From 2e241a36343dc9bee5bffc2fa5ab81cb36aa772c Mon Sep 17 00:00:00 2001 From: Dalia Khater Date: Tue, 5 Aug 2025 15:17:56 -0500 Subject: [PATCH 1/2] add mcd_local_unsupported_packages metric from MCO to telemetry --- Documentation/data-collection.md | 6 ++++++ Documentation/deps-versions.md | 5 ++--- assets/admission-webhook/deployment.yaml | 6 +++--- assets/admission-webhook/pod-disruption-budget.yaml | 2 +- assets/admission-webhook/service-account.yaml | 2 +- assets/admission-webhook/service.yaml | 2 +- .../cluster-role-binding.yaml | 2 +- .../prometheus-operator-user-workload/cluster-role.yaml | 2 +- assets/prometheus-operator-user-workload/deployment.yaml | 8 ++++---- .../service-account.yaml | 2 +- .../service-monitor.yaml | 4 ++-- assets/prometheus-operator-user-workload/service.yaml | 2 +- assets/prometheus-operator/cluster-role-binding.yaml | 2 +- assets/prometheus-operator/cluster-role.yaml | 2 +- assets/prometheus-operator/deployment.yaml | 9 ++++----- assets/prometheus-operator/prometheus-rule.yaml | 2 +- assets/prometheus-operator/service-account.yaml | 2 +- assets/prometheus-operator/service-monitor.yaml | 4 ++-- assets/prometheus-operator/service.yaml | 2 +- jsonnet/versions.yaml | 4 ++-- .../0000_50_cluster-monitoring-operator_04-config.yaml | 6 ++++++ 21 files changed, 43 insertions(+), 33 deletions(-) diff --git a/Documentation/data-collection.md b/Documentation/data-collection.md index 4ca77bbfab..c25b635a7e 100644 --- a/Documentation/data-collection.md +++ b/Documentation/data-collection.md @@ -1123,6 +1123,12 @@ data: # os_image_url_override:sum tells whether cluster is using default OS image or has been overridden by user - '{__name__="os_image_url_override:sum"}' # + # owners: (https://github.com/openshift/machine-config-operator/) + # + # node:mcd_local_unsupported_packages:count tracks the number of unsupported, + # locally layered RPM packages on a given node. + - '{__name__="node:mcd_local_unsupported_packages:count"}' + # # owners: (https://github.com/openshift/vmware-vsphere-csi-driver-operator, @openshift/storage) # # cluster:vsphere_topology_tags:max shows how many vSphere topology tag categories are configured. diff --git a/Documentation/deps-versions.md b/Documentation/deps-versions.md index fae5a10591..75f1f45550 100644 --- a/Documentation/deps-versions.md +++ b/Documentation/deps-versions.md @@ -1,8 +1,7 @@ | OCP Version | alertmanager | kubeRbacProxy | kubeStateMetrics | kubernetesMetricsServer | monitoringPlugin | nodeExporter | promLabelProxy | prometheus | prometheusOperator | thanos | |--------------|----------------------------------------------------------------------------------|--------------------------------------------------------------------------|-----------------------------------------------------------------------------|-----------------------------------------------------------------------------------|---------------------------------------------------------------------------|-----------------------------------------------------------------------|---------------------------------------------------------------------------|---------------------------------------------------------------------|------------------------------------------------------------------------------|-----------------------------------------------------------------| -| release-4.22 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.22) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.22) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.22) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.22) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.22) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.22) | [0.12.1](https://github.com/openshift/prom-label-proxy/blob/release-4.22) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.22) | [0.85.0](https://github.com/openshift/prometheus-operator/blob/release-4.22) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.22) | -| release-4.21 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.21) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.21) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.21) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.21) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.21) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.21) | [0.12.1](https://github.com/openshift/prom-label-proxy/blob/release-4.21) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.21) | [0.85.0](https://github.com/openshift/prometheus-operator/blob/release-4.21) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.21) | -| release-4.20 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.20) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.20) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.20) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.20) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.20) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.20) | [0.12.0](https://github.com/openshift/prom-label-proxy/blob/release-4.20) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.20) | [0.85.0](https://github.com/openshift/prometheus-operator/blob/release-4.20) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.20) | +| release-4.21 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.21) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.21) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.21) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.21) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.21) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.21) | [0.12.0](https://github.com/openshift/prom-label-proxy/blob/release-4.21) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.21) | [0.84.1](https://github.com/openshift/prometheus-operator/blob/release-4.21) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.21) | +| release-4.20 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.20) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.20) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.20) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.20) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.20) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.20) | [0.12.0](https://github.com/openshift/prom-label-proxy/blob/release-4.20) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.20) | [0.84.1](https://github.com/openshift/prometheus-operator/blob/release-4.20) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.20) | | release-4.19 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.19) | [0.19.0](https://github.com/openshift/kube-rbac-proxy/blob/release-4.19) | [2.15.0](https://github.com/openshift/kube-state-metrics/blob/release-4.19) | [0.7.2](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.19) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.19) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.19) | [0.11.0](https://github.com/openshift/prom-label-proxy/blob/release-4.19) | [3.2.1](https://github.com/openshift/prometheus/blob/release-4.19) | [0.81.0](https://github.com/openshift/prometheus-operator/blob/release-4.19) | [0.37.2](https://github.com/openshift/thanos/blob/release-4.19) | | release-4.18 | [0.27.0](https://github.com/openshift/prometheus-alertmanager/blob/release-4.18) | [0.18.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.18) | [2.13.0](https://github.com/openshift/kube-state-metrics/blob/release-4.18) | [0.7.2](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.18) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.18) | [1.8.2](https://github.com/openshift/node_exporter/blob/release-4.18) | [0.11.0](https://github.com/openshift/prom-label-proxy/blob/release-4.18) | [2.55.1](https://github.com/openshift/prometheus/blob/release-4.18) | [0.78.2](https://github.com/openshift/prometheus-operator/blob/release-4.18) | [0.36.1](https://github.com/openshift/thanos/blob/release-4.18) | | release-4.17 | [0.27.0](https://github.com/openshift/prometheus-alertmanager/blob/release-4.17) | [0.17.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.17) | [2.13.0](https://github.com/openshift/kube-state-metrics/blob/release-4.17) | [0.7.1](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.17) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.17) | [1.8.2](https://github.com/openshift/node_exporter/blob/release-4.17) | [0.11.0](https://github.com/openshift/prom-label-proxy/blob/release-4.17) | [2.53.1](https://github.com/openshift/prometheus/blob/release-4.17) | [0.75.2](https://github.com/openshift/prometheus-operator/blob/release-4.17) | [0.35.1](https://github.com/openshift/thanos/blob/release-4.17) | diff --git a/assets/admission-webhook/deployment.yaml b/assets/admission-webhook/deployment.yaml index 4436c12067..0faaa50fe8 100644 --- a/assets/admission-webhook/deployment.yaml +++ b/assets/admission-webhook/deployment.