From 297f63a01e9724d118b43725636dd2a756567efd Mon Sep 17 00:00:00 2001 From: hagen1778 Date: Tue, 3 Oct 2023 16:45:33 +0200 Subject: [PATCH] alerting: account for `vmauth` component for alerts `ServiceDown` and `TooManyRestarts` Signed-off-by: hagen1778 --- deployment/docker/alerts-health.yml | 4 ++-- docs/CHANGELOG.md | 2 ++ 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/deployment/docker/alerts-health.yml b/deployment/docker/alerts-health.yml index 11ec22c1f8..eb1e2987c3 100644 --- a/deployment/docker/alerts-health.yml +++ b/deployment/docker/alerts-health.yml @@ -7,7 +7,7 @@ groups: # note the `job` filter and update accordingly to your setup rules: - alert: TooManyRestarts - expr: changes(process_start_time_seconds{job=~"victoriametrics.*|vmselect.*|vminsert.*|vmstorage.*|vmagent.*|vmalert.*|vmsingle.*|vmalertmanager.*"}[15m]) > 2 + expr: changes(process_start_time_seconds{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"}[15m]) > 2 labels: severity: critical annotations: @@ -16,7 +16,7 @@ groups: It might be crashlooping." - alert: ServiceDown - expr: up{job=~"victoriametrics.*|vmselect.*|vminsert.*|vmstorage.*|vmagent.*|vmalert.*|vmsingle.*|vmalertmanager.*"} == 0 + expr: up{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"} == 0 for: 2m labels: severity: critical diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md index 833c8dc64f..bcb4c6218b 100644 --- a/docs/CHANGELOG.md +++ b/docs/CHANGELOG.md @@ -28,6 +28,8 @@ The sandbox cluster installation is running under the constant load generated by ## tip +* FEATURE: [Alerting rules for VictoriaMetrics](https://github.com/VictoriaMetrics/VictoriaMetrics/tree/master/deployment/docker#alerts): account for `vmauth` component for alerts `ServiceDown` and `TooManyRestarts`. + ## [v1.94.0](https://github.com/VictoriaMetrics/VictoriaMetrics/releases/tag/v1.94.0) Released at 2023-10-02