Add support for OCP 4.16

appuio · Oct 15, 2024 · eb521f6 · eb521f6
1 parent 4d39bbd
commit eb521f6
Show file tree

Hide file tree

Showing 27 changed files with 3,356 additions and 107 deletions.
diff --git a/class/defaults.yml b/class/defaults.yml
@@ -10,9 +10,9 @@ parameters:
     manifests_version: release-4.15
     # no release branches newer than 4.9 exist
     =_operator_lifecycle_manager_map:
-      release-4.13: release-4.9
       release-4.14: release-4.9
       release-4.15: release-4.9
+      release-4.16: release-4.9
     jsonnetfile_parameters:
       cmo_version: ${openshift4_monitoring:manifests_version}
       etcd_version: ${openshift4_monitoring:manifests_version}
@@ -205,9 +205,9 @@ parameters:
           NodeMemoryMajorPagesFaults:
             # Only alert for >100*cores major page faults/node instead of >500/node
             expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) > on (instance) (count by (instance) (node_cpu_info{}) * 100)
-        release-4.13: {}
         release-4.14: {}
         release-4.15: {}
+        release-4.16: {}
       # Alerts to ignore for user workload monitoring
       ignoreUserWorkload: []
 

diff --git a/class/openshift4-monitoring.yml b/class/openshift4-monitoring.yml
@@ -2,10 +2,6 @@ parameters:
   openshift4_monitoring:
     =_manifest_urls:
       kube-apiserver:
-        release-4.13:
-          api-usage: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.13/bindata/assets/alerts/api-usage.yaml
-          cpu-utilization: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.13/bindata/assets/alerts/cpu-utilization.yaml
-          slos: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.13/bindata/assets/alerts/kube-apiserver-slos-basic.yaml
         release-4.14:
           api-usage: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.14/bindata/assets/alerts/api-usage.yaml
           cpu-utilization: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.14/bindata/assets/alerts/cpu-utilization.yaml
@@ -14,21 +10,28 @@ parameters:
           api-usage: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.15/bindata/assets/alerts/api-usage.yaml
           cpu-utilization: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.15/bindata/assets/alerts/cpu-utilization.yaml
           slos: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.15/bindata/assets/alerts/kube-apiserver-slos-basic.yaml
+        release-4.16:
+          api-usage: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.16/bindata/assets/alerts/api-usage.yaml
+          cpu-utilization: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.16/bindata/assets/alerts/cpu-utilization.yaml
+          slos: https://raw.githubusercontent.com/openshift/cluster-kube-apiserver-operator/release-4.16/bindata/assets/alerts/kube-apiserver-slos-basic.yaml
 
       machine-api-operator:
-        release-4.13:
-          prometheus: https://raw.githubusercontent.com/openshift/machine-api-operator/release-4.13/install/0000_90_machine-api-operator_04_alertrules.yaml
         release-4.14:
           prometheus: https://raw.githubusercontent.com/openshift/machine-api-operator/release-4.14/install/0000_90_machine-api-operator_04_alertrules.yaml
         release-4.15:
           prometheus: https://raw.githubusercontent.com/openshift/machine-api-operator/release-4.15/install/0000_90_machine-api-operator_04_alertrules.yaml
+        release-4.16:
+          prometheus: https://raw.githubusercontent.com/openshift/machine-api-operator/release-4.16/install/0000_90_machine-api-operator_04_alertrules.yaml
+
+      machine-config-operator:
+        release-4.14:
+          prometheus: https://raw.githubusercontent.com/openshift/machine-config-operator/release-4.14/install/0000_90_machine-config-operator_01_prometheus-rules.yaml
+        release-4.15:
+          prometheus: https://raw.githubusercontent.com/openshift/machine-config-operator/release-4.15/install/0000_90_machine-config-operator_01_prometheus-rules.yaml
+        release-4.16:
+          prometheus: https://raw.githubusercontent.com/openshift/machine-config-operator/release-4.16/install/0000_90_machine-config_01_prometheus-rules.yaml
 
       ovn-kubernetes:
-        release-4.13:
-          common: https://raw.githubusercontent.com/openshift/cluster-network-operator/${openshift4_monitoring:manifests_version}/bindata/network/ovn-kubernetes/common/alert-rules.yaml
-          # We use the "self-hosted" variant of the control-plane alerts, so
-          # we don't have to worry about unresolved gotemplate references.
-          control_plane: https://raw.githubusercontent.com/openshift/cluster-network-operator/${openshift4_monitoring:manifests_version}/bindata/network/ovn-kubernetes/self-hosted/alert-rules-control-plane.yaml
         release-4.14:
           common: https://raw.githubusercontent.com/openshift/cluster-network-operator/${openshift4_monitoring:manifests_version}/bindata/network/ovn-kubernetes/common/alert-rules.yaml
           # We handle the gotemplate stuff in Jsonnet for now, since Jinja
@@ -47,11 +50,16 @@ parameters:
           # The only templates that are in the alerting rules can be handled
           # with a simple string replace.
           control_plane: https://raw.githubusercontent.com/openshift/cluster-network-operator/release-4.15/bindata/network/ovn-kubernetes/self-hosted/alert-rules-control-plane.yaml
+        release-4.16:
+          common: https://raw.githubusercontent.com/openshift/cluster-network-operator/${openshift4_monitoring:manifests_version}/bindata/network/ovn-kubernetes/common/alert-rules.yaml
+          # We use the "self-hosted" variant of the control-plane alerts, so
+          # we don't have to worry about unresolved gotemplate references.
+          control_plane: https://raw.githubusercontent.com/openshift/cluster-network-operator/${openshift4_monitoring:manifests_version}/bindata/network/ovn-kubernetes/self-hosted/alert-rules-control-plane.yaml
 
       cloud-credential-operator:
-        release-4.13: https://raw.githubusercontent.com/openshift/cloud-credential-operator/release-4.13/manifests/0000_90_cloud-credential-operator_04_alertrules.yaml
         release-4.14: https://raw.githubusercontent.com/openshift/cloud-credential-operator/release-4.14/manifests/0000_90_cloud-credential-operator_04_alertrules.yaml
         release-4.15: https://raw.githubusercontent.com/openshift/cloud-credential-operator/release-4.15/manifests/0000_90_cloud-credential-operator_03_alertrules.yaml
+        release-4.16: https://raw.githubusercontent.com/openshift/cloud-credential-operator/release-4.16/manifests/0000_90_cloud-credential-operator_03_alertrules.yaml
 
 
   kapitan:
@@ -103,7 +111,7 @@ parameters:
         source: ${openshift4_monitoring:_manifest_urls:machine-api-operator:${openshift4_monitoring:manifests_version}:prometheus}
         output_path: dependencies/openshift4-monitoring/manifests/${openshift4_monitoring:manifests_version}/machine-api-operator.yaml
       - type: https
-        source: https://raw.githubusercontent.com/openshift/machine-config-operator/${openshift4_monitoring:manifests_version}/install/0000_90_machine-config-operator_01_prometheus-rules.yaml
+        source: ${openshift4_monitoring:_manifest_urls:machine-config-operator:${openshift4_monitoring:manifests_version}:prometheus}
         output_path: dependencies/openshift4-monitoring/manifests/${openshift4_monitoring:manifests_version}/machine-config-operator.yaml
       - type: https
         source: https://raw.githubusercontent.com/operator-framework/operator-lifecycle-manager/${openshift4_monitoring:_operator_lifecycle_manager_map:${openshift4_monitoring:manifests_version}}/manifests/0000_90_olm_01-prometheus-rule.yaml

diff --git a/tests/custom-rules.yml b/tests/custom-rules.yml
@@ -11,7 +11,7 @@ parameters:
       name: patch-sa
 
   openshift4_monitoring:
-    manifests_version: release-4.13
+    manifests_version: release-4.16
 
     customNodeExporter:
       enabled: true
@@ -25,7 +25,7 @@ parameters:
             labels:
               foo: foo
               generic: patch
-        release-4.13:
+        release-4.16:
           HighOverallControlPlaneMemory:
             labels:
               foo: bar

diff --git a/...alerts-with-node-labels/openshift4-monitoring/openshift4-monitoring/prometheus_rules.yaml b/...alerts-with-node-labels/openshift4-monitoring/openshift4-monitoring/prometheus_rules.yaml
@@ -852,7 +852,7 @@ spec:
             syn_component: openshift4-monitoring
           expr: |
             (
-              max by(namespace, statefulset) (
+              max by(namespace, statefulset, job, cluster) (
                 kube_statefulset_status_current_revision{namespace=~"(appuio.*|cilium|default|kube-.*|openshift-.*|syn.*)",job="kube-state-metrics"}
                   unless
                 kube_statefulset_status_update_revision{namespace=~"(appuio.*|cilium|default|kube-.*|openshift-.*|syn.*)",job="kube-state-metrics"}
@@ -1040,7 +1040,7 @@ spec:
               }} of its incoming requests.
             syn_component: openshift4-monitoring
           expr: |
-            sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m]))  / (  sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
+            sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by(cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
           for: 5m
           labels:
             severity: warning