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator-admission-webhook namespace: openshift-monitoring spec: @@ -27,7 +27,7 @@ spec: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 spec: affinity: podAntiAffinity: @@ -47,7 +47,7 @@ spec: - --web.key-file=/etc/tls/private/tls.key - --web.tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 - --web.tls-min-version=VersionTLS12 - image: quay.io/prometheus-operator/admission-webhook:v0.85.0 + image: quay.io/prometheus-operator/admission-webhook:v0.84.1 livenessProbe: httpGet: path: /healthz diff --git a/assets/admission-webhook/pod-disruption-budget.yaml b/assets/admission-webhook/pod-disruption-budget.yaml index bd948691a6..226ae21672 100644 --- a/assets/admission-webhook/pod-disruption-budget.yaml +++ b/assets/admission-webhook/pod-disruption-budget.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator-admission-webhook namespace: openshift-monitoring spec: diff --git a/assets/admission-webhook/service-account.yaml b/assets/admission-webhook/service-account.yaml index e1d38d0716..19e38901f9 100644 --- a/assets/admission-webhook/service-account.yaml +++ b/assets/admission-webhook/service-account.yaml @@ -6,6 +6,6 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator-admission-webhook namespace: openshift-monitoring diff --git a/assets/admission-webhook/service.yaml b/assets/admission-webhook/service.yaml index e6c0cfa991..697c43c04e 100644 --- a/assets/admission-webhook/service.yaml +++ b/assets/admission-webhook/service.yaml @@ -8,7 +8,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator-admission-webhook namespace: openshift-monitoring spec: diff --git a/assets/prometheus-operator-user-workload/cluster-role-binding.yaml b/assets/prometheus-operator-user-workload/cluster-role-binding.yaml index d9d5a90ebd..e294a2d65d 100644 --- a/assets/prometheus-operator-user-workload/cluster-role-binding.yaml +++ b/assets/prometheus-operator-user-workload/cluster-role-binding.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-user-workload-operator roleRef: apiGroup: rbac.authorization.k8s.io diff --git a/assets/prometheus-operator-user-workload/cluster-role.yaml b/assets/prometheus-operator-user-workload/cluster-role.yaml index 19b46c52fa..9b9f0656c5 100644 --- a/assets/prometheus-operator-user-workload/cluster-role.yaml +++ b/assets/prometheus-operator-user-workload/cluster-role.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-user-workload-operator rules: - apiGroups: diff --git a/assets/prometheus-operator-user-workload/deployment.yaml b/assets/prometheus-operator-user-workload/deployment.yaml index 2ffc55d73b..7e0b562811 100644 --- a/assets/prometheus-operator-user-workload/deployment.yaml +++ b/assets/prometheus-operator-user-workload/deployment.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-user-workload-monitoring spec: @@ -27,12 +27,12 @@ spec: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 spec: automountServiceAccountToken: true containers: - args: - - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.85.0 + - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.84.1 - --kubelet-endpoints=true - --kubelet-endpointslice=false - --prometheus-instance-namespaces=openshift-user-workload-monitoring @@ -47,7 +47,7 @@ spec: env: - name: GOGC value: "30" - image: quay.io/prometheus-operator/prometheus-operator:v0.85.0 + image: quay.io/prometheus-operator/prometheus-operator:v0.84.1 name: prometheus-operator ports: [] resources: diff --git a/assets/prometheus-operator-user-workload/service-account.yaml b/assets/prometheus-operator-user-workload/service-account.yaml index 398ed6f3a3..345da09c33 100644 --- a/assets/prometheus-operator-user-workload/service-account.yaml +++ b/assets/prometheus-operator-user-workload/service-account.yaml @@ -7,6 +7,6 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-user-workload-monitoring diff --git a/assets/prometheus-operator-user-workload/service-monitor.yaml b/assets/prometheus-operator-user-workload/service-monitor.yaml index 224ad9b2e4..2ffa2b5c2e 100644 --- a/assets/prometheus-operator-user-workload/service-monitor.yaml +++ b/assets/prometheus-operator-user-workload/service-monitor.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-user-workload-monitoring spec: @@ -24,4 +24,4 @@ spec: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 diff --git a/assets/prometheus-operator-user-workload/service.yaml b/assets/prometheus-operator-user-workload/service.yaml index 9e249806d5..73451f8425 100644 --- a/assets/prometheus-operator-user-workload/service.yaml +++ b/assets/prometheus-operator-user-workload/service.yaml @@ -9,7 +9,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-user-workload-monitoring spec: diff --git a/assets/prometheus-operator/cluster-role-binding.yaml b/assets/prometheus-operator/cluster-role-binding.yaml index c18694edea..cbf3c963b4 100644 --- a/assets/prometheus-operator/cluster-role-binding.yaml +++ b/assets/prometheus-operator/cluster-role-binding.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator roleRef: apiGroup: rbac.authorization.k8s.io diff --git a/assets/prometheus-operator/cluster-role.yaml b/assets/prometheus-operator/cluster-role.yaml index 00882d05cf..0e7c3c40f9 100644 --- a/assets/prometheus-operator/cluster-role.yaml +++ b/assets/prometheus-operator/cluster-role.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator rules: - apiGroups: diff --git a/assets/prometheus-operator/deployment.yaml b/assets/prometheus-operator/deployment.yaml index 7ed00be172..127d83effb 100644 --- a/assets/prometheus-operator/deployment.yaml +++ b/assets/prometheus-operator/deployment.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-monitoring spec: @@ -27,16 +27,15 @@ spec: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 spec: automountServiceAccountToken: true containers: - args: - --kubelet-service=kube-system/kubelet - - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.85.0 + - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.84.1 - --kubelet-endpoints=true - --kubelet-endpointslice=false - - --watch-referenced-objects-in-all-namespaces=true - --prometheus-instance-namespaces=openshift-monitoring - --thanos-ruler-instance-namespaces=openshift-monitoring - --alertmanager-instance-namespaces=openshift-monitoring @@ -49,7 +48,7 @@ spec: env: - name: GOGC value: "30" - image: quay.io/prometheus-operator/prometheus-operator:v0.85.0 + image: quay.io/prometheus-operator/prometheus-operator:v0.84.1 name: prometheus-operator ports: [] resources: diff --git a/assets/prometheus-operator/prometheus-rule.yaml b/assets/prometheus-operator/prometheus-rule.yaml index 0dc1fa5465..d09da173d8 100644 --- a/assets/prometheus-operator/prometheus-rule.yaml +++ b/assets/prometheus-operator/prometheus-rule.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 prometheus: k8s role: alert-rules name: prometheus-operator-rules diff --git a/assets/prometheus-operator/service-account.yaml b/assets/prometheus-operator/service-account.yaml index 121fa459ed..331eff60f0 100644 --- a/assets/prometheus-operator/service-account.yaml +++ b/assets/prometheus-operator/service-account.yaml @@ -7,6 +7,6 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-monitoring diff --git a/assets/prometheus-operator/service-monitor.yaml b/assets/prometheus-operator/service-monitor.yaml index 3f46c62f45..049a71f559 100644 --- a/assets/prometheus-operator/service-monitor.yaml +++ b/assets/prometheus-operator/service-monitor.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-monitoring spec: @@ -24,4 +24,4 @@ spec: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 diff --git a/assets/prometheus-operator/service.yaml b/assets/prometheus-operator/service.yaml index 7cdb419341..584735c082 100644 --- a/assets/prometheus-operator/service.yaml +++ b/assets/prometheus-operator/service.yaml @@ -9,7 +9,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.85.0 + app.kubernetes.io/version: 0.84.1 name: prometheus-operator namespace: openshift-monitoring spec: diff --git a/jsonnet/versions.yaml b/jsonnet/versions.yaml index 6e37218915..ce62d4c4d6 100644 --- a/jsonnet/versions.yaml +++ b/jsonnet/versions.yaml @@ -20,8 +20,8 @@ versions: kubernetesMetricsServer: 0.8.0 monitoringPlugin: 1.0.0 nodeExporter: 1.9.1 - promLabelProxy: 0.12.1 + promLabelProxy: 0.12.0 prometheus: 3.5.0 prometheusAdapter: 0.12.0 - prometheusOperator: 0.85.0 + prometheusOperator: 0.84.1 thanos: 0.39.2 diff --git a/manifests/0000_50_cluster-monitoring-operator_04-config.yaml b/manifests/0000_50_cluster-monitoring-operator_04-config.yaml index 7ebdd422d0..d3a2874d01 100644 --- a/manifests/0000_50_cluster-monitoring-operator_04-config.yaml +++ b/manifests/0000_50_cluster-monitoring-operator_04-config.yaml @@ -1115,6 +1115,12 @@ data: # os_image_url_override:sum tells whether cluster is using default OS image or has been overridden by user - '{__name__="os_image_url_override:sum"}' # + # owners: (https://github.com/openshift/machine-config-operator/) + # + # node:mcd_local_unsupported_packages:count tracks the number of unsupported, + # locally layered RPM packages on a given node. + - '{__name__="node:mcd_local_unsupported_packages:count"}' + # # owners: (https://github.com/openshift/vmware-vsphere-csi-driver-operator, @openshift/storage) # # cluster:vsphere_topology_tags:max shows how many vSphere topology tag categories are configured. From cc633915089324b78a584eda6ce8184fe5f4cc32 