From 046cd93581246ee4d5c056ca278ad57b8d528c07 Mon Sep 17 00:00:00 2001 From: Jeltz Date: Mon, 13 Dec 2021 02:41:12 +0100 Subject: [PATCH] Monitor APT pending and change swap alert level --- .../prometheus/templates/server.rules.yml.j2 | 26 ++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/roles/prometheus/templates/server.rules.yml.j2 b/roles/prometheus/templates/server.rules.yml.j2 index 5277fdf..53a228d 100644 --- a/roles/prometheus/templates/server.rules.yml.j2 +++ b/roles/prometheus/templates/server.rules.yml.j2 @@ -50,13 +50,14 @@ groups: node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes ) - ) * 100 >= 20 + ) * 100 >= 50 for: 3m labels: severity: warning annotations: summary: >- - La mémoire swap est utilisée à {{ raw('$value | printf "%.1f"') }}% + La mémoire swap est utilisée à + {{ raw('$value | printf "%.1f"') }}% - alert: HostPhysicalComponentTooHot expr: node_hwmon_temp_celsius > 79 @@ -155,5 +156,24 @@ groups: labels: severity: "critical" annotations: - summary: "Le Disque {{ raw('$labels.disk') }} n'est pas en bonne santé !" + summary: > + Le disque {{ raw('$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 ... -- 2.38.5