aurore/ansible
aurore/ansible
11
2
Fork 0
Code Issues 1 Pull requests 13 Releases Wiki Activity

Cleanup Prometheus alerts #45

Merged
jeltz merged 11 commits from prometheus_alerts into master 2021-04-01 19:24:26 +02:00
Conversation 0 Commits 11 Files changed 11 +150 -124
3 changed files with 150 additions and 124 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit e247aa3f70 - Show all commits

1
roles/prometheus/handlers/main.yml
View file

@ -8,3 +8,4 @@
service:
name: prometheus-snmp-exporter
state: restarted
...

267
roles/prometheus/templates/prometheus/alert.rules.yml.j2
View file

@ -1,138 +1,161 @@
# {{ ansible_managed }}
{# As this is also Jinja2 it will conflict without a raw block #}
{# Depending of Prometheus Node exporter version, rules can change depending of version #}
{% raw %}
---
{{ ansible_managed | comment }}
{% macro raw(string) -%}
{{ string }}
{%- endmacro %}
{% set instance = '[{{ raw("$label.instance") }}]' %}
groups:
- name: alert.rules
rules:
- name: alert.rules
rules:
# Alert for any instance that is unreachable for >3 minutes.
- alert: InstanceDown
expr: up == 0
for: 3m
labels:
severity: critical
annotations:
summary: "{{ $labels.instance }} est invisible depuis plus de 3 minutes !"
- alert: InstanceDown
expr: up == 0
for: 3m
labels:
severity: critical
annotations:
summary: >-
{{ instance }} Invisible depuis plus de 3 minutes
# Alert for out of memory
- alert: OutOfMemory
expr: (node_memory_MemFree_bytes + node_memory_Cached_bytes + node_memory_Buffers_bytes) / node_memory_MemTotal_bytes * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Mémoire libre de {{ $labels.instance }} à {{ humanize $value }}%."
- alert: OutOfMemory
expr: >-
(
node_memory_MemFree_bytes
+ node_memory_Cached_bytes
+ node_memory_Buffers_bytes
) / node_memory_MemTotal_bytes * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} {{ raw("$value | round") }}% de mémoire libre
# Alert for out of disk space
- alert: OutOfDiskSpace
expr: node_filesystem_free_bytes{fstype="ext4"} / node_filesystem_size_bytes{fstype="ext4"} * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Espace libre de {{ $labels.mountpoint }} sur {{ $labels.instance }} à {{ humanize $value }}%."
- alert: OutOfDiskSpace
expr: >-
node_filesystem_free_bytes / node_filesystem_size_bytes * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} Espace libre de {{ raw("$labels.mountpoint") }} sur
à {{ raw("$value | round") }}%
# Alert for out of inode space on disk
- alert: OutOfInodes
expr: node_filesystem_files_free{fstype="ext4"} / node_filesystem_files{fstype="ext4"} * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: "Presque plus d'inodes disponibles ({{ $value }}% restant) dans {{ $labels.mountpoint }} sur {{ $labels.instance }}."
- alert: OutOfInodes
expr: node_filesystem_files_free / node_filesystem_files * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} {{ raw("$value | round") }}% d'inodes restants
pour {{ raw("$labels.mountpoint") }}
# Alert for high CPU usage
- alert: CpuUsage
expr: (100 - avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 75
for: 10m
labels:
severity: warning
annotations:
summary: "CPU sur {{ $labels.instance }} à {{ humanize $value }}%."
- alert: CpuUsage
expr: >-
(
100 - avg by (instance) (
irate(node_cpu_seconds_total{mode="idle"}[5m])
) * 100
) > 75
for: 10m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} CPU à {{ raw("$value | round") }}%
# Check systemd unit (> buster)
- alert: SystemdServiceFailed
expr: node_systemd_unit_state{state="failed"} == 1
for: 10m
labels:
severity: warning
annotations:
summary: "{{ $labels.name }} a échoué sur {{ $labels.instance }}"
- alert: SystemdServiceFailed
expr: node_systemd_unit_state{state="failed"} == 1
