fix prometheusrequestserror alert

Signed-off-by: QuentinBisson <[email protected]>
giantswarm · Aug 27, 2024 · 55c7942 · 55c7942
1 parent 618ee88
commit 55c7942
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 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
+
+- Fix PromtailRequestError to also account for 4xx and -1 errors (https://github.com/giantswarm/giantswarm/issues/31387).
+
 ## [4.12.0] - 2024-08-26
 
 ### Added

diff --git a/helm/prometheus-rules/templates/platform/atlas/alerting-rules/promtail.rules.yml b/helm/prometheus-rules/templates/platform/atlas/alerting-rules/promtail.rules.yml
@@ -31,13 +31,12 @@ spec:
             cancel_if_cluster_status_updating: "true"
             cancel_if_node_unschedulable: "true"
             cancel_if_node_not_ready: "true"
-        # Not tested
         - alert: PromtailRequestsErrors
           annotations:
             description: This alert checks if that the amount of failed requests is below 10% for promtail
             opsrecipe: promtail/
           expr: |
-            100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[2m])) by (cluster_id, installation, provider, pipeline, namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[2m])) by (cluster_id, installation, provider, pipeline, namespace, job, route, instance) > 10
+            100 * (sum(rate(promtail_request_duration_seconds_count{status_code!~"2.."}[2m])) by (cluster_id, installation, provider, pipeline, namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[2m])) by (cluster_id, installation, provider, pipeline, namespace, job, route, instance)) > 10
           for: 15m
           labels:
             area: platform