diff --git a/.../golden/capacity-alerts/openshift4-monitoring/openshift4-monitoring/prometheus_rules.yaml b/.../golden/capacity-alerts/openshift4-monitoring/openshift4-monitoring/prometheus_rules.yaml
@@ -852,7 +852,7 @@ spec:
             syn_component: openshift4-monitoring
           expr: |
             (
-              max by(namespace, statefulset) (
+              max by(namespace, statefulset, job, cluster) (
                 kube_statefulset_status_current_revision{namespace=~"(appuio.*|cilium|default|kube-.*|openshift-.*|syn.*)",job="kube-state-metrics"}
                   unless
                 kube_statefulset_status_update_revision{namespace=~"(appuio.*|cilium|default|kube-.*|openshift-.*|syn.*)",job="kube-state-metrics"}
@@ -1040,7 +1040,7 @@ spec:
               }} of its incoming requests.
             syn_component: openshift4-monitoring
           expr: |
-            sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m]))  / (  sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
+            sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by(cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
           for: 5m
           labels:
             severity: warning

diff --git a/...golden/custom-rules/openshift4-monitoring/openshift4-monitoring/appuio_node_exporter.yaml b/...golden/custom-rules/openshift4-monitoring/openshift4-monitoring/appuio_node_exporter.yaml
@@ -4,7 +4,6 @@ metadata:
   labels:
     app.kubernetes.io/part-of: openshift4-monitoring
   name: appuio-node-exporter
-  namespace: openshift-monitoring
 rules:
   - apiGroups:
       - authentication.k8s.io
@@ -33,7 +32,6 @@ metadata:
   labels:
     app.kubernetes.io/part-of: openshift4-monitoring
   name: appuio-node-exporter
-  namespace: openshift-monitoring
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole
@@ -59,6 +57,7 @@ spec:
     metadata:
       annotations:
         kubectl.kubernetes.io/default-container: appuio-node-exporter
+        openshift.io/required-scc: node-exporter
       labels:
         app.kubernetes.io/managed-by: cluster-monitoring-operator
         app.kubernetes.io/part-of: openshift4-monitoring
@@ -152,6 +151,9 @@ spec:
               fi
               echo "ts=$(date -Iseconds) num_cpus=$NUM_CPUS gomaxprocs=$GOMAXPROCS"
               exec /bin/node_exporter "$0" "$@"
+          env:
+            - name: DBUS_SYSTEM_BUS_ADDRESS
+              value: unix:path=/host/root/var/run/dbus/system_bus_socket
           image: quay.io/prometheus/node-exporter:v1.8.2
           name: appuio-node-exporter
           resources:
@@ -162,7 +164,6 @@ spec:
               cpu: 8m
               memory: 32Mi
           securityContext: {}
-          terminationMessagePolicy: FallbackToLogsOnError
           volumeMounts:
             - mountPath: /host/sys
               mountPropagation: HostToContainer
@@ -177,7 +178,6 @@ spec:
               readOnly: true
           workingDir: /var/node_exporter/textfile
         - args:
-            - --logtostderr
             - --secure-listen-address=[$(IP)]:9199
             - --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
             - --upstream=http://127.0.0.1:9199/
@@ -209,7 +209,8 @@ spec:
             runAsGroup: 65532
             runAsNonRoot: true
             runAsUser: 65532
-          terminationMessagePolicy: FallbackToLogsOnError
+            seccompProfile:
+              type: RuntimeDefault
           volumeMounts:
             - mountPath: /etc/tls/private
               name: node-exporter-tls
@@ -240,7 +241,6 @@ spec:
           securityContext:
             privileged: true
             runAsUser: 0
-          terminationMessagePolicy: FallbackToLogsOnError
           volumeMounts:
             - mountPath: /var/node_exporter/textfile
               name: node-exporter-textfile
@@ -306,6 +306,8 @@ apiVersion: v1
 kind: Service
 metadata:
   annotations:
+    openshift.io/description: Expose the `/metrics` endpoint on port 9199. This port
+      is for internal use, and no other usage is guaranteed.
     service.beta.openshift.io/serving-cert-secret-name: appuio-node-exporter-tls
   labels:
     app.kubernetes.io/part-of: openshift4-monitoring