Mon Sep 17 00:00:00 2001 From: Dalia Khater Date: Mon, 15 Sep 2025 10:53:13 -0500 Subject: [PATCH 2/2] makefile changes --- Documentation/data-collection.md | 8 ++++---- Documentation/deps-versions.md | 5 +++-- Documentation/sample-metrics.md | 2 +- Documentation/telemetry/telemeter_query | 2 +- assets/admission-webhook/deployment.yaml | 6 +++--- assets/admission-webhook/pod-disruption-budget.yaml | 2 +- assets/admission-webhook/service-account.yaml | 2 +- assets/admission-webhook/service.yaml | 2 +- .../cluster-role-binding.yaml | 2 +- .../prometheus-operator-user-workload/cluster-role.yaml | 2 +- assets/prometheus-operator-user-workload/deployment.yaml | 8 ++++---- .../service-account.yaml | 2 +- .../service-monitor.yaml | 4 ++-- assets/prometheus-operator-user-workload/service.yaml | 2 +- assets/prometheus-operator/cluster-role-binding.yaml | 2 +- assets/prometheus-operator/cluster-role.yaml | 2 +- assets/prometheus-operator/deployment.yaml | 9 +++++---- assets/prometheus-operator/prometheus-rule.yaml | 2 +- assets/prometheus-operator/service-account.yaml | 2 +- assets/prometheus-operator/service-monitor.yaml | 4 ++-- assets/prometheus-operator/service.yaml | 2 +- jsonnet/versions.yaml | 4 ++-- .../0000_50_cluster-monitoring-operator_04-config.yaml | 8 ++++---- 23 files changed, 43 insertions(+), 41 deletions(-) diff --git a/Documentation/data-collection.md b/Documentation/data-collection.md index c25b635a7e..cc267cd938 100644 --- a/Documentation/data-collection.md +++ b/Documentation/data-collection.md @@ -1125,10 +1125,10 @@ data: # # owners: (https://github.com/openshift/machine-config-operator/) # - # node:mcd_local_unsupported_packages:count tracks the number of unsupported, - # locally layered RPM packages on a given node. - - '{__name__="node:mcd_local_unsupported_packages:count"}' - # + # cluster:mcd_nodes_with_unsupported_packages:count is the total number of nodes with unsupported packages. + - '{__name__="cluster:mcd_nodes_with_unsupported_packages:count"}' + # cluster:mcd_total_unsupported_packages:sum is the sum of all unsupported packages across all nodes. + - '{__name__="cluster:mcd_total_unsupported_packages:sum"}' # owners: (https://github.com/openshift/vmware-vsphere-csi-driver-operator, @openshift/storage) # # cluster:vsphere_topology_tags:max shows how many vSphere topology tag categories are configured. diff --git a/Documentation/deps-versions.md b/Documentation/deps-versions.md index 75f1f45550..fae5a10591 100644 --- a/Documentation/deps-versions.md +++ b/Documentation/deps-versions.md @@ -1,7 +1,8 @@ | OCP Version | alertmanager | kubeRbacProxy | kubeStateMetrics | kubernetesMetricsServer | monitoringPlugin | nodeExporter | promLabelProxy | prometheus | prometheusOperator | thanos | |--------------|----------------------------------------------------------------------------------|--------------------------------------------------------------------------|-----------------------------------------------------------------------------|-----------------------------------------------------------------------------------|---------------------------------------------------------------------------|-----------------------------------------------------------------------|---------------------------------------------------------------------------|---------------------------------------------------------------------|------------------------------------------------------------------------------|-----------------------------------------------------------------| -| release-4.21 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.21) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.21) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.21) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.21) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.21) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.21) | [0.12.0](https://github.com/openshift/prom-label-proxy/blob/release-4.21) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.21) | [0.84.1](https://github.com/openshift/prometheus-operator/blob/release-4.21) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.21) | -| release-4.20 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.20) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.20) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.20) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.20) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.20) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.20) | [0.12.0](https://github.com/openshift/prom-label-proxy/blob/release-4.20) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.20) | [0.84.1](https://github.com/openshift/prometheus-operator/blob/release-4.20) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.20) | +| release-4.22 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.22) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.22) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.22) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.22) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.22) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.22) | [0.12.1](https://github.com/openshift/prom-label-proxy/blob/release-4.22) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.22) | [0.85.0](https://github.com/openshift/prometheus-operator/blob/release-4.22) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.22) | +| release-4.21 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.21) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.21) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.21) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.21) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.21) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.21) | [0.12.1](https://github.com/openshift/prom-label-proxy/blob/release-4.21) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.21) | [0.85.0](https://github.com/openshift/prometheus-operator/blob/release-4.21) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.21) | +| release-4.20 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.20) | [0.19.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.20) | [2.16.0](https://github.com/openshift/kube-state-metrics/blob/release-4.20) | [0.8.0](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.20) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.20) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.20) | [0.12.0](https://github.com/openshift/prom-label-proxy/blob/release-4.20) | [3.5.0](https://github.com/openshift/prometheus/blob/release-4.20) | [0.85.0](https://github.com/openshift/prometheus-operator/blob/release-4.20) | [0.39.2](https://github.com/openshift/thanos/blob/release-4.20) | | release-4.19 | [0.28.1](https://github.com/openshift/prometheus-alertmanager/blob/release-4.19) | [0.19.0](https://github.com/openshift/kube-rbac-proxy/blob/release-4.19) | [2.15.0](https://github.com/openshift/kube-state-metrics/blob/release-4.19) | [0.7.2](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.19) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.19) | [1.9.1](https://github.com/openshift/node_exporter/blob/release-4.19) | [0.11.0](https://github.com/openshift/prom-label-proxy/blob/release-4.19) | [3.2.1](https://github.com/openshift/prometheus/blob/release-4.19) | [0.81.0](https://github.com/openshift/prometheus-operator/blob/release-4.19) | [0.37.2](https://github.com/openshift/thanos/blob/release-4.19) | | release-4.18 | [0.27.0](https://github.com/openshift/prometheus-alertmanager/blob/release-4.18) | [0.18.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.18) | [2.13.0](https://github.com/openshift/kube-state-metrics/blob/release-4.18) | [0.7.2](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.18) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.18) | [1.8.2](https://github.com/openshift/node_exporter/blob/release-4.18) | [0.11.0](https://github.com/openshift/prom-label-proxy/blob/release-4.18) | [2.55.1](https://github.com/openshift/prometheus/blob/release-4.18) | [0.78.2](https://github.com/openshift/prometheus-operator/blob/release-4.18) | [0.36.1](https://github.com/openshift/thanos/blob/release-4.18) | | release-4.17 | [0.27.0](https://github.com/openshift/prometheus-alertmanager/blob/release-4.17) | [0.17.1](https://github.com/openshift/kube-rbac-proxy/blob/release-4.17) | [2.13.0](https://github.com/openshift/kube-state-metrics/blob/release-4.17) | [0.7.1](https://github.com/openshift/kubernetes-metrics-server/blob/release-4.17) | [1.0.0](https://github.com/openshift/monitoring-plugin/blob/release-4.17) | [1.8.2](https://github.com/openshift/node_exporter/blob/release-4.17) | [0.11.0](https://github.com/openshift/prom-label-proxy/blob/release-4.17) | [2.53.1](https://github.com/openshift/prometheus/blob/release-4.17) | [0.75.2](https://github.com/openshift/prometheus-operator/blob/release-4.17) | [0.35.1](https://github.com/openshift/thanos/blob/release-4.17) | diff --git a/Documentation/sample-metrics.md b/Documentation/sample-metrics.md index cc0fdd9933..2e6b80c15b 100644 --- a/Documentation/sample-metrics.md +++ b/Documentation/sample-metrics.md @@ -13,7 +13,7 @@ return the full set of metrics that the Telemeter client captures: [embedmd]:# (telemetry/telemeter_query txt) ```txt -{__name__=~"cluster:usage:.