assets,site/content: daily assets regeneration

monitoring-mixins · Nov 8, 2024 · 5ca8d2b · 5ca8d2b
1 parent 3e4f531
commit 5ca8d2b
Show file tree

Hide file tree

Showing 2 changed files with 24 additions and 14 deletions.
diff --git a/assets/kubernetes/alerts.yaml b/assets/kubernetes/alerts.yaml
@@ -169,12 +169,13 @@ groups:
       severity: warning
   - alert: KubeContainerWaiting
     annotations:
-      description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container
-        {{ $labels.container}} has been in waiting state for longer than 1 hour.
+      description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on
+        container {{ $labels.container}} has been in waiting state for longer than
+        1 hour. (reason: "{{ $labels.reason }}").'
       runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
       summary: Pod container waiting longer than 1 hour
     expr: |
-      sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
+      kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics"} > 0
     for: 1h
     labels:
       severity: warning
@@ -365,9 +366,9 @@ groups:
       runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
       summary: Processes experience elevated CPU throttling.
     expr: |
-      sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace)
+      sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
         /
-      sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace)
+      sum(increase(container_cpu_cfs_periods_total{job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
         > ( 25 / 100 )
     for: 15m
     labels:
@@ -573,7 +574,9 @@ groups:
       runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
       summary: Client certificate is about to expire.
     expr: |
-      apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
+      histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
+      and
+      on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
     for: 5m
     labels:
       severity: warning
@@ -584,7 +587,9 @@ groups:
       runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
       summary: Client certificate is about to expire.
     expr: |
-      apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
+      histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
+      and
+      on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
     for: 5m
     labels:
       severity: critical

diff --git a/site/content/kubernetes/_index.md b/site/content/kubernetes/_index.md
@@ -244,12 +244,13 @@ https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md
 {{< code lang="yaml" >}}
 alert: KubeContainerWaiting
 annotations:
-  description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container
-    {{ $labels.container}} has been in waiting state for longer than 1 hour.
+  description: 'pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container
+    {{ $labels.container}} has been in waiting state for longer than 1 hour. (reason:
+    "{{ $labels.reason }}").'
   runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
   summary: Pod container waiting longer than 1 hour
 expr: |
-  sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
+  kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics"} > 0
 for: 1h
 labels:
   severity: warning
@@ -525,9 +526,9 @@ annotations:
   runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
   summary: Processes experience elevated CPU throttling.
 expr: |
-  sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace)
+  sum(increase(container_cpu_cfs_throttled_periods_total{container!="", job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
     /
-  sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace)
+  sum(increase(container_cpu_cfs_periods_total{job="cadvisor", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)
     > ( 25 / 100 )
 for: 15m
 labels:
@@ -805,7 +806,9 @@ annotations:
   runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
   summary: Client certificate is about to expire.
 expr: |
-  apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
+  histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
+  and
+  on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
 for: 5m
 labels:
   severity: warning
@@ -822,7 +825,9 @@ annotations:
   runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
   summary: Client certificate is about to expire.
 expr: |
-  apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0 and on(cluster, job) histogram_quantile(0.01, sum by (cluster, job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
+  histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
+  and
+  on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="kube-apiserver"} > 0
 for: 5m
 labels:
   severity: critical