diff --git a/jsonnet/kube-prometheus/versions.json b/jsonnet/kube-prometheus/versions.json index 4b700d246a1ee3a177f9b0a436fe6f69f5fded1d..379bc298ccfe65bdc28a21caecd133e76f9f1815 100644 --- a/jsonnet/kube-prometheus/versions.json +++ b/jsonnet/kube-prometheus/versions.json @@ -1,13 +1,12 @@ { "alertmanager": "0.24.0", "blackboxExporter": "0.20.0", - "grafana": "8.4.4", + "grafana": "8.4.5", "kubeStateMetrics": "2.4.2", "nodeExporter": "1.3.1", "prometheus": "2.34.0", "prometheusAdapter": "0.9.1", "prometheusOperator": "0.55.1", - "pyrra": "0.3.4", "kubeRbacProxy": "0.11.0", "configmapReload": "0.5.0" } diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 3e412a8f916711c802bbca26d4d814c47155c086..08d0922916b1110ab8c45cc177de2efc05db5e4d 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -18,7 +18,7 @@ "subdir": "contrib/mixin" } }, - "version": "be2929568f81080b20ef6812992f2e09c8dac91b", + "version": "3d3c4373e3a4b029bd266afce307e69e3e399470", "sum": "zhLYhUNcXNkMRfJhMUX0UiOpi8TOuLmUqJfO9NFKFkg=" }, { @@ -28,7 +28,7 @@ "subdir": "grafana-mixin" } }, - "version": "8c622c1ef626a6982e0a6353877dd02313988010", + "version": "1120f9e255760a3c104b57871fcb91801e934382", "sum": "MkjR7zCgq6MUZgjDzop574tFKoTX2OBr7DTwm1K+Ofs=" }, { @@ -48,7 +48,7 @@ "subdir": "grafana-builder" } }, - "version": "98c3060877aa178f6bdfc6ac618fbe0043fc3de7", + "version": "fa7633803d478c461352f9a4a67ca6fd0a1a7b30", "sum": "0KkygBQd/AFzUvVzezE4qF/uDYgrwUXVpZfINBti0oc=" }, { @@ -58,8 +58,8 @@ "subdir": "" } }, - "version": "a2196d1b3493c15117550df2fd35dbdf54e4fa0e", - "sum": "QW/hop00uVdVHZ0ay2Ceogrra7qfBCvGqtuyYaoxHXY=" + "version": "5c2dd2c63c8d655bdb7717f695d02bd22bd180e8", + "sum": "aCO3uWUERAebUKdE8OE/x5M5EWe8f+mOWs6lp4yqtbs=" }, { "source": { @@ -68,7 +68,7 @@ "subdir": "lib/promgrafonnet" } }, - "version": "a2196d1b3493c15117550df2fd35dbdf54e4fa0e", + "version": "5c2dd2c63c8d655bdb7717f695d02bd22bd180e8", "sum": "zv7hXGui6BfHzE9wPatHI/AGZa4A2WKo6pq7ZdqBsps=" }, { @@ -98,7 +98,7 @@ "subdir": "jsonnet/mixin" } }, - "version": "90e243ea91e4f332d517b0a2c190df9d5c3026a9", + "version": "1d0d4b8f5dc96e81ae2280dfdbce18de556fb175", "sum": "joc3gM74r0q658bmpfTbeAr0Nce4gTBv0rf3I+2J0rQ=", "name": "prometheus-operator-mixin" }, @@ -109,8 +109,8 @@ "subdir": "jsonnet/prometheus-operator" } }, - "version": "90e243ea91e4f332d517b0a2c190df9d5c3026a9", - "sum": "SmdmXrgVBxc68tkc827FD2ozO4JRwvJCEVYLgKTYWwk=" + "version": "1d0d4b8f5dc96e81ae2280dfdbce18de556fb175", + "sum": "NqiD9mjw2dbS/xXSv5q+JAxU4v+YtQDnwpkSqNFD/pQ=" }, { "source": { @@ -130,7 +130,7 @@ "subdir": "docs/node-mixin" } }, - "version": "9aae303a46c3153b75e4d32b0936b40e4ee0beeb", + "version": "b52bf958f8e2d4ed1624b8122d08af4d12da9322", "sum": "/SFdKggqBEmznyeGfpyEZl4rC69mMtLGEB9lG1mQhVA=" }, { @@ -140,8 +140,8 @@ "subdir": "documentation/prometheus-mixin" } }, - "version": "c7be45d957dd90e605738d8b74482e7579da0db0", - "sum": "7mS7v4Tt0wypJhUrjbHNbSe5maAToU5qHFD8LsLs+jM=", + "version": "f889ad3f7340e4bac6a70511167ddc33001df1f6", + "sum": "APXOIP3B3dZ3Tyh7L2UhyWR8Vbf5+9adTLz/ya7n6uU=", "name": "prometheus" }, { @@ -151,7 +151,7 @@ "subdir": "config/crd/bases" } }, - "version": "6b0b6c2f362bbbea151a6610e18870e7cb1c2b5b", + "version": "a41c490e224515fafbbbefe4bf12d45f4ccca0a3", "sum": "GQ0GFKGdIWKx1b78VRs6jtC4SMqkBjT5jl65QUjPKK4=" }, { @@ -161,7 +161,7 @@ "subdir": "mixin" } }, - "version": "f0e673a2e4860d8cffafba4c97955171e5c6cb2b", + "version": "0afd343224dc40d27843bb907b2c7008cdbe3219", "sum": "dBm9ML50quhu6dwTIgfNmVruMqfaUeQVCO/6EKtQLxE=", "name": "thanos-mixin" }, diff --git a/manifests/grafana-config.yaml b/manifests/grafana-config.yaml index eb280ba10cfa23d291790155b476a1a30a9a2b77..947bad302ab4fd1e63a1244b3a6e454eb1b121a2 100644 --- a/manifests/grafana-config.yaml +++ b/manifests/grafana-config.