*|count:up0|count:up1|cluster_version|cluster_version_available_updates|cluster_version_capability|cluster_operator_up|cluster_operator_conditions|cluster_version_payload|cluster_installer|cluster_infrastructure_provider|cluster_feature_set|instance:etcd_object_counts:sum|ALERTS|code:apiserver_request_total:rate:sum|cluster:capacity_cpu_cores:sum|cluster:capacity_memory_bytes:sum|cluster:cpu_usage_cores:sum|cluster:memory_usage_bytes:sum|openshift:cpu_usage_cores:sum|openshift:memory_usage_bytes:sum|workload:cpu_usage_cores:sum|workload:memory_usage_bytes:sum|cluster:virt_platform_nodes:sum|cluster:node_instance_type_count:sum|cnv:vmi_status_running:count|cnv_abnormal|cluster:vmi_request_cpu_cores:sum|node_role_os_version_machine:cpu_capacity_cores:sum|node_role_os_version_machine:cpu_capacity_sockets:sum|subscription_sync_total|olm_resolution_duration_seconds|csv_succeeded|csv_abnormal|cluster:kube_persistentvolumeclaim_resource_requests_storage_bytes:provisioner:sum|cluster:kubelet_volume_stats_used_bytes:provisioner:sum|ceph_cluster_total_bytes|ceph_cluster_total_used_raw_bytes|ceph_health_status|odf_system_raw_capacity_total_bytes|odf_system_raw_capacity_used_bytes|odf_system_health_status|job:ceph_osd_metadata:count|job:kube_pv:count|job:odf_system_pvs:count|job:ceph_pools_iops:total|job:ceph_pools_iops_bytes:total|job:ceph_versions_running:count|job:noobaa_total_unhealthy_buckets:sum|job:noobaa_bucket_count:sum|job:noobaa_total_object_count:sum|odf_system_bucket_count|odf_system_objects_total|noobaa_accounts_num|noobaa_total_usage|console_url|cluster:console_auth_login_requests_total:sum|cluster:console_auth_login_successes_total:sum|cluster:console_auth_login_failures_total:sum|cluster:console_auth_logout_requests_total:sum|cluster:console_usage_users:max|cluster:console_plugins_info:max|cluster:console_customization_perspectives_info:max|cluster:ovnkube_controller_egress_routing_via_host:max|cluster:ovnkube_controller_admin_network_policies_db_objects:max|cluster:ovnkube_controller_baseline_admin_network_policies_db_objects:max|cluster:ovnkube_controller_admin_network_policies_rules:max|cluster:ovnkube_controller_baseline_admin_network_policies_rules:max|cluster:network_attachment_definition_instances:max|cluster:network_attachment_definition_enabled_instance_up:max|cluster:ingress_controller_aws_nlb_active:sum|cluster:route_metrics_controller_routes_per_shard:min|cluster:route_metrics_controller_routes_per_shard:max|cluster:route_metrics_controller_routes_per_shard:avg|cluster:route_metrics_controller_routes_per_shard:median|cluster:openshift_route_info:tls_termination:sum|insightsclient_request_send_total|cam_app_workload_migrations|cluster:apiserver_current_inflight_requests:sum:max_over_time:2m|cluster:alertmanager_integrations:max|cluster:telemetry_selected_series:count|openshift:prometheus_tsdb_head_series:sum|openshift:prometheus_tsdb_head_samples_appended_total:sum|monitoring:container_memory_working_set_bytes:sum|namespace_job:scrape_series_added:topk3_sum1h|namespace_job:scrape_samples_post_metric_relabeling:topk3|monitoring:haproxy_server_http_responses_total:sum|profile:cluster_monitoring_operator_collection_profile:max|vendor_model:node_accelerator_cards:sum|rhmi_status|status:upgrading:version:rhoam_state:max|state:rhoam_critical_alerts:max|state:rhoam_warning_alerts:max|rhoam_7d_slo_percentile:max|rhoam_7d_slo_remaining_error_budget:max|cluster_legacy_scheduler_policy|cluster_master_schedulable|che_workspace_status|che_workspace_started_total|che_workspace_failure_total|che_workspace_start_time_seconds_sum|che_workspace_start_time_seconds_count|cco_credentials_mode|cluster:kube_persistentvolume_plugin_type_counts:sum|acm_managed_cluster_info|acm_managed_cluster_worker_cores:max|acm_console_page_count:sum|cluster:vsphere_vcenter_info:sum|cluster:vsphere_esxi_version_total:sum|cluster:vsphere_node_hw_version_total:sum|openshift:build_by_strategy:sum|rhods_aggregate_availability|rhods_total_users|instance:etcd_disk_wal_fsync_duration_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_bytes:sum|instance:etcd_network_peer_round_trip_time_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_use_in_bytes:sum|instance:etcd_disk_backend_commit_duration_seconds:histogram_quantile|jaeger_operator_instances_storage_types|jaeger_operator_instances_strategies|jaeger_operator_instances_agent_strategies|type:tempo_operator_tempostack_storage_backend:sum|state:tempo_operator_tempostack_managed:sum|type:tempo_operator_tempostack_multi_tenancy:sum|enabled:tempo_operator_tempostack_jaeger_ui:sum|type:opentelemetry_collector_receivers:sum|type:opentelemetry_collector_exporters:sum|type:opentelemetry_collector_processors:sum|type:opentelemetry_collector_extensions:sum|type:opentelemetry_collector_connectors:sum|type:opentelemetry_collector_info:sum|appsvcs:cores_by_product:sum|nto_custom_profiles:count|openshift_csi_share_configmap|openshift_csi_share_secret|openshift_csi_share_mount_failures_total|openshift_csi_share_mount_requests_total|eo_es_storage_info|eo_es_redundancy_policy_info|eo_es_defined_delete_namespaces_total|eo_es_misconfigured_memory_resources_info|cluster:eo_es_data_nodes_total:max|cluster:eo_es_documents_created_total:sum|cluster:eo_es_documents_deleted_total:sum|pod:eo_es_shards_total:max|eo_es_cluster_management_state_info|imageregistry:imagestreamtags_count:sum|imageregistry:operations_count:sum|log_logging_info|log_collector_error_count_total|log_forwarder_pipeline_info|log_forwarder_input_info|log_forwarder_output_info|cluster:log_collected_bytes_total:sum|cluster:log_logged_bytes_total:sum|openshift_logging:log_forwarder_pipelines:sum|openshift_logging:log_forwarders:sum|openshift_logging:log_forwarder_input_type:sum|openshift_logging:log_forwarder_output_type:sum|openshift_logging:vector_component_received_bytes_total:rate5m|cluster:kata_monitor_running_shim_count:sum|platform:hypershift_hostedclusters:max|platform:hypershift_nodepools:max|cluster_name:hypershift_nodepools_size:sum|cluster_name:hypershift_nodepools_available_replicas:sum|namespace:noobaa_unhealthy_bucket_claims:max|namespace:noobaa_buckets_claims:max|namespace:noobaa_unhealthy_namespace_resources:max|namespace:noobaa_namespace_resources:max|namespace:noobaa_unhealthy_namespace_buckets:max|namespace:noobaa_namespace_buckets:max|namespace:noobaa_accounts:max|namespace:noobaa_usage:max|namespace:noobaa_system_health_status:max|ocs_advanced_feature_usage|os_image_url_override:sum|cluster:vsphere_topology_tags:max|cluster:vsphere_infrastructure_failure_domains:max|apiserver_list_watch_request_success_total:rate:sum|rhacs:telemetry:rox_central_info|rhacs:telemetry:rox_central_secured_clusters|rhacs:telemetry:rox_central_secured_nodes|rhacs:telemetry:rox_central_secured_vcpus|rhacs:telemetry:rox_sensor_info|cluster:volume_manager_selinux_pod_context_mismatch_total|cluster:volume_manager_selinux_volume_context_mismatch_warnings_total|cluster:volume_manager_selinux_volume_context_mismatch_errors_total|cluster:volume_manager_selinux_volumes_admitted_total|ols:provider_model_configuration|ols:rest_api_query_calls_total:2xx|ols:rest_api_query_calls_total:4xx|ols:rest_api_query_calls_total:5xx|openshift:openshift_network_operator_ipsec_state:info|cluster:health:group_severity:count|cluster:controlplane_topology:info|cluster:infrastructure_topology:info|cluster:selinux_warning_controller_selinux_volume_conflict:count",action=~"Pass|Allow|Deny|Allow|Deny|",alertstate=~"firing|",direction=~"Ingress|Egress|Ingress|Egress|",enabled=~"true|false|",mode=~"HighlyAvailable|HighlyAvailableArbiter|SingleReplica|DualReplica|External|HighlyAvailable|SingleReplica|",page=~"overview-classic|overview-fleet|search|search-details|clusters|application|governance|",quantile=~"0.99|0.99|0.99|",reason=~"memory_working_set_delta_from_request|memory_rss_delta_from_request|",severity=~"critical|warning|info|none|critical|warning|info|none|",state=~"Managed|Unmanaged|",system_type=~"OCS|OCS|",system_vendor=~"Red Hat|Red Hat|",table_name=~"ACL|Address_Set|ACL|Address_Set|",type=~"azure|gcs|s3|static|openshift|disabled|jaeger|hostmetrics|opencensus|prometheus|zipkin|kafka|filelog|journald|k8sevents|kubeletstats|k8scluster|k8sobjects|otlp|debug|logging|otlp|otlphttp|prometheus|lokiexporter|kafka|awscloudwatchlogs|loadbalancing|batch|memorylimiter|attributes|resource|span|k8sattributes|resourcedetection|filter|routing|cumulativetodelta|groupbyattrs|zpages|ballast|memorylimiter|jaegerremotesampling|healthcheck|pprof|oauth2clientauth|oidcauth|bearertokenauth|filestorage|spanmetrics|forward|deployment|daemonset|sidecar|statefulset|",vendor=~"NVIDIA|AMD|GAUDI|INTEL|QUALCOMM|Marvell|Mellanox|",verb=~"LIST|WATCH|"} +{__name__=~"cluster:usage:.