From 016af2f507cba62c44d8e21c47a6b4e15fae3a3c Mon Sep 17 00:00:00 2001
From: Quentin Duchemin <quentinduchemin@tuta.io>
Date: Sun, 29 Aug 2021 01:10:10 +0200
Subject: [PATCH] Alerts based on SMART values only for physical machines
---
pica-metrologie/docker-compose.yml | 4 ++--
pica-metrologie/vmalert-rules.yml | 5 ++++-
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/pica-metrologie/docker-compose.yml b/pica-metrologie/docker-compose.yml
index 5eff7f1a..022a8bc8 100644
--- a/pica-metrologie/docker-compose.yml
+++ b/pica-metrologie/docker-compose.yml
@@ -78,12 +78,12 @@ services:
# Where to read metrics
- "-datasource.url=http://victoria-metrics:8428"
# Where to write and read alert states, to keep
- # state during restart, as vmagent stores states in memory
+ # state during restart, as vmalert stores states in memory
- "-remoteWrite.url=http://victoria-metrics:8428"
- "-remoteRead.url=http://victoria-metrics:8428"
# Where to send alert when they must be triggered
- "-notifier.url=http://alertmanager:9093"
- # HTTP server for vmagent's own metrics
+ # HTTP server for vmalert's own metrics
- "-httpListenAddr=:8880"
# By default, evaluate rules every 1 minute
- "-evaluationInterval=1m"
diff --git a/pica-metrologie/vmalert-rules.yml b/pica-metrologie/vmalert-rules.yml
index e9b10e07..1396e1ce 100644
--- a/pica-metrologie/vmalert-rules.yml
+++ b/pica-metrologie/vmalert-rules.yml
@@ -68,7 +68,10 @@ groups:
summary: Proxmox HDD volume 90% full
description: Proxmox HDD volume ({{ $labels.storage }}) on {{ $labels.instance }} is {{ $value }}% full
- alert: DiskDamaged
- expr: smartmon_device_smart_healthy != 1
+ # Only get values from real disks so ignore VMs
+ # This is hardcoded but I cannot see other way to do so because VMs do no have a specific prefix
+ # We must add new machines here
+ expr: smartmon_device_smart_healthy{node=~"alice|bob"} != 1
labels:
severity: critical
annotations:
--
GitLab