diff --git a/CHANGELOG.md b/CHANGELOG.md index 9bce4d7b..07fcca0e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Fixed - Update `MimirHPAReachedMaxReplicas` opsrecipe link +- Fix aggregation rule of the `slo:current_burn_rate:ratio` slo. ## [4.15.1] - 2024-09-16 diff --git a/helm/prometheus-rules/templates/platform/atlas/recording-rules/grafana-cloud.rules.yml b/helm/prometheus-rules/templates/platform/atlas/recording-rules/grafana-cloud.rules.yml index 1164c13a..a4e22112 100644 --- a/helm/prometheus-rules/templates/platform/atlas/recording-rules/grafana-cloud.rules.yml +++ b/helm/prometheus-rules/templates/platform/atlas/recording-rules/grafana-cloud.rules.yml @@ -550,7 +550,21 @@ spec: - name: slos.grafana-cloud.recording rules: # Let's not send any of the slo:sli_error:ratio_ratexxx metrics but the slo:sli_error:ratio_rate5m rule to Grafana Cloud as it's not useful for the SLOs dashboard. - - expr: sum(slo:current_burn_rate:ratio) by (cluster_id, cluster_type, customer, installation, pipeline, provider, region, slo, service) + - expr: sum( + label_replace( + label_replace( + slo:current_burn_rate:ratio, + "slo", + "$1", + "sloth_id", + "(.*)" + ), + "service", + "$1", + "sloth_service", + "(.*)" + ) + ) by (cluster_id, cluster_type, customer, installation, pipeline, provider, region, slo, service) record: aggregation:slo:current_burn_rate:ratio - expr: |- sum(