*|count:up0|count:up1|cluster_version|cluster_version_available_updates|cluster_version_capability|cluster_operator_up|cluster_operator_conditions|cluster_version_payload|cluster_installer|cluster_infrastructure_provider|cluster_feature_set|instance:etcd_object_counts:sum|ALERTS|code:apiserver_request_total:rate:sum|cluster:capacity_cpu_cores:sum|cluster:capacity_memory_bytes:sum|cluster:cpu_usage_cores:sum|cluster:memory_usage_bytes:sum|openshift:cpu_usage_cores:sum|openshift:memory_usage_bytes:sum|workload:cpu_usage_cores:sum|workload:memory_usage_bytes:sum|cluster:virt_platform_nodes:sum|cluster:node_instance_type_count:sum|cnv:vmi_status_running:count|cnv_abnormal|cluster:vmi_request_cpu_cores:sum|node_role_os_version_machine:cpu_capacity_cores:sum|node_role_os_version_machine:cpu_capacity_sockets:sum|subscription_sync_total|olm_resolution_duration_seconds|csv_succeeded|csv_abnormal|cluster:kube_persistentvolumeclaim_resource_requests_storage_bytes:provisioner:sum|cluster:kubelet_volume_stats_used_bytes:provisioner:sum|ceph_cluster_total_bytes|ceph_cluster_total_used_raw_bytes|ceph_health_status|odf_system_raw_capacity_total_bytes|odf_system_raw_capacity_used_bytes|odf_system_health_status|job:ceph_osd_metadata:count|job:kube_pv:count|job:odf_system_pvs:count|job:ceph_pools_iops:total|job:ceph_pools_iops_bytes:total|job:ceph_versions_running:count|job:noobaa_total_unhealthy_buckets:sum|job:noobaa_bucket_count:sum|job:noobaa_total_object_count:sum|odf_system_bucket_count|odf_system_objects_total|noobaa_accounts_num|noobaa_total_usage|console_url|cluster:console_auth_login_requests_total:sum|cluster:console_auth_login_successes_total:sum|cluster:console_auth_login_failures_total:sum|cluster:console_auth_logout_requests_total:sum|cluster:console_usage_users:max|cluster:console_plugins_info:max|cluster:console_customization_perspectives_info:max|cluster:ovnkube_controller_egress_routing_via_host:max|cluster:ovnkube_controller_admin_network_policies_db_objects:max|cluster:ovnkube_controller_baseline_admin_network_policies_db_objects:max|cluster:ovnkube_controller_admin_network_policies_rules:max|cluster:ovnkube_controller_baseline_admin_network_policies_rules:max|cluster:network_attachment_definition_instances:max|cluster:network_attachment_definition_enabled_instance_up:max|cluster:ingress_controller_aws_nlb_active:sum|cluster:route_metrics_controller_routes_per_shard:min|cluster:route_metrics_controller_routes_per_shard:max|cluster:route_metrics_controller_routes_per_shard:avg|cluster:route_metrics_controller_routes_per_shard:median|cluster:openshift_route_info:tls_termination:sum|insightsclient_request_send_total|cam_app_workload_migrations|cluster:apiserver_current_inflight_requests:sum:max_over_time:2m|cluster:alertmanager_integrations:max|cluster:telemetry_selected_series:count|openshift:prometheus_tsdb_head_series:sum|openshift:prometheus_tsdb_head_samples_appended_total:sum|monitoring:container_memory_working_set_bytes:sum|namespace_job:scrape_series_added:topk3_sum1h|namespace_job:scrape_samples_post_metric_relabeling:topk3|monitoring:haproxy_server_http_responses_total:sum|profile:cluster_monitoring_operator_collection_profile:max|vendor_model:node_accelerator_cards:sum|rhmi_status|status:upgrading:version:rhoam_state:max|state:rhoam_critical_alerts:max|state:rhoam_warning_alerts:max|rhoam_7d_slo_percentile:max|rhoam_7d_slo_remaining_error_budget:max|cluster_legacy_scheduler_policy|cluster_master_schedulable|che_workspace_status|che_workspace_started_total|che_workspace_failure_total|che_workspace_start_time_seconds_sum|che_workspace_start_time_seconds_count|cco_credentials_mode|cluster:kube_persistentvolume_plugin_type_counts:sum|acm_managed_cluster_info|acm_managed_cluster_worker_cores:max|acm_console_page_count:sum|cluster:vsphere_vcenter_info:sum|cluster:vsphere_esxi_version_total:sum|cluster:vsphere_node_hw_version_total:sum|openshift:build_by_strategy:sum|rhods_aggregate_availability|rhods_total_users|instance:etcd_disk_wal_fsync_duration_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_bytes:sum|instance:etcd_network_peer_round_trip_time_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_use_in_bytes:sum|instance:etcd_disk_backend_commit_duration_seconds:histogram_quantile|jaeger_operator_instances_storage_types|jaeger_operator_instances_strategies|jaeger_operator_instances_agent_strategies|type:tempo_operator_tempostack_storage_backend:sum|state:tempo_operator_tempostack_managed:sum|type:tempo_operator_tempostack_multi_tenancy:sum|enabled:tempo_operator_tempostack_jaeger_ui:sum|type:opentelemetry_collector_receivers:sum|type:opentelemetry_collector_exporters:sum|type:opentelemetry_collector_processors:sum|type:opentelemetry_collector_extensions:sum|type:opentelemetry_collector_connectors:sum|type:opentelemetry_collector_info:sum|appsvcs:cores_by_product:sum|nto_custom_profiles:count|openshift_csi_share_configmap|openshift_csi_share_secret|openshift_csi_share_mount_failures_total|openshift_csi_share_mount_requests_total|eo_es_storage_info|eo_es_redundancy_policy_info|eo_es_defined_delete_namespaces_total|eo_es_misconfigured_memory_resources_info|cluster:eo_es_data_nodes_total:max|cluster:eo_es_documents_created_total:sum|cluster:eo_es_documents_deleted_total:sum|pod:eo_es_shards_total:max|eo_es_cluster_management_state_info|imageregistry:imagestreamtags_count:sum|imageregistry:operations_count:sum|log_logging_info|log_collector_error_count_total|log_forwarder_pipeline_info|log_forwarder_input_info|log_forwarder_output_info|cluster:log_collected_bytes_total:sum|cluster:log_logged_bytes_total:sum|openshift_logging:log_forwarder_pipelines:sum|openshift_logging:log_forwarders:sum|openshift_logging:log_forwarder_input_type:sum|openshift_logging:log_forwarder_output_type:sum|openshift_logging:vector_component_received_bytes_total:rate5m|cluster:kata_monitor_running_shim_count:sum|platform:hypershift_hostedclusters:max|platform:hypershift_nodepools:max|cluster_name:hypershift_nodepools_size:sum|cluster_name:hypershift_nodepools_available_replicas:sum|namespace:noobaa_unhealthy_bucket_claims:max|namespace:noobaa_buckets_claims:max|namespace:noobaa_unhealthy_namespace_resources:max|namespace:noobaa_namespace_resources:max|namespace:noobaa_unhealthy_namespace_buckets:max|namespace:noobaa_namespace_buckets:max|namespace:noobaa_accounts:max|namespace:noobaa_usage:max|namespace:noobaa_system_health_status:max|ocs_advanced_feature_usage|os_image_url_override:sum|cluster:mcd_nodes_with_unsupported_packages:count|cluster:mcd_total_unsupported_packages:sum|cluster:vsphere_topology_tags:max|cluster:vsphere_infrastructure_failure_domains:max|apiserver_list_watch_request_success_total:rate:sum|rhacs:telemetry:rox_central_info|rhacs:telemetry:rox_central_secured_clusters|rhacs:telemetry:rox_central_secured_nodes|rhacs:telemetry:rox_central_secured_vcpus|rhacs:telemetry:rox_sensor_info|cluster:volume_manager_selinux_pod_context_mismatch_total|cluster:volume_manager_selinux_volume_context_mismatch_warnings_total|cluster:volume_manager_selinux_volume_context_mismatch_errors_total|cluster:volume_manager_selinux_volumes_admitted_total|ols:provider_model_configuration|ols:rest_api_query_calls_total:2xx|ols:rest_api_query_calls_total:4xx|ols:rest_api_query_calls_total:5xx|openshift:openshift_network_operator_ipsec_state:info|cluster:health:group_severity:count|cluster:controlplane_topology:info|cluster:infrastructure_topology:info|cluster:selinux_warning_controller_selinux_volume_conflict:count",action=~"Pass|Allow|Deny|Allow|Deny|",alertstate=~"firing|",direction=~"Ingress|Egress|Ingress|Egress|",enabled=~"true|false|",mode=~"HighlyAvailable|HighlyAvailableArbiter|SingleReplica|DualReplica|External|HighlyAvailable|SingleReplica|",page=~"overview-classic|overview-fleet|search|search-details|clusters|application|governance|",quantile=~"0.99|0.99|0.99|",reason=~"memory_working_set_delta_from_request|memory_rss_delta_from_request|",severity=~"critical|warning|info|none|critical|warning|info|none|",state=~"Managed|Unmanaged|",system_type=~"OCS|OCS|",system_vendor=~"Red Hat|Red Hat|",table_name=~"ACL|Address_Set|ACL|Address_Set|",type=~"azure|gcs|s3|static|openshift|disabled|jaeger|hostmetrics|opencensus|prometheus|zipkin|kafka|filelog|journald|k8sevents|kubeletstats|k8scluster|k8sobjects|otlp|debug|logging|otlp|otlphttp|prometheus|lokiexporter|kafka|awscloudwatchlogs|loadbalancing|batch|memorylimiter|attributes|resource|span|k8sattributes|resourcedetection|filter|routing|cumulativetodelta|groupbyattrs|zpages|ballast|memorylimiter|jaegerremotesampling|healthcheck|pprof|oauth2clientauth|oidcauth|bearertokenauth|filestorage|spanmetrics|forward|deployment|daemonset|sidecar|statefulset|",vendor=~"NVIDIA|AMD|GAUDI|INTEL|QUALCOMM|Marvell|Mellanox|",verb=~"LIST|WATCH|"} ``` For reference, here is an example response produced by a running OpenShift cluster: diff --git a/Documentation/telemetry/telemeter_query b/Documentation/telemetry/telemeter_query index 0c3e3ff2dc..43fc36aee0 100644 --- a/Documentation/telemetry/telemeter_query +++ b/Documentation/telemetry/telemeter_query @@ -1 +1 @@ -{__name__=~"cluster:usage:.