ansible/roles/prometheus/templates/server.rules.yml.j2
Jeltz 046cd93581
All checks were successful
continuous-integration/drone/push Build is passing
continuous-integration/drone/pr Build is passing
Monitor APT pending and change swap alert level
2021-12-13 02:44:35 +01:00

179 lines
4.8 KiB
Django/Jinja

---
{{ ansible_managed | comment }}
{% macro raw(string) -%}
{{ "{{" }} {{ string }} {{ "}}" }}
{%- endmacro %}
groups:
- name: server.rules
rules:
- alert: InstanceDown
expr: up{instance!~".*.borne.auro.re$"} == 0
for: 3m
labels:
severity: critical
annotations:
summary: >-
Invisible depuis plus de 3 minutes
- alert: AccessPointDown
expr: up{instance=~".*.borne.auro.re$"} == 0
for: 3m
labels:
severity: warning
annotations:
summary: >-
Invisible depuis plus de 3 minutes
- 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: >-
{{ raw('$value | printf "%.1f"') }}% de mémoire
libre
- alert: HostSwapIsFillingUp
expr: >-
(
1 - (
node_memory_SwapFree_bytes
/ node_memory_SwapTotal_bytes
)
) * 100 >= 50
for: 3m
labels:
severity: warning
annotations:
summary: >-
La mémoire swap est utilisée à
{{ raw('$value | printf "%.1f"') }}%
- alert: HostPhysicalComponentTooHot
expr: node_hwmon_temp_celsius > 79
for: 3m
labels:
severity: critical
annotations:
summary: >-
La température de l'hôte est de {{ raw('$value') }}°C
({{ raw('$labels.chip') }}, {{ raw('$labels.sensor') }})
- alert: HostNodeOvertemperatureAlarm
expr: node_hwmon_temp_crit_alarm_celsius == 1
for: 0m
labels:
severity: critical
annotations:
summary: >-
L'alarme de température de l'hôte est active
({{ raw('$labels.chip') }}, {{ raw('$labels.sensor') }})
- alert: HostOomKillDetected
expr: increase(node_vmstat_oom_kill[1m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: Le noyau a tué {{ raw('$value') }} processus (OOM killer)
- alert: HostEdacCorrectableErrorsDetected
expr: increase(node_edac_correctable_errors_total[1m]) > 0
for: 0m
labels:
severity: warning
annotations:
summary: >-
{{ raw('$value | print "%.1f"') }} erreur(s) ont été
corrigée(s) (EDAC)
- alert: OutOfDiskSpace
expr: >-
node_filesystem_free_bytes / node_filesystem_size_bytes * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: >-
{{ raw('$value | printf "%.1f"') }}% d'espace libre pour
{{ raw('$labels.mountpoint') }}
- alert: OutOfInodes
expr: node_filesystem_files_free / node_filesystem_files * 100 < 10
for: 5m
labels:
severity: warning
annotations:
summary: >-
{{ raw('$value | printf "%.1f"') }}% d'inodes
restants pour {{ raw('$labels.mountpoint') }}
- alert: CpuUsage
expr: >-
(
100 - avg by (instance) (
irate(node_cpu_seconds_total{mode="idle"}[5m])
) * 100
) > 75
for: 10m
labels:
severity: warning
annotations:
summary: >-
CPU à {{ raw('$value | printf "%.1f"') }}%
- alert: SystemdServiceFailed
expr: node_systemd_unit_state{state="failed"} == 1
for: 10m
labels:
severity: warning
annotations:
summary: >-
{{ raw('$labels.name') }} a échoué
- alert: LoadUsage
expr: node_load1 > 5
for: 2m
labels:
severity: warning
annotations:
summary: >
Charge à {{ raw('$value') }}
- alert: UnhealthyDisk
expr: smartmon_device_smart_healthy < 1
for: 10m
labels:
severity: "critical"
annotations:
summary: >
Le disque {{ raw('$labels.disk') }} n'est pas en bonne santé
- alert: AptUpgradesPending
expr: sum by (instance) (apt_upgrades_pending) > 0
for: 10m
labels:
severity: warning
annotations:
summary: >
Des mises à jour de paquets sont en attente
- alert: RebootRequired
expr: node_reboot_required == 1
for: 10m
labels:
severity: warning
annotations:
summary: >
Un redémarrage est nécessaire
...