for: 10m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} {{ raw("$label.name") }} a échoué
# Check load of instance
- alert: LoadUsage
expr: node_load1 > 5
for: 2m
labels:
severity: warning
annotations:
summary: "La charge de {{ $labels.instance }} est à {{ $value }} !"
- alert: LoadUsage
expr: node_load1 > 5
for: 2m
labels:
severity: warning
annotations:
summary: >
{{ instance }} Charge à {{ raw("$value") }}
# Check UPS
- alert: UpsOutputSourceChanged
expr: upsOutputSource != 3
for: 1m
labels:
severity: warning
annotations:
summary: "La source d'alimentation de {{ $labels.instance }} a changé !"
- alert: UpsOutputSourceChanged
expr: upsOutputSource != 3
for: 1m
labels:
severity: critical
annotations:
summary: >-
{{ instance }} Source d'alimentation changée
- alert: UpsBatteryStatusWarning
expr: upsBatteryStatus == 3
for: 2m
labels:
severity: warning
annotations:
summary: "L'état de la batterie de {{ $labels.instance }} est faible !"
- alert: UpsBatteryStatusWarning
expr: upsBatteryStatus == 3
for: 2m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} État de la batterie faible
- alert: UpsBatteryStatusCritical
expr: upsBatteryStatus == 4
for: 10m
labels:
severity: warning
annotations:
summary: "L'état de la batterie de {{ $labels.instance }} est affaibli !"
- alert: UpsBatteryStatusCritical
expr: upsBatteryStatus == 4
for: 10m
labels:
severity: critical
annotations:
summary: >-
{{ instance }} État de la batterie critique
- alert: UpsHighLoad
expr: upsOutputPercentLoad > 70
for: 5m
labels:
severity: critical
annotations:
summary: "La charge de {{ $labels.instance }} est de {{ $value }}% !"
- alert: UpsHighLoad
expr: upsOutputPercentLoad > 70
for: 5m
labels:
severity: critical
annotations:
summary: >-
{{ instance }} Charge de {{ raw("$value | round") }}%
- alert: UpsWrongInputVoltage
expr: (upsInputVoltage < 210) or (upsInputVoltage > 250)
for: 10m
labels:
severity: warning
annotations:
summary: "La tension d'entrée de {{ $labels.instance }} est de {{ $value }}V."
- alert: UpsWrongInputVoltage
expr: (upsInputVoltage < 210) or (upsInputVoltage > 250)
for: 10m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} Tension d'entrée de {{ raw("$value") }}V
- alert: UpsWrongOutputVoltage
expr: (upsOutputVoltage < 220) or (upsOutputVoltage > 240)
for: 10m
labels:
severity: warning
annotations:
summary: "La tension de sortie de {{ $labels.instance }} est de {{ $value }}V."
- alert: UpsWrongOutputVoltage
expr: (upsOutputVoltage < 220) or (upsOutputVoltage > 240)
for: 10m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} Tension de sortie de {{ raw("$value") }}V
- alert: UpsTimeRemainingWarning
expr: upsEstimatedMinutesRemaining < 8
for: 1m
labels:
severity: warning
annotations:
summary: "L'autonomie restante sur {{ $labels.instance }} est de {{ $value }} min."
- alert: UpsTimeRemainingWarning
expr: upsEstimatedMinutesRemaining < 8
for: 1m
labels:
severity: warning
annotations:
summary: >-
{{ instance }} Autonomie restante de {{ raw("$value") }} min
- alert: UpsTimeRemainingCritical
expr: upsEstimatedMinutesRemaining < 5
for: 1m
labels:
severity: critical
annotations:
summary: "L'autonomie restante sur {{ $labels.instance }} est de {{ $value }} min."
{% endraw %}
- alert: UpsTimeRemainingCritical
expr: upsEstimatedMinutesRemaining < 5
for: 1m
labels:
severity: critical
annotations:
summary: >-
{{ instance }} Autonomie restante de {{ raw("$value") }} min
...

4
roles/prometheus/templates/prometheus/prometheus.yml.j2
View file

@ -1,4 +1,5 @@
# {{ ansible_managed }}
---
{{ ansible_managed | comment }}
global:
# scrape_interval is set to the global default (60s)
@ -100,3 +101,4 @@ scrape_configs:
file_sd_configs:
- files:
- '/etc/prometheus/targets_docker.json'
...