*|count:up0|count:up1|cluster_version|cluster_version_available_updates|cluster_version_capability|cluster_operator_up|cluster_operator_conditions|cluster_version_payload|cluster_installer|cluster_infrastructure_provider|cluster_feature_set|instance:etcd_object_counts:sum|ALERTS|code:apiserver_request_total:rate:sum|cluster:capacity_cpu_cores:sum|cluster:capacity_memory_bytes:sum|cluster:cpu_usage_cores:sum|cluster:memory_usage_bytes:sum|openshift:cpu_usage_cores:sum|openshift:memory_usage_bytes:sum|workload:cpu_usage_cores:sum|workload:memory_usage_bytes:sum|cluster:virt_platform_nodes:sum|cluster:node_instance_type_count:sum|cnv:vmi_status_running:count|cnv_abnormal|cluster:vmi_request_cpu_cores:sum|node_role_os_version_machine:cpu_capacity_cores:sum|node_role_os_version_machine:cpu_capacity_sockets:sum|subscription_sync_total|olm_resolution_duration_seconds|csv_succeeded|csv_abnormal|cluster:kube_persistentvolumeclaim_resource_requests_storage_bytes:provisioner:sum|cluster:kubelet_volume_stats_used_bytes:provisioner:sum|ceph_cluster_total_bytes|ceph_cluster_total_used_raw_bytes|ceph_health_status|odf_system_raw_capacity_total_bytes|odf_system_raw_capacity_used_bytes|odf_system_health_status|job:ceph_osd_metadata:count|job:kube_pv:count|job:odf_system_pvs:count|job:ceph_pools_iops:total|job:ceph_pools_iops_bytes:total|job:ceph_versions_running:count|job:noobaa_total_unhealthy_buckets:sum|job:noobaa_bucket_count:sum|job:noobaa_total_object_count:sum|odf_system_bucket_count|odf_system_objects_total|noobaa_accounts_num|noobaa_total_usage|console_url|cluster:console_auth_login_requests_total:sum|cluster:console_auth_login_successes_total:sum|cluster:console_auth_login_failures_total:sum|cluster:console_auth_logout_requests_total:sum|cluster:console_usage_users:max|cluster:console_plugins_info:max|cluster:console_customization_perspectives_info:max|cluster:ovnkube_controller_egress_routing_via_host:max|cluster:ovnkube_controller_admin_network_policies_db_objects:max|cluster:ovnkube_controller_baseline_admin_network_policies_db_objects:max|cluster:ovnkube_controller_admin_network_policies_rules:max|cluster:ovnkube_controller_baseline_admin_network_policies_rules:max|cluster:network_attachment_definition_instances:max|cluster:network_attachment_definition_enabled_instance_up:max|cluster:ingress_controller_aws_nlb_active:sum|cluster:route_metrics_controller_routes_per_shard:min|cluster:route_metrics_controller_routes_per_shard:max|cluster:route_metrics_controller_routes_per_shard:avg|cluster:route_metrics_controller_routes_per_shard:median|cluster:openshift_route_info:tls_termination:sum|insightsclient_request_send_total|cam_app_workload_migrations|cluster:apiserver_current_inflight_requests:sum:max_over_time:2m|cluster:alertmanager_integrations:max|cluster:telemetry_selected_series:count|openshift:prometheus_tsdb_head_series:sum|openshift:prometheus_tsdb_head_samples_appended_total:sum|monitoring:container_memory_working_set_bytes:sum|namespace_job:scrape_series_added:topk3_sum1h|namespace_job:scrape_samples_post_metric_relabeling:topk3|monitoring:haproxy_server_http_responses_total:sum|profile:cluster_monitoring_operator_collection_profile:max|vendor_model:node_accelerator_cards:sum|rhmi_status|status:upgrading:version:rhoam_state:max|state:rhoam_critical_alerts:max|state:rhoam_warning_alerts:max|rhoam_7d_slo_percentile:max|rhoam_7d_slo_remaining_error_budget:max|cluster_legacy_scheduler_policy|cluster_master_schedulable|che_workspace_status|che_workspace_started_total|che_workspace_failure_total|che_workspace_start_time_seconds_sum|che_workspace_start_time_seconds_count|cco_credentials_mode|cluster:kube_persistentvolume_plugin_type_counts:sum|acm_managed_cluster_info|acm_managed_cluster_worker_cores:max|acm_console_page_count:sum|cluster:vsphere_vcenter_info:sum|cluster:vsphere_esxi_version_total:sum|cluster:vsphere_node_hw_version_total:sum|openshift:build_by_strategy:sum|rhods_aggregate_availability|rhods_total_users|instance:etcd_disk_wal_fsync_duration_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_bytes:sum|instance:etcd_network_peer_round_trip_time_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_use_in_bytes:sum|instance:etcd_disk_backend_commit_duration_seconds:histogram_quantile|jaeger_operator_instances_storage_types|jaeger_operator_instances_strategies|jaeger_operator_instances_agent_strategies|type:tempo_operator_tempostack_storage_backend:sum|state:tempo_operator_tempostack_managed:sum|type:tempo_operator_tempostack_multi_tenancy:sum|enabled:tempo_operator_tempostack_jaeger_ui:sum|type:opentelemetry_collector_receivers:sum|type:opentelemetry_collector_exporters:sum|type:opentelemetry_collector_processors:sum|type:opentelemetry_collector_extensions:sum|type:opentelemetry_collector_connectors:sum|type:opentelemetry_collector_info:sum|appsvcs:cores_by_product:sum|nto_custom_profiles:count|openshift_csi_share_configmap|openshift_csi_share_secret|openshift_csi_share_mount_failures_total|openshift_csi_share_mount_requests_total|eo_es_storage_info|eo_es_redundancy_policy_info|eo_es_defined_delete_namespaces_total|eo_es_misconfigured_memory_resources_info|cluster:eo_es_data_nodes_total:max|cluster:eo_es_documents_created_total:sum|cluster:eo_es_documents_deleted_total:sum|pod:eo_es_shards_total:max|eo_es_cluster_management_state_info|imageregistry:imagestreamtags_count:sum|imageregistry:operations_count:sum|log_logging_info|log_collector_error_count_total|log_forwarder_pipeline_info|log_forwarder_input_info|log_forwarder_output_info|cluster:log_collected_bytes_total:sum|cluster:log_logged_bytes_total:sum|openshift_logging:log_forwarder_pipelines:sum|openshift_logging:log_forwarders:sum|openshift_logging:log_forwarder_input_type:sum|openshift_logging:log_forwarder_output_type:sum|openshift_logging:vector_component_received_bytes_total:rate5m|cluster:kata_monitor_running_shim_count:sum|platform:hypershift_hostedclusters:max|platform:hypershift_nodepools:max|cluster_name:hypershift_nodepools_size:sum|cluster_name:hypershift_nodepools_available_replicas:sum|namespace:noobaa_unhealthy_bucket_claims:max|namespace:noobaa_buckets_claims:max|namespace:noobaa_unhealthy_namespace_resources:max|namespace:noobaa_namespace_resources:max|namespace:noobaa_unhealthy_namespace_buckets:max|namespace:noobaa_namespace_buckets:max|namespace:noobaa_accounts:max|namespace:noobaa_usage:max|namespace:noobaa_system_health_status:max|ocs_advanced_feature_usage|os_image_url_override:sum|cluster:vsphere_topology_tags:max|cluster:vsphere_infrastructure_failure_domains:max|apiserver_list_watch_request_success_total:rate:sum|rhacs:telemetry:rox_central_info|rhacs:telemetry:rox_central_secured_clusters|rhacs:telemetry:rox_central_secured_nodes|rhacs:telemetry:rox_central_secured_vcpus|rhacs:telemetry:rox_sensor_info|cluster:volume_manager_selinux_pod_context_mismatch_total|cluster:volume_manager_selinux_volume_context_mismatch_warnings_total|cluster:volume_manager_selinux_volume_context_mismatch_errors_total|cluster:volume_manager_selinux_volumes_admitted_total|ols:provider_model_configuration|ols:rest_api_query_calls_total:2xx|ols:rest_api_query_calls_total:4xx|ols:rest_api_query_calls_total:5xx|openshift:openshift_network_operator_ipsec_state:info|cluster:health:group_severity:count|cluster:controlplane_topology:info|cluster:infrastructure_topology:info|cluster:selinux_warning_controller_selinux_volume_conflict:count",action=~"Pass|Allow|Deny|Allow|Deny|",alertstate=~"firing|",direction=~"Ingress|Egress|Ingress|Egress|",enabled=~"true|false|",mode=~"HighlyAvailable|HighlyAvailableArbiter|SingleReplica|DualReplica|External|HighlyAvailable|SingleReplica|",page=~"overview-classic|overview-fleet|search|search-details|clusters|application|governance|",quantile=~"0.99|0.99|0.99|",reason=~"memory_working_set_delta_from_request|memory_rss_delta_from_request|",severity=~"critical|warning|info|none|critical|warning|info|none|",state=~"Managed|Unmanaged|",system_type=~"OCS|OCS|",system_vendor=~"Red Hat|Red Hat|",table_name=~"ACL|Address_Set|ACL|Address_Set|",type=~"azure|gcs|s3|static|openshift|disabled|jaeger|hostmetrics|opencensus|prometheus|zipkin|kafka|filelog|journald|k8sevents|kubeletstats|k8scluster|k8sobjects|otlp|debug|logging|otlp|otlphttp|prometheus|lokiexporter|kafka|awscloudwatchlogs|loadbalancing|batch|memorylimiter|attributes|resource|span|k8sattributes|resourcedetection|filter|routing|cumulativetodelta|groupbyattrs|zpages|ballast|memorylimiter|jaegerremotesampling|healthcheck|pprof|oauth2clientauth|oidcauth|bearertokenauth|filestorage|spanmetrics|forward|deployment|daemonset|sidecar|statefulset|",vendor=~"NVIDIA|AMD|GAUDI|INTEL|QUALCOMM|Marvell|Mellanox|",verb=~"LIST|WATCH|"} +{__name__=~"cluster:usage:.*|count:up0|count:up1|cluster_version|cluster_version_available_updates|cluster_version_capability|cluster_operator_up|cluster_operator_conditions|cluster_version_payload|cluster_installer|cluster_infrastructure_provider|cluster_feature_set|instance:etcd_object_counts:sum|ALERTS|code:apiserver_request_total:rate:sum|cluster:capacity_cpu_cores:sum|cluster:capacity_memory_bytes:sum|cluster:cpu_usage_cores:sum|cluster:memory_usage_bytes:sum|openshift:cpu_usage_cores:sum|openshift:memory_usage_bytes:sum|workload:cpu_usage_cores:sum|workload:memory_usage_bytes:sum|cluster:virt_platform_nodes:sum|cluster:node_instance_type_count:sum|cnv:vmi_status_running:count|cnv_abnormal|cluster:vmi_request_cpu_cores:sum|node_role_os_version_machine:cpu_capacity_cores:sum|node_role_os_version_machine:cpu_capacity_sockets:sum|subscription_sync_total|olm_resolution_duration_seconds|csv_succeeded|csv_abnormal|cluster:kube_persistentvolumeclaim_resource_requests_storage_bytes:provisioner:sum|cluster:kubelet_volume_stats_used_bytes:provisioner:sum|ceph_cluster_total_bytes|ceph_cluster_total_used_raw_bytes|ceph_health_status|odf_system_raw_capacity_total_bytes|odf_system_raw_capacity_used_bytes|odf_system_health_status|job:ceph_osd_metadata:count|job:kube_pv:count|job:odf_system_pvs:count|job:ceph_pools_iops:total|job:ceph_pools_iops_bytes:total|job:ceph_versions_running:count|job:noobaa_total_unhealthy_buckets:sum|job:noobaa_bucket_count:sum|job:noobaa_total_object_count:sum|odf_system_bucket_count|odf_system_objects_total|noobaa_accounts_num|noobaa_total_usage|console_url|cluster:console_auth_login_requests_total:sum|cluster:console_auth_login_successes_total:sum|cluster:console_auth_login_failures_total:sum|cluster:console_auth_logout_requests_total:sum|cluster:console_usage_users:max|cluster:console_plugins_info:max|cluster:console_customization_perspectives_info:max|cluster:ovnkube_controller_egress_routing_via_host:max|cluster:ovnkube_controller_admin_network_policies_db_objects:max|cluster:ovnkube_controller_baseline_admin_network_policies_db_objects:max|cluster:ovnkube_controller_admin_network_policies_rules:max|cluster:ovnkube_controller_baseline_admin_network_policies_rules:max|cluster:network_attachment_definition_instances:max|cluster:network_attachment_definition_enabled_instance_up:max|cluster:ingress_controller_aws_nlb_active:sum|cluster:route_metrics_controller_routes_per_shard:min|cluster:route_metrics_controller_routes_per_shard:max|cluster:route_metrics_controller_routes_per_shard:avg|cluster:route_metrics_controller_routes_per_shard:median|cluster:openshift_route_info:tls_termination:sum|insightsclient_request_send_total|cam_app_workload_migrations|cluster:apiserver_current_inflight_requests:sum:max_over_time:2m|cluster:alertmanager_integrations:max|cluster:telemetry_selected_series:count|openshift:prometheus_tsdb_head_series:sum|openshift:prometheus_tsdb_head_samples_appended_total:sum|monitoring:container_memory_working_set_bytes:sum|namespace_job:scrape_series_added:topk3_sum1h|namespace_job:scrape_samples_post_metric_relabeling:topk3|monitoring:haproxy_server_http_responses_total:sum|profile:cluster_monitoring_operator_collection_profile:max|vendor_model:node_accelerator_cards:sum|rhmi_status|status:upgrading:version:rhoam_state:max|state:rhoam_critical_alerts:max|state:rhoam_warning_alerts:max|rhoam_7d_slo_percentile:max|rhoam_7d_slo_remaining_error_budget:max|cluster_legacy_scheduler_policy|cluster_master_schedulable|che_workspace_status|che_workspace_started_total|che_workspace_failure_total|che_workspace_start_time_seconds_sum|che_workspace_start_time_seconds_count|cco_credentials_mode|cluster:kube_persistentvolume_plugin_type_counts:sum|acm_managed_cluster_info|acm_managed_cluster_worker_cores:max|acm_console_page_count:sum|cluster:vsphere_vcenter_info:sum|cluster:vsphere_esxi_version_total:sum|cluster:vsphere_node_hw_version_total:sum|openshift:build_by_strategy:sum|rhods_aggregate_availability|rhods_total_users|instance:etcd_disk_wal_fsync_duration_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_bytes:sum|instance:etcd_network_peer_round_trip_time_seconds:histogram_quantile|instance:etcd_mvcc_db_total_size_in_use_in_bytes:sum|instance:etcd_disk_backend_commit_duration_seconds:histogram_quantile|jaeger_operator_instances_storage_types|jaeger_operator_instances_strategies|jaeger_operator_instances_agent_strategies|type:tempo_operator_tempostack_storage_backend:sum|state:tempo_operator_tempostack_managed:sum|type:tempo_operator_tempostack_multi_tenancy:sum|enabled:tempo_operator_tempostack_jaeger_ui:sum|type:opentelemetry_collector_receivers:sum|type:opentelemetry_collector_exporters:sum|type:opentelemetry_collector_processors:sum|type:opentelemetry_collector_extensions:sum|type:opentelemetry_collector_connectors:sum|type:opentelemetry_collector_info:sum|appsvcs:cores_by_product:sum|nto_custom_profiles:count|openshift_csi_share_configmap|openshift_csi_share_secret|openshift_csi_share_mount_failures_total|openshift_csi_share_mount_requests_total|eo_es_storage_info|eo_es_redundancy_policy_info|eo_es_defined_delete_namespaces_total|eo_es_misconfigured_memory_resources_info|cluster:eo_es_data_nodes_total:max|cluster:eo_es_documents_created_total:sum|cluster:eo_es_documents_deleted_total:sum|pod:eo_es_shards_total:max|eo_es_cluster_management_state_info|imageregistry:imagestreamtags_count:sum|imageregistry:operations_count:sum|log_logging_info|log_collector_error_count_total|log_forwarder_pipeline_info|log_forwarder_input_info|log_forwarder_output_info|cluster:log_collected_bytes_total:sum|cluster:log_logged_bytes_total:sum|openshift_logging:log_forwarder_pipelines:sum|openshift_logging:log_forwarders:sum|openshift_logging:log_forwarder_input_type:sum|openshift_logging:log_forwarder_output_type:sum|openshift_logging:vector_component_received_bytes_total:rate5m|cluster:kata_monitor_running_shim_count:sum|platform:hypershift_hostedclusters:max|platform:hypershift_nodepools:max|cluster_name:hypershift_nodepools_size:sum|cluster_name:hypershift_nodepools_available_replicas:sum|namespace:noobaa_unhealthy_bucket_claims:max|namespace:noobaa_buckets_claims:max|namespace:noobaa_unhealthy_namespace_resources:max|namespace:noobaa_namespace_resources:max|namespace:noobaa_unhealthy_namespace_buckets:max|namespace:noobaa_namespace_buckets:max|namespace:noobaa_accounts:max|namespace:noobaa_usage:max|namespace:noobaa_system_health_status:max|ocs_advanced_feature_usage|os_image_url_override:sum|cluster:mcd_nodes_with_unsupported_packages:count|cluster:mcd_total_unsupported_packages:sum|cluster:vsphere_topology_tags:max|cluster:vsphere_infrastructure_failure_domains:max|apiserver_list_watch_request_success_total:rate:sum|rhacs:telemetry:rox_central_info|rhacs:telemetry:rox_central_secured_clusters|rhacs:telemetry:rox_central_secured_nodes|rhacs:telemetry:rox_central_secured_vcpus|rhacs:telemetry:rox_sensor_info|cluster:volume_manager_selinux_pod_context_mismatch_total|cluster:volume_manager_selinux_volume_context_mismatch_warnings_total|cluster:volume_manager_selinux_volume_context_mismatch_errors_total|cluster:volume_manager_selinux_volumes_admitted_total|ols:provider_model_configuration|ols:rest_api_query_calls_total:2xx|ols:rest_api_query_calls_total:4xx|ols:rest_api_query_calls_total:5xx|openshift:openshift_network_operator_ipsec_state:info|cluster:health:group_severity:count|cluster:controlplane_topology:info|cluster:infrastructure_topology:info|cluster:selinux_warning_controller_selinux_volume_conflict:count",action=~"Pass|Allow|Deny|Allow|Deny|",alertstate=~"firing|",direction=~"Ingress|Egress|Ingress|Egress|",enabled=~"true|false|",mode=~"HighlyAvailable|HighlyAvailableArbiter|SingleReplica|DualReplica|External|HighlyAvailable|SingleReplica|",page=~"overview-classic|overview-fleet|search|search-details|clusters|application|governance|",quantile=~"0.99|0.99|0.99|",reason=~"memory_working_set_delta_from_request|memory_rss_delta_from_request|",severity=~"critical|warning|info|none|critical|warning|info|none|",state=~"Managed|Unmanaged|",system_type=~"OCS|OCS|",system_vendor=~"Red Hat|Red Hat|",table_name=~"ACL|Address_Set|ACL|Address_Set|",type=~"azure|gcs|s3|static|openshift|disabled|jaeger|hostmetrics|opencensus|prometheus|zipkin|kafka|filelog|journald|k8sevents|kubeletstats|k8scluster|k8sobjects|otlp|debug|logging|otlp|otlphttp|prometheus|lokiexporter|kafka|awscloudwatchlogs|loadbalancing|batch|memorylimiter|attributes|resource|span|k8sattributes|resourcedetection|filter|routing|cumulativetodelta|groupbyattrs|zpages|ballast|memorylimiter|jaegerremotesampling|healthcheck|pprof|oauth2clientauth|oidcauth|bearertokenauth|filestorage|spanmetrics|forward|deployment|daemonset|sidecar|statefulset|",vendor=~"NVIDIA|AMD|GAUDI|INTEL|QUALCOMM|Marvell|Mellanox|",verb=~"LIST|WATCH|"} diff --git a/assets/admission-webhook/deployment.yaml b/assets/admission-webhook/deployment.yaml index 0faaa50fe8..4436c12067 100644 --- a/assets/admission-webhook/deployment.yaml +++ b/assets/admission-webhook/deployment.