diff options
author | Ilya Mashchenko <ilya@netdata.cloud> | 2021-07-02 14:25:15 +0300 |
---|---|---|
committer | GitHub <noreply@github.com> | 2021-07-02 14:25:15 +0300 |
commit | 8b78803a4edbb52764f5d2ade7c11c2d746545a1 (patch) | |
tree | 91262481b816e206e724bfd42ce1d2bd1f45a289 /backends/prometheus | |
parent | 1bc24efdcabbb33055d4f12148ecca790760166c (diff) |
[docs] fix prometheus node cpu alert rule (#11309)
Diffstat (limited to 'backends/prometheus')
-rw-r--r-- | backends/prometheus/README.md | 68 |
1 files changed, 34 insertions, 34 deletions
diff --git a/backends/prometheus/README.md b/backends/prometheus/README.md index 10275fa205..0346aa666a 100644 --- a/backends/prometheus/README.md +++ b/backends/prometheus/README.md @@ -131,40 +131,40 @@ add a _- "nodes.yml"_ entry under the _rule_files:_ section in the example prome ```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 |