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-config namespace: monitoring stringData: diff --git a/manifests/grafana-dashboardDatasources.yaml b/manifests/grafana-dashboardDatasources.yaml index e2cc10acf03056b4b089972531b016b691edf7cf..802d464ae5d4d7a3717bae0f7367f492b9d3121f 100644 --- a/manifests/grafana-dashboardDatasources.yaml +++ b/manifests/grafana-dashboardDatasources.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-datasources namespace: monitoring stringData: diff --git a/manifests/grafana-dashboardDefinitions.yaml b/manifests/grafana-dashboardDefinitions.yaml index 8958e35cae9ec1105e8d341da865669e3540abb9..3e10cd4b5b075e5f01a64eec8540e4fa3d81d4a0 100644 --- a/manifests/grafana-dashboardDefinitions.yaml +++ b/manifests/grafana-dashboardDefinitions.yaml @@ -596,7 +596,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-alertmanager-overview namespace: monitoring - apiVersion: v1 @@ -2357,7 +2357,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-apiserver namespace: monitoring - apiVersion: v1 @@ -4228,7 +4228,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-cluster-total namespace: monitoring - apiVersion: v1 @@ -5407,7 +5407,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-controller-manager namespace: monitoring - apiVersion: v1 @@ -6032,7 +6032,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-grafana-overview namespace: monitoring - apiVersion: v1 @@ -9109,7 +9109,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-k8s-resources-cluster namespace: monitoring - apiVersion: v1 @@ -11895,7 +11895,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-k8s-resources-namespace namespace: monitoring - apiVersion: v1 @@ -12910,7 +12910,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-k8s-resources-node namespace: monitoring - apiVersion: v1 @@ -15368,7 +15368,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-k8s-resources-pod namespace: monitoring - apiVersion: v1 @@ -17381,7 +17381,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-k8s-resources-workload namespace: monitoring - apiVersion: v1 @@ -19559,7 +19559,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-k8s-resources-workloads-namespace namespace: monitoring - apiVersion: v1 @@ -21802,7 +21802,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-kubelet namespace: monitoring - apiVersion: v1 @@ -23255,7 +23255,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-namespace-by-pod namespace: monitoring - apiVersion: v1 @@ -24980,7 +24980,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-namespace-by-workload namespace: monitoring - apiVersion: v1 @@ -26032,7 +26032,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-node-cluster-rsrc-use namespace: monitoring - apiVersion: v1 @@ -27110,7 +27110,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-node-rsrc-use namespace: monitoring - apiVersion: v1 @@ -28090,7 +28090,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-nodes namespace: monitoring - apiVersion: v1 @@ -28666,7 +28666,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-persistentvolumesusage namespace: monitoring - apiVersion: v1 @@ -29883,7 +29883,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-pod-total namespace: monitoring - apiVersion: v1 @@ -31542,7 +31542,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-prometheus-remote-write namespace: monitoring - apiVersion: v1 @@ -32766,7 +32766,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-prometheus namespace: monitoring - apiVersion: v1 @@ -34026,7 +34026,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-proxy namespace: monitoring - apiVersion: v1 @@ -35127,7 +35127,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-scheduler namespace: monitoring - apiVersion: v1 @@ -36554,7 +36554,7 @@ items: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboard-workload-total namespace: monitoring kind: ConfigMapList diff --git a/manifests/grafana-dashboardSources.yaml b/manifests/grafana-dashboardSources.yaml index 7fab4bad31a0c491681c61c22708acbee75c7172..7bbf3eeda349357b2d7a781d414e6fa1b52f31e8 100644 --- a/manifests/grafana-dashboardSources.yaml +++ b/manifests/grafana-dashboardSources.yaml @@ -22,6 +22,6 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana-dashboards namespace: monitoring diff --git a/manifests/grafana-deployment.yaml b/manifests/grafana-deployment.yaml index e5d9dedcd9e90629c5564dc91ecd42e687d4b9ff..d0e463affea39f3bc0e57a5e82c1906496e32f78 100644 --- a/manifests/grafana-deployment.yaml +++ b/manifests/grafana-deployment.