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator-admission-webhook namespace: openshift-monitoring spec: @@ -27,7 +27,7 @@ spec: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 spec: affinity: podAntiAffinity: @@ -47,7 +47,7 @@ spec: - --web.key-file=/etc/tls/private/tls.key - --web.tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 - --web.tls-min-version=VersionTLS12 - image: quay.io/prometheus-operator/admission-webhook:v0.84.1 + image: quay.io/prometheus-operator/admission-webhook:v0.85.0 livenessProbe: httpGet: path: /healthz diff --git a/assets/admission-webhook/pod-disruption-budget.yaml b/assets/admission-webhook/pod-disruption-budget.yaml index 226ae21672..bd948691a6 100644 --- a/assets/admission-webhook/pod-disruption-budget.yaml +++ b/assets/admission-webhook/pod-disruption-budget.yaml @@ -5,7 +5,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator-admission-webhook namespace: openshift-monitoring spec: diff --git a/assets/admission-webhook/service-account.yaml b/assets/admission-webhook/service-account.yaml index 19e38901f9..e1d38d0716 100644 --- a/assets/admission-webhook/service-account.yaml +++ b/assets/admission-webhook/service-account.yaml @@ -6,6 +6,6 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator-admission-webhook namespace: openshift-monitoring diff --git a/assets/admission-webhook/service.yaml b/assets/admission-webhook/service.yaml index 697c43c04e..e6c0cfa991 100644 --- a/assets/admission-webhook/service.yaml +++ b/assets/admission-webhook/service.yaml @@ -8,7 +8,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator-admission-webhook app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator-admission-webhook namespace: openshift-monitoring spec: diff --git a/assets/prometheus-operator-user-workload/cluster-role-binding.yaml b/assets/prometheus-operator-user-workload/cluster-role-binding.yaml index e294a2d65d..d9d5a90ebd 100644 --- a/assets/prometheus-operator-user-workload/cluster-role-binding.yaml +++ b/assets/prometheus-operator-user-workload/cluster-role-binding.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-user-workload-operator roleRef: apiGroup: rbac.authorization.k8s.io diff --git a/assets/prometheus-operator-user-workload/cluster-role.yaml b/assets/prometheus-operator-user-workload/cluster-role.yaml index 9b9f0656c5..19b46c52fa 100644 --- a/assets/prometheus-operator-user-workload/cluster-role.yaml +++ b/assets/prometheus-operator-user-workload/cluster-role.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-user-workload-operator rules: - apiGroups: diff --git a/assets/prometheus-operator-user-workload/deployment.yaml b/assets/prometheus-operator-user-workload/deployment.yaml index 7e0b562811..2ffc55d73b 100644 --- a/assets/prometheus-operator-user-workload/deployment.yaml +++ b/assets/prometheus-operator-user-workload/deployment.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-user-workload-monitoring spec: @@ -27,12 +27,12 @@ spec: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 spec: automountServiceAccountToken: true containers: - args: - - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.84.1 + - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.85.0 - --kubelet-endpoints=true - --kubelet-endpointslice=false - --prometheus-instance-namespaces=openshift-user-workload-monitoring @@ -47,7 +47,7 @@ spec: env: - name: GOGC value: "30" - image: quay.io/prometheus-operator/prometheus-operator:v0.84.1 + image: quay.io/prometheus-operator/prometheus-operator:v0.85.0 name: prometheus-operator ports: [] resources: diff --git a/assets/prometheus-operator-user-workload/service-account.yaml b/assets/prometheus-operator-user-workload/service-account.yaml index 345da09c33..398ed6f3a3 100644 --- a/assets/prometheus-operator-user-workload/service-account.yaml +++ b/assets/prometheus-operator-user-workload/service-account.yaml @@ -7,6 +7,6 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-user-workload-monitoring diff --git a/assets/prometheus-operator-user-workload/service-monitor.yaml b/assets/prometheus-operator-user-workload/service-monitor.yaml index 2ffa2b5c2e..224ad9b2e4 100644 --- a/assets/prometheus-operator-user-workload/service-monitor.yaml +++ b/assets/prometheus-operator-user-workload/service-monitor.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-user-workload-monitoring spec: @@ -24,4 +24,4 @@ spec: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 diff --git a/assets/prometheus-operator-user-workload/service.yaml b/assets/prometheus-operator-user-workload/service.yaml index 73451f8425..9e249806d5 100644 --- a/assets/prometheus-operator-user-workload/service.yaml +++ b/assets/prometheus-operator-user-workload/service.yaml @@ -9,7 +9,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-user-workload-monitoring spec: diff --git a/assets/prometheus-operator/cluster-role-binding.yaml b/assets/prometheus-operator/cluster-role-binding.yaml index cbf3c963b4..c18694edea 100644 --- a/assets/prometheus-operator/cluster-role-binding.yaml +++ b/assets/prometheus-operator/cluster-role-binding.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator roleRef: apiGroup: rbac.authorization.k8s.io diff --git a/assets/prometheus-operator/cluster-role.yaml b/assets/prometheus-operator/cluster-role.yaml index 0e7c3c40f9..00882d05cf 100644 --- a/assets/prometheus-operator/cluster-role.yaml +++ b/assets/prometheus-operator/cluster-role.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator rules: - apiGroups: diff --git a/assets/prometheus-operator/deployment.yaml b/assets/prometheus-operator/deployment.yaml index 127d83effb..7ed00be172 100644 --- a/assets/prometheus-operator/deployment.yaml +++ b/assets/prometheus-operator/deployment.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-monitoring spec: @@ -27,15 +27,16 @@ spec: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 spec: automountServiceAccountToken: true containers: - args: - --kubelet-service=kube-system/kubelet - - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.84.1 + - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.85.0 - --kubelet-endpoints=true - --kubelet-endpointslice=false + - --watch-referenced-objects-in-all-namespaces=true - --prometheus-instance-namespaces=openshift-monitoring - --thanos-ruler-instance-namespaces=openshift-monitoring - --alertmanager-instance-namespaces=openshift-monitoring @@ -48,7 +49,7 @@ spec: env: - name: GOGC value: "30" - image: quay.io/prometheus-operator/prometheus-operator:v0.84.1 + image: quay.io/prometheus-operator/prometheus-operator:v0.85.0 name: prometheus-operator ports: [] resources: diff --git a/assets/prometheus-operator/prometheus-rule.yaml b/assets/prometheus-operator/prometheus-rule.yaml index d09da173d8..0dc1fa5465 100644 --- a/assets/prometheus-operator/prometheus-rule.yaml +++ b/assets/prometheus-operator/prometheus-rule.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 prometheus: k8s role: alert-rules name: prometheus-operator-rules diff --git a/assets/prometheus-operator/service-account.yaml b/assets/prometheus-operator/service-account.yaml index 331eff60f0..121fa459ed 100644 --- a/assets/prometheus-operator/service-account.yaml +++ b/assets/prometheus-operator/service-account.yaml @@ -7,6 +7,6 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-monitoring diff --git a/assets/prometheus-operator/service-monitor.yaml b/assets/prometheus-operator/service-monitor.yaml index 049a71f559..3f46c62f45 100644 --- a/assets/prometheus-operator/service-monitor.yaml +++ b/assets/prometheus-operator/service-monitor.yaml @@ -6,7 +6,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-monitoring spec: @@ -24,4 +24,4 @@ spec: app.kubernetes.io/component: controller app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 diff --git a/assets/prometheus-operator/service.yaml b/assets/prometheus-operator/service.yaml index 584735c082..7cdb419341 100644 --- a/assets/prometheus-operator/service.yaml +++ b/assets/prometheus-operator/service.yaml @@ -9,7 +9,7 @@ metadata: app.kubernetes.io/managed-by: cluster-monitoring-operator app.kubernetes.io/name: prometheus-operator app.kubernetes.io/part-of: openshift-monitoring - app.kubernetes.io/version: 0.84.1 + app.kubernetes.io/version: 0.85.0 name: prometheus-operator namespace: openshift-monitoring spec: diff --git a/jsonnet/versions.yaml b/jsonnet/versions.yaml index ce62d4c4d6..6e37218915 100644 --- a/jsonnet/versions.yaml +++ b/jsonnet/versions.yaml @@ -20,8 +20,8 @@ versions: kubernetesMetricsServer: 0.8.0 monitoringPlugin: 1.0.0 nodeExporter: 1.9.1 - promLabelProxy: 0.12.0 + promLabelProxy: 0.12.1 prometheus: 3.5.0 prometheusAdapter: 0.12.0 - prometheusOperator: 0.84.1 + prometheusOperator: 0.85.0 thanos: 0.39.2 diff --git a/manifests/0000_50_cluster-monitoring-operator_04-config.yaml b/manifests/0000_50_cluster-monitoring-operator_04-config.yaml index d3a2874d01..2cc9f3b72f 100644 --- a/manifests/0000_50_cluster-monitoring-operator_04-config.yaml +++ b/manifests/0000_50_cluster-monitoring-operator_04-config.yaml @@ -1117,10 +1117,10 @@ data: # # owners: (https://github.com/openshift/machine-config-operator/) # - # node:mcd_local_unsupported_packages:count tracks the number of unsupported, - # locally layered RPM packages on a given node. - - '{__name__="node:mcd_local_unsupported_packages:count"}' - # + # cluster:mcd_nodes_with_unsupported_packages:count is the total number of nodes with unsupported packages. + - '{__name__="cluster:mcd_nodes_with_unsupported_packages:count"}' + # cluster:mcd_total_unsupported_packages:sum is the sum of all unsupported packages across all nodes. + - '{__name__="cluster:mcd_total_unsupported_packages:sum"}' # owners: (https://github.com/openshift/vmware-vsphere-csi-driver-operator, @openshift/storage) # # cluster:vsphere_topology_tags:max shows how many vSphere topology tag categories are configured.