feat: Add default alerting rule for build failure SLO
diff --git a/deploy/operator-prometheus-rule.yaml b/deploy/operator-prometheus-rule.yaml
index 6a009dd..0d6ca96 100644
--- a/deploy/operator-prometheus-rule.yaml
+++ b/deploy/operator-prometheus-rule.yaml
@@ -68,3 +68,16 @@
message: |
{{ printf "%0.0f" $value }}% of the successful builds
for {{ $labels.job }} have their duration above 5m.
+ - alert: CamelKBuildFailure
+ expr: |
+ sum(rate(camel_k_build_duration_seconds_count{result="Error"}[5m])) by (job)
+ /
+ sum(rate(camel_k_build_duration_seconds_count[5m])) by (job)
+ * 100
+ > 1
+ for: 10m
+ labels:
+ severity: warning
+ annotations:
+ message: |
+ {{ printf "%0.0f" $value }}% of the builds for {{ $labels.job }} have failed.