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana namespace: monitoring spec: @@ -18,19 +18,19 @@ spec: template: metadata: annotations: - checksum/grafana-config: ea65309d1ed89a6a1d3bd859ffa36bd0 - checksum/grafana-dashboardproviders: 058a2c55a953c791c17e5db4d9ffb6f6 - checksum/grafana-datasources: 5cff90f5c35ec1604e12e13ce3bf2700 + checksum/grafana-config: 813d4bf6c9d7cac884a9fa2261205c2d + checksum/grafana-dashboardproviders: e9459f6ac64d3855b06645176035b1f2 + checksum/grafana-datasources: 57939af14bc401215e5364bbe0f81094 labels: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 spec: automountServiceAccountToken: false containers: - env: [] - image: grafana/grafana:8.4.4 + image: grafana/grafana:8.4.5 name: grafana ports: - containerPort: 3000 diff --git a/manifests/grafana-prometheusRule.yaml b/manifests/grafana-prometheusRule.yaml index 6cb31de46a78809afda28dd3f905ecf1cb988855..0c522a748173ab375a7d72f5b6308a11fa36bd98 100644 --- a/manifests/grafana-prometheusRule.yaml +++ b/manifests/grafana-prometheusRule.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 prometheus: k8s role: alert-rules name: grafana-rules diff --git a/manifests/grafana-service.yaml b/manifests/grafana-service.yaml index 9cbff85d27e7b2cd34fc6c417062182e0b5dc2de..7342bb4f05e96efd46cf712890d93618de9facb9 100644 --- a/manifests/grafana-service.yaml +++ b/manifests/grafana-service.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana namespace: monitoring spec: diff --git a/manifests/grafana-serviceAccount.yaml b/manifests/grafana-serviceAccount.yaml index 8e942017043508d973c06ce44e723e7fe69e9dd2..ce7352875d25f6f5868741b9fe4a637f533c16a4 100644 --- a/manifests/grafana-serviceAccount.yaml +++ b/manifests/grafana-serviceAccount.yaml @@ -6,6 +6,6 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana namespace: monitoring diff --git a/manifests/grafana-serviceMonitor.yaml b/manifests/grafana-serviceMonitor.yaml index d6a8d0ce4df7a24bc1ad6783eb075dd5ff34db8e..a9a41140a9c710054377265a983357d9a61b1215 100644 --- a/manifests/grafana-serviceMonitor.yaml +++ b/manifests/grafana-serviceMonitor.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/component: grafana app.kubernetes.io/name: grafana app.kubernetes.io/part-of: kube-prometheus - app.kubernetes.io/version: 8.4.4 + app.kubernetes.io/version: 8.4.5 name: grafana namespace: monitoring spec: diff --git a/manifests/kubernetesControlPlane-prometheusRule.yaml b/manifests/kubernetesControlPlane-prometheusRule.yaml index 964324bf161bf85db1a087585d6e394275232943..397c657d741aaf0c0ac2fb603287326f55f4cc39 100644 --- a/manifests/kubernetesControlPlane-prometheusRule.yaml +++ b/manifests/kubernetesControlPlane-prometheusRule.yaml @@ -202,15 +202,16 @@ spec: for: 15m labels: severity: warning - - alert: KubeJobCompletion + - alert: KubeJobNotCompleted annotations: description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking - more than 12 hours to complete. - runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobcompletion + more than {{ "43200" | humanizeDuration }} to complete. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted summary: Job did not complete in time expr: | - kube_job_spec_completions{job="kube-state-metrics"} - kube_job_status_succeeded{job="kube-state-metrics"} > 0 - for: 12h + time() - max by(namespace, job_name) (kube_job_status_start_time{job="kube-state-metrics"} + and + kube_job_status_active{job="kube-state-metrics"} > 0) > 43200 labels: severity: warning - alert: KubeJobFailed @@ -451,9 +452,9 @@ spec: runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors summary: Kubernetes API server client is experiencing errors. expr: | - (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job, namespace) + (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (cluster, instance, job, namespace) / - sum(rate(rest_client_requests_total[5m])) by (instance, job, namespace)) + sum(rate(rest_client_requests_total[5m])) by (cluster, instance, job, namespace)) > 0.01 for: 15m labels: @@ -612,11 +613,11 @@ spec: runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods summary: Kubelet is running at capacity. expr: | - count by(node) ( + count by(cluster, node) ( (kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"}) ) / - max by(node) ( + max by(cluster, node) ( kube_node_status_capacity{job="kube-state-metrics",resource="pods"} != 1 ) > 0.95 for: 15m @@ -629,7 +630,7 @@ spec: runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping summary: Node readiness status is flapping. expr: | - sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (node) > 2 + sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (cluster, node) > 2 for: 15m labels: severity: warning @@ -1391,8 +1392,8 @@ spec: - name: node.rules rules: - expr: | - topk by(namespace, pod) (1, - max by (node, namespace, pod) ( + topk by(cluster, namespace, pod) (1, + max by (cluster, node, namespace, pod) ( label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)") )) record: 'node_namespace_pod:kube_pod_info:' diff --git a/manifests/prometheus-prometheusRule.yaml b/manifests/prometheus-prometheusRule.yaml index d8571fe12736d19d2efd26859c535ca1c6274ea9..a8fab1ccf2dfd4f6fce6e7f4d11c36584fe6502c 100644 --- a/manifests/prometheus-prometheusRule.yaml +++ b/manifests/prometheus-prometheusRule.yaml @@ -253,9 +253,9 @@ spec: severity: warning - alert: PrometheusScrapeBodySizeLimitHit annotations: - description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped - {{ printf "%.0f" $value }} targets because some targets exceeded the configured - body_size_limit. + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ + printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded + the configured body_size_limit. runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapebodysizelimithit summary: Prometheus has dropped some targets that exceeded body size limit. expr: | @@ -263,6 +263,19 @@ spec: for: 15m labels: severity: warning + - alert: PrometheusScrapeSampleLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ + printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded + the configured sample_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapesamplelimithit + summary: Prometheus has failed scrapes that have exceeded the configured sample + limit. + expr: | + increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 15m + labels: + severity: warning - alert: PrometheusTargetSyncFailure annotations: description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}} diff --git a/manifests/setup/0alertmanagerConfigCustomResourceDefinition.yaml b/manifests/setup/0alertmanagerConfigCustomResourceDefinition.yaml index cad11e62cfa34c4080748d67dd69b698927ec830..7b03c0fc1fd95e8be72129b67bf2d2b74343fb1e 100644 --- a/manifests/setup/0alertmanagerConfigCustomResourceDefinition.yaml +++ b/manifests/setup/0alertmanagerConfigCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: AlertmanagerConfig listKind: AlertmanagerConfigList plural: alertmanagerconfigs + shortNames: + - amcfg singular: alertmanagerconfig scope: Namespaced versions: @@ -444,6 +446,10 @@ spec: description: OpsGenieConfig configures notifications via OpsGenie. See https://prometheus.io/docs/alerting/latest/configuration/#opsgenie_config properties: + actions: + description: Comma separated list of actions that will + be available for the alert. + type: string apiKey: description: The secret's key that contains the OpsGenie API key. The secret needs to be in the same namespace @@ -490,6 +496,10 @@ spec: - value type: object type: array + entity: + description: Optional field that can be used to specify + which domain alert is related to. + type: string httpConfig: description: HTTP client configuration. properties: diff --git a/manifests/setup/0alertmanagerCustomResourceDefinition.yaml b/manifests/setup/0alertmanagerCustomResourceDefinition.yaml index 978306f26e7f088507759220dab40a49215de75b..7222c29739d883a49e3e7bbfcb722e3f6efb395f 100644 --- a/manifests/setup/0alertmanagerCustomResourceDefinition.yaml +++ b/manifests/setup/0alertmanagerCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: Alertmanager listKind: AlertmanagerList plural: alertmanagers + shortNames: + - am singular: alertmanager scope: Namespaced versions: diff --git a/manifests/setup/0podmonitorCustomResourceDefinition.yaml b/manifests/setup/0podmonitorCustomResourceDefinition.yaml index 9bc826f5fdbc1ef1c8720fbce140412a1a790bd6..be76658f705bf5ffc901e4c98823d2b3f5a9d62e 100644 --- a/manifests/setup/0podmonitorCustomResourceDefinition.yaml +++ b/manifests/setup/0podmonitorCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: PodMonitor listKind: PodMonitorList plural: podmonitors + shortNames: + - pmon singular: podmonitor scope: Namespaced versions: diff --git a/manifests/setup/0probeCustomResourceDefinition.yaml b/manifests/setup/0probeCustomResourceDefinition.yaml index 14260d4a5aa989cd9051eb202ed8bff04d8be811..04dd46d23199869302adb76ae5f887b33709e492 100644 --- a/manifests/setup/0probeCustomResourceDefinition.yaml +++ b/manifests/setup/0probeCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: Probe listKind: ProbeList plural: probes + shortNames: + - prb singular: probe scope: Namespaced versions: diff --git a/manifests/setup/0prometheusCustomResourceDefinition.yaml b/manifests/setup/0prometheusCustomResourceDefinition.yaml index ae37bb13fc81f9c25915d444fe56507c97bd9968..8f5b65a6c837243c479497db4882137d3c124351 100644 --- a/manifests/setup/0prometheusCustomResourceDefinition.yaml +++ b/manifests/setup/0prometheusCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: Prometheus listKind: PrometheusList plural: prometheuses + shortNames: + - prom singular: prometheus scope: Namespaced versions: diff --git a/manifests/setup/0prometheusruleCustomResourceDefinition.yaml b/manifests/setup/0prometheusruleCustomResourceDefinition.yaml index de8ec2357be8d77e0f53fe05af665ce7b4352bde..02241a6dd87b0215197c50066e5cbbf8931c2a29 100644 --- a/manifests/setup/0prometheusruleCustomResourceDefinition.yaml +++ b/manifests/setup/0prometheusruleCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: PrometheusRule listKind: PrometheusRuleList plural: prometheusrules + shortNames: + - promrule singular: prometheusrule scope: Namespaced versions: diff --git a/manifests/setup/0servicemonitorCustomResourceDefinition.yaml b/manifests/setup/0servicemonitorCustomResourceDefinition.yaml index 0fbc1aa6f3e2398bbdfcb3fd4abbdf43b098f1e9..f0a4089a128e245689100dccc34340952cdd6af3 100644 --- a/manifests/setup/0servicemonitorCustomResourceDefinition.yaml +++ b/manifests/setup/0servicemonitorCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: ServiceMonitor listKind: ServiceMonitorList plural: servicemonitors + shortNames: + - smon singular: servicemonitor scope: Namespaced versions: diff --git a/manifests/setup/0thanosrulerCustomResourceDefinition.yaml b/manifests/setup/0thanosrulerCustomResourceDefinition.yaml index 8af132f00398a807fc2ff326a82eec43aefeb249..0c9aa9ccb54b89be9b7dcd982d39875affcf951d 100644 --- a/manifests/setup/0thanosrulerCustomResourceDefinition.yaml +++ b/manifests/setup/0thanosrulerCustomResourceDefinition.yaml @@ -13,6 +13,8 @@ spec: kind: ThanosRuler listKind: ThanosRulerList plural: thanosrulers + shortNames: + - ruler singular: thanosruler scope: Namespaced versions: