assets: regenerate

Signed-off-by: Jayapriya Pai <[email protected]>
openshift · Feb 4, 2022 · 2b55d7c · 2b55d7c
1 parent 0fa97ae
commit 2b55d7c
Show file tree

Hide file tree

Showing 16 changed files with 165 additions and 76 deletions.
diff --git a/assets/alertmanager/secret.yaml b/assets/alertmanager/secret.yaml
@@ -28,10 +28,17 @@ stringData:
       - "severity = warning"
       "target_matchers":
       - "severity = info"
+    - "equal":
+      - "namespace"
+      "source_matchers":
+      - "alertname = InfoInhibitor"
+      "target_matchers":
+      - "severity = info"
     "receivers":
     - "name": "Default"
     - "name": "Watchdog"
     - "name": "Critical"
+    - "name": "null"
     "route":
       "group_by":
       - "namespace"
@@ -43,6 +50,9 @@ stringData:
       - "matchers":
         - "alertname = Watchdog"
         "receiver": "Watchdog"
+      - "matchers":
+        - "alertname = InfoInhibitor"
+        "receiver": "null"
       - "matchers":
         - "severity = critical"
         "receiver": "Critical"

diff --git a/assets/cluster-monitoring-operator/prometheus-rule.yaml b/assets/cluster-monitoring-operator/prometheus-rule.yaml
@@ -420,6 +420,20 @@ spec:
       labels:
         namespace: openshift-monitoring
         severity: none
+    - alert: InfoInhibitor
+      annotations:
+        description: |
+          This is an alert that is used to inhibit info alerts.
+          By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with
+          other alerts.
+          This alert fires whenever there's a severity="info" alert, and stops firing when another alert with a
+          severity of 'warning' or 'critical' starts firing on the same namespace.
+          This alert should be routed to a null receiver and configured to inhibit alerts with severity="info".
+        summary: Info-level alert inhibition.
+      expr: ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname !=
+        "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1
+      labels:
+        severity: none
   - name: node-network
     rules:
     - alert: NodeNetworkInterfaceFlapping

diff --git a/assets/control-plane/prometheus-rule.yaml b/assets/control-plane/prometheus-rule.yaml
@@ -125,7 +125,7 @@ spec:
              !=
             0
           ) or (
-            kube_daemonset_updated_number_scheduled{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"}
+            kube_daemonset_status_updated_number_scheduled{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"}
              !=
             kube_daemonset_status_desired_number_scheduled{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"}
           ) or (
@@ -134,7 +134,7 @@ spec:
             kube_daemonset_status_desired_number_scheduled{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"}
           )
         ) and (
-          changes(kube_daemonset_updated_number_scheduled{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"}[5m])
+          changes(kube_daemonset_status_updated_number_scheduled{namespace=~"(openshift-.*|kube-.*|default)",job="kube-state-metrics"}[5m])
             ==
           0
         )
@@ -674,6 +674,16 @@ spec:
       labels:
         workload_type: statefulset
       record: namespace_workload_pod:kube_pod_owner:relabel
+    - expr: |
+        max by (cluster, namespace, workload, pod) (
+          label_replace(
+            kube_pod_owner{job="kube-state-metrics", owner_kind="Job"},
+            "workload", "$1", "owner_name", "(.*)"
+          )
+        )
+      labels:
+        workload_type: job
+      record: namespace_workload_pod:kube_pod_owner:relabel
   - name: kube-scheduler.rules
     rules:
     - expr: |
@@ -743,17 +753,17 @@ spec:
   - name: kubelet.rules
     rules:
     - expr: |
-        histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
+        histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
       labels:
         quantile: "0.99"
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
     - expr: |
-        histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
+        histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
       labels:
         quantile: "0.9"
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
     - expr: |
-        histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
+        histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
       labels:
         quantile: "0.5"
       record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile