Fix MimirToGrafanaCloudExporterFailures alerts: labels cleanup (#1266)

Co-authored-by: Herve Nicol <[email protected]>
giantswarm · Jun 24, 2024 · 60ad6e7 · 60ad6e7
1 parent baad23f
commit 60ad6e7
Show file tree

Hide file tree

Showing 2 changed files with 14 additions and 3 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Fixed
+
+- Fixed MimirToGrafanaCloudExporterFailures alerts: labels cleanup
+
 ## [4.3.4] - 2024-06-21
 
 ### Fixed

diff --git a/...s-rules/templates/platform/atlas/alerting-rules/mimir-to-grafana-cloud-exporter.rules.yml b/...s-rules/templates/platform/atlas/alerting-rules/mimir-to-grafana-cloud-exporter.rules.yml
@@ -36,9 +36,16 @@ spec:
       # For remote read, we are looking the number of read queries are increasing
       # For remote write, we are looking the rate (on 10 minutes) of failed samples are not greater than 0 for 30 minutes
       expr: |
-        sum by (cluster_id, installation, provider, pipeline) (
-          rate(prometheus_remote_storage_read_queries_total{job="mimir/mimir-to-grafana-cloud", code=~"2.."}[10m]) == 0
-          or rate(prometheus_remote_storage_samples_failed_total{job="mimir/mimir-to-grafana-cloud"}[10m]) > 0
+        (
+          sum by (cluster_id, installation, provider, pipeline) (
+            rate(prometheus_remote_storage_read_queries_total{job="mimir/mimir-to-grafana-cloud", code=~"2.."}[10m])
+          ) == 0
+        )
+        or
+        (
+          sum by (cluster_id, installation, provider, pipeline) (
+            rate(prometheus_remote_storage_samples_failed_total{job="mimir/mimir-to-grafana-cloud"}[10m])
+          ) > 0
         )
       for: 30m
       labels: