diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 93018a239bfcda7c15158a2adc239469990c6c48..3d0bf90f0c54c5838b7c3b18072a979155364669 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -18,7 +18,7 @@ "subdir": "contrib/mixin" } }, - "version": "7a98ab3ae0d66239f3802b43b26530c3e9c299c7", + "version": "e2a5df534cf6b0a12859e61bfc2758d56a1e1971", "sum": "IkDHlaE0gvvcPjSNurFT+jQ2aCOAbqHF1WVmXbAgkds=" }, { @@ -58,7 +58,7 @@ "subdir": "grafana-builder" } }, - "version": "e9f44d885c53d9ebdc849203f06ed74c7eccd362", + "version": "9a399823cb1f0e045b24c4648182cf12f953603a", "sum": "tDR6yT2GVfw0wTU12iZH+m01HrbIr6g/xN+/8nzNkU0=" }, { @@ -68,8 +68,8 @@ "subdir": "" } }, - "version": "07ee0700006ecbc8704ff0b2790fccac18c36c6d", - "sum": "lKvjoL0XAZa7+qswrvdV4TzoTiE2KRB73GNyduq/Ygg=" + "version": "555203ad42bcd4a0a6d14a765bf071bc3247f60e", + "sum": "NMyqYHiET2Vxg5QaMmuApyls/74Ea/fIp9TjJK3UPT0=" }, { "source": { @@ -98,7 +98,7 @@ "subdir": "jsonnet/mixin" } }, - "version": "4acdc01e8bdf0abc8ce1bf87d9c684edb0ab44d0", + "version": "16dfbf448ff439907daaa8c58a3b388e1060106f", "sum": "GQmaVFJwKMiD/P4n3N2LrAZVcwutriWrP8joclDtBYQ=", "name": "prometheus-operator-mixin" }, @@ -109,8 +109,8 @@ "subdir": "jsonnet/prometheus-operator" } }, - "version": "4acdc01e8bdf0abc8ce1bf87d9c684edb0ab44d0", - "sum": "aByD2Nl33aUKhxijXIjT09utrzpE8DRGitrAP9CJWdg=" + "version": "16dfbf448ff439907daaa8c58a3b388e1060106f", + "sum": "jF5A+40DDfjzytGawI3NDOguAMEdbH3t/QFfIOvSe6c=" }, { "source": { @@ -119,7 +119,7 @@ "subdir": "doc/alertmanager-mixin" } }, - "version": "41eb1213bb1c7ce0aa9e6464e297976d9c81cfe5", + "version": "14a265b71024b858dd8186bd6ace3f666f1e934c", "sum": "PsK+V7oETCPKu2gLoPfqY0wwPKH9TzhNj6o2xezjjXc=", "name": "alertmanager" }, @@ -130,7 +130,7 @@ "subdir": "docs/node-mixin" } }, - "version": "c914f0052629e3c99449bdfb4fa7189ce09e77b5", + "version": "1724b28d27ff99fda3143207d1b0a52fa3a70122", "sum": "TwdaTm0Z++diiLyaKAAimmC6hBL7XbrJc0RHhBCpAdU=" }, { @@ -140,7 +140,7 @@ "subdir": "documentation/prometheus-mixin" } }, - "version": "d2f5fdd17eb525cfc49e606744c3004fa93b6948", + "version": "6c008ec56af958debf4123d7cd58a6681d17303d", "sum": "LRx0tbMnoE1p8KEn+i81j2YsA5Sgt3itE5Y6jBf5eOQ=", "name": "prometheus" }, @@ -161,7 +161,7 @@ "subdir": "mixin" } }, - "version": "8da34a1b76a60aadc2cf5020b3db1a2ae6cfc289", + "version": "c88f5a36d0f651b72f09294b8b35500172e52590", "sum": "QIPkur4Hka3BId8ek3OkriAUKphk0mC/NORqJhFgxag=", "name": "thanos-mixin" }, diff --git a/manifests/kubernetesControlPlane-prometheusRule.yaml b/manifests/kubernetesControlPlane-prometheusRule.yaml index d707eb0810edad68a8806c94cb9ee27a70eb577f..10f2b087ae525b600b7a9c6dd47d5c6089d844fb 100644 --- a/manifests/kubernetesControlPlane-prometheusRule.yaml +++ b/manifests/kubernetesControlPlane-prometheusRule.yaml @@ -499,9 +499,9 @@ 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 (cluster, instance, job, namespace) + (sum(rate(rest_client_requests_total{job="apiserver",code=~"5.."}[5m])) by (cluster, instance, job, namespace) / - sum(rate(rest_client_requests_total[5m])) by (cluster, instance, job, namespace)) + sum(rate(rest_client_requests_total{job="apiserver"}[5m])) by (cluster, instance, job, namespace)) > 0.01 for: 15m labels: @@ -679,7 +679,7 @@ 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 (cluster, node) > 2 + sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2 for: 15m labels: severity: warning @@ -1479,17 +1479,17 @@ spec: - name: kubelet.rules rules: - expr: | - histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) labels: quantile: "0.99" record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile - expr: | - histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) labels: quantile: "0.9" record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile - expr: | - histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) labels: quantile: "0.5" record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile diff --git a/manifests/setup/0alertmanagerCustomResourceDefinition.yaml b/manifests/setup/0alertmanagerCustomResourceDefinition.yaml index bb18d5a613081763b0461e76d904f6356c96f252..ae6f1f02b378f6ac37f21c3e32a76169afb590e7 100644 --- a/manifests/setup/0alertmanagerCustomResourceDefinition.yaml +++ b/manifests/setup/0alertmanagerCustomResourceDefinition.yaml @@ -1362,6 +1362,25 @@ spec: they always include EndsAt. pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ type: string + slackApiUrl: + description: The default Slack API URL. + properties: + key: + description: The key of the secret to select from. Must + be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names + TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must + be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic type: object name: description: The name of the AlertmanagerConfig resource which