m multiplier 1.5 max 1h
+ info: appl mgmt health status
+ to: sysadmin
+
+
+# Software updates health:
+# - 0: no updates available.
+# - 2: non-security updates are available.
+# - 3: security updates are available.
+# - 4: an error retrieving information on software updates.
+
+template: vcsa_software_updates_health
+ on: vcsa.software_updates_health
+ lookup: max -10s unaligned of software_packages
+ units: status
+ every: 10s
+ warn: $this == 4
+ crit: $this == 3
+ delay: down 1m multiplier 1.5 max 1h
+ info: software packages health status
+ to: sysadmin
diff --git a/health/health.d/zookeeper.conf b/health/health.d/zookeeper.conf
new file mode 100644
index 000000000..ffbe31baf
--- /dev/null
+++ b/health/health.d/zookeeper.conf
@@ -0,0 +1,14 @@
+
+# make sure zookeeper is running
+
+template: zookeeper_last_collected_secs
+ on: zookeeper.requests
+ calc: $now - $last_collected_t
+ units: seconds ago
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: webmaster
+
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-08 20:28:26 +0000