summaryrefslogtreecommitdiffstats
path: root/backends/prometheus
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2021-12-01 06:15:04 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2021-12-01 06:15:04 +0000
commite970e0b37b8bd7f246feb3f70c4136418225e434 (patch)
tree0b67c0ca45f56f2f9d9c5c2e725279ecdf52d2eb /backends/prometheus
parentAdding upstream version 1.31.0. (diff)
downloadnetdata-e970e0b37b8bd7f246feb3f70c4136418225e434.tar.xz
netdata-e970e0b37b8bd7f246feb3f70c4136418225e434.zip
Adding upstream version 1.32.0.upstream/1.32.0
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'backends/prometheus')
-rw-r--r--backends/prometheus/README.md72
1 files changed, 36 insertions, 36 deletions
diff --git a/backends/prometheus/README.md b/backends/prometheus/README.md
index 10275fa20..a0460d1d8 100644
--- a/backends/prometheus/README.md
+++ b/backends/prometheus/README.md
@@ -110,7 +110,7 @@ scrape_configs:
# You can use `prometheus_all_hosts` if you want Prometheus to set the `instance` to your hostname instead of IP
format: [prometheus]
#
- # sources: as-collected | raw | average | sum | volume
+ # source: as-collected | raw | average | sum | volume
# default is: average
#source: [as-collected]
#
@@ -125,46 +125,46 @@ scrape_configs:
#### Install nodes.yml
-The following is completely optional, it will enable Prometheus to generate alerts from some NetData sources. Tweak the
+The following is completely optional, it will enable Prometheus to generate alerts from some Netdata sources. Tweak the
values to your own needs. We will use the following `nodes.yml` file below. Save it at `/opt/prometheus/nodes.yml`, and
add a _- "nodes.yml"_ entry under the _rule_files:_ section in the example prometheus.yml file above.
```yaml
groups:
-- name: nodes
-
- rules:
- - alert: node_high_cpu_usage_70
- expr: avg(rate(netdata_cpu_cpu_percentage_average{dimension="idle"}[1m])) by (job) > 70
- for: 1m
- annotations:
- description: '{{ $labels.job }} on ''{{ $labels.job }}'' CPU usage is at {{ humanize $value }}%.'
- summary: CPU alert for container node '{{ $labels.job }}'
-
- - alert: node_high_memory_usage_70
- expr: 100 / sum(netdata_system_ram_MB_average) by (job)
- * sum(netdata_system_ram_MB_average{dimension=~"free|cached"}) by (job) < 30
- for: 1m
- annotations:
- description: '{{ $labels.job }} memory usage is {{ humanize $value}}%.'
- summary: Memory alert for container node '{{ $labels.job }}'
-
- - alert: node_low_root_filesystem_space_20
- expr: 100 / sum(netdata_disk_space_GB_average{family="/"}) by (job)
- * sum(netdata_disk_space_GB_average{family="/",dimension=~"avail|cached"}) by (job) < 20
- for: 1m
- annotations:
- description: '{{ $labels.job }} root filesystem space is {{ humanize $value}}%.'
- summary: Root filesystem alert for container node '{{ $labels.job }}'
-
- - alert: node_root_filesystem_fill_rate_6h
- expr: predict_linear(netdata_disk_space_GB_average{family="/",dimension=~"avail|cached"}[1h], 6 * 3600) < 0
- for: 1h
- labels:
- severity: critical
- annotations:
- description: Container node {{ $labels.job }} root filesystem is going to fill up in 6h.
- summary: Disk fill alert for Swarm node '{{ $labels.job }}'
+ - name: nodes
+
+ rules:
+ - alert: node_high_cpu_usage_70
+ expr: sum(sum_over_time(netdata_system_cpu_percentage_average{dimension=~"(user|system|softirq|irq|guest)"}[10m])) by (job) / sum(count_over_time(netdata_system_cpu_percentage_average{dimension="idle"}[10m])) by (job) > 70
+ for: 1m
+ annotations:
+ description: '{{ $labels.job }} on ''{{ $labels.job }}'' CPU usage is at {{ humanize $value }}%.'
+ summary: CPU alert for container node '{{ $labels.job }}'
+
+ - alert: node_high_memory_usage_70
+ expr: 100 / sum(netdata_system_ram_MB_average) by (job)
+ * sum(netdata_system_ram_MB_average{dimension=~"free|cached"}) by (job) < 30
+ for: 1m
+ annotations:
+ description: '{{ $labels.job }} memory usage is {{ humanize $value}}%.'
+ summary: Memory alert for container node '{{ $labels.job }}'
+
+ - alert: node_low_root_filesystem_space_20
+ expr: 100 / sum(netdata_disk_space_GB_average{family="/"}) by (job)
+ * sum(netdata_disk_space_GB_average{family="/",dimension=~"avail|cached"}) by (job) < 20
+ for: 1m
+ annotations:
+ description: '{{ $labels.job }} root filesystem space is {{ humanize $value}}%.'
+ summary: Root filesystem alert for container node '{{ $labels.job }}'
+
+ - alert: node_root_filesystem_fill_rate_6h
+ expr: predict_linear(netdata_disk_space_GB_average{family="/",dimension=~"avail|cached"}[1h], 6 * 3600) < 0
+ for: 1h
+ labels:
+ severity: critical
+ annotations:
+ description: Container node {{ $labels.job }} root filesystem is going to fill up in 6h.
+ summary: Disk fill alert for Swarm node '{{ $labels.job }}'
```
#### Install prometheus.service