lukaszraczylo/kubemirror
1
0
Fork 0
mirror of https://github.com/lukaszraczylo/kubemirror.git synced 2026-07-11 02:33:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(monitoring): match real controller label values in dashboards and alerts

Browse Source 
kubemirror overrides controller names to <Kind>.<version>.<group> (e.g. Secret.v1.), but the dashboards, alerts, and recording rules filtered controller=~"secret|configmap" (the controller-runtime default name), so every panel and alert matched nothing. Switch all selectors to Secret.*|ConfigMap.* and document the naming convention.
This commit is contained in:
Lukasz Raczylo
2026-06-21 13:26:49 +01:00
parent 6d27d7dfe7
commit 28896ab1d6
3 changed files with 29 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
monitoring/prometheusrule.yaml
+12 -12
View File
@@ -25,9 +25,9 @@ spec:
- alert: KubeMirrorHighReconcileErrors
expr: |
rate(controller_runtime_reconcile_errors_total{controller="secret"}[5m]) > 0.1
rate(controller_runtime_reconcile_errors_total{controller=~"Secret.*"}[5m]) > 0.1
or
rate(controller_runtime_reconcile_errors_total{controller="configmap"}[5m]) > 0.1
rate(controller_runtime_reconcile_errors_total{controller=~"ConfigMap.*"}[5m]) > 0.1
for: 10m
labels:
severity: warning
@@ -39,7 +39,7 @@ spec:
- alert: KubeMirrorReconcileLatencyHigh
expr: |
histogram_quantile(0.99,
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"secret|configmap"}[5m])
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"Secret.*|ConfigMap.*"}[5m])
) > 5
for: 10m
labels:
@@ -51,7 +51,7 @@ spec:
- alert: KubeMirrorWorkqueueDepthHigh
expr: |
workqueue_depth{name=~"secret|configmap"} > 100
workqueue_depth{name=~"Secret.*|ConfigMap.*"} > 100
for: 15m
labels:
severity: warning
@@ -74,9 +74,9 @@ spec:
# Resource mirror alerts
- alert: KubeMirrorHighFailureRate
expr: |
sum(rate(controller_runtime_reconcile_errors_total{controller=~"secret|configmap"}[5m]))
sum(rate(controller_runtime_reconcile_errors_total{controller=~"Secret.*|ConfigMap.*"}[5m]))
/
sum(rate(controller_runtime_reconcile_total{controller=~"secret|configmap"}[5m]))
sum(rate(controller_runtime_reconcile_total{controller=~"Secret.*|ConfigMap.*"}[5m]))
> 0.05
for: 10m
labels:
@@ -118,29 +118,29 @@ spec:
- record: kubemirror:reconcile_duration_seconds:p99
expr: |
histogram_quantile(0.99,
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"secret|configmap"}[5m])
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"Secret.*|ConfigMap.*"}[5m])
)
- record: kubemirror:reconcile_duration_seconds:p95
expr: |
histogram_quantile(0.95,
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"secret|configmap"}[5m])
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"Secret.*|ConfigMap.*"}[5m])
)
- record: kubemirror:reconcile_duration_seconds:p50
expr: |
histogram_quantile(0.50,
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"secret|configmap"}[5m])
rate(controller_runtime_reconcile_time_seconds_bucket{controller=~"Secret.*|ConfigMap.*"}[5m])
)
- record: kubemirror:reconcile_rate:5m
expr: |
sum(rate(controller_runtime_reconcile_total{controller=~"secret|configmap"}[5m])) by (controller, result)
sum(rate(controller_runtime_reconcile_total{controller=~"Secret.*|ConfigMap.*"}[5m])) by (controller, result)
- record: kubemirror:reconcile_errors:rate5m
expr: |
sum(rate(controller_runtime_reconcile_errors_total{controller=~"secret|configmap"}[5m])) by (controller)
sum(rate(controller_runtime_reconcile_errors_total{controller=~"Secret.*|ConfigMap.*"}[5m])) by (controller)
- record: kubemirror:workqueue_depth:max
expr: |
max(workqueue_depth{name=~"secret|configmap"}) by (name)
max(workqueue_depth{name=~"Secret.*|ConfigMap.*"}) by (name)