fix: disable OverCommit alerts globally

charts/kubezero-metrics/README.md

@@ -90,13 +90,11 @@ Kubernetes: `>= 1.26.0`
 | kube-prometheus-stack.alertmanager.config.inhibit_rules[2].equal[0] | string | `"namespace"` |  |
 | kube-prometheus-stack.alertmanager.config.inhibit_rules[2].source_matchers[0] | string | `"alertname = InfoInhibitor"` |  |
 | kube-prometheus-stack.alertmanager.config.inhibit_rules[2].target_matchers[0] | string | `"severity = info"` |  |
-| kube-prometheus-stack.alertmanager.config.inhibit_rules[3].source_matchers[0] | string | `"alertname = ClusterAutoscalerNodeGroupsEnabled"` |  |
-| kube-prometheus-stack.alertmanager.config.inhibit_rules[3].target_matchers[0] | string | `"alertname =~ \"KubeCPUOvercommit|KubeMemoryOvercommit\""` |  |
 | kube-prometheus-stack.alertmanager.config.route.group_by[0] | string | `"alertname"` |  |
 | kube-prometheus-stack.alertmanager.config.route.group_by[1] | string | `"severity"` |  |
 | kube-prometheus-stack.alertmanager.config.route.group_by[2] | string | `"status"` |  |
 | kube-prometheus-stack.alertmanager.config.route.group_interval | string | `"5m"` |  |
-| kube-prometheus-stack.alertmanager.config.route.group_wait | string | `"15s"` |  |
+| kube-prometheus-stack.alertmanager.config.route.group_wait | string | `"30s"` |  |
 | kube-prometheus-stack.alertmanager.config.route.repeat_interval | string | `"4h"` |  |
 | kube-prometheus-stack.alertmanager.config.route.routes[0].matchers[0] | string | `"severity = none"` |  |
 | kube-prometheus-stack.alertmanager.config.route.routes[0].receiver | string | `"null"` |  |

charts/kubezero-metrics/jsonnet/jsonnetfile.lock.json

@@ -18,7 +18,7 @@
           "subdir": "contrib/mixin"
         }
       },
-      "version": "a45cc4961e827009dba7d164e441a0ebe2eef870",
+      "version": "2b323071a8bd4f02ddaf63e0dfa1fd98c221dccb",
       "sum": "IXI3LQIT9NmTPJAk8WLUJd5+qZfcGpeNCyWIK7oEpws="
     },
     {

charts/kubezero-metrics/jsonnet/rules.libsonnet

@@ -42,10 +42,13 @@ local kp = (import 'kube-prometheus/main.libsonnet') + {
           (
             if group.name == 'kubernetes-resources' then
               group {
-                rules: [
+                rules: std.filter(
-                  {
+                  function(rule)
+                    rule.alert != 'KubeCPUOvercommit' && rule.alert != 'KubeMemoryOvercommit',
+                  group.rules
+                ) + [{
                   alert: 'ClusterAutoscalerNodeGroupsEnabled',
-                    expr: 'cluster_autoscaler_node_groups_count{job="addons-aws-cluster-autoscaler",node_group_type="autoscaled"} > 0 or vector(1)',
+                  expr: 'cluster_autoscaler_node_groups_count{job="addons-aws-cluster-autoscaler",node_group_type="autoscaled"} > 0',
                   'for': '5m',
                   labels: {
                     severity: 'none',
@@ -54,8 +57,7 @@ local kp = (import 'kube-prometheus/main.libsonnet') + {
                     description: 'Inhibitor rule if the Cluster Autoscaler found at least one node group',
                     summary: 'Cluster Autoscaler found at least one node group.',
                   },
-                  },
+                }],
-                ] + super.rules,
               }
             else
               group

charts/kubezero-metrics/jsonnet/rules/kubernetes-prometheusRule

@@ -228,44 +228,6 @@
          {
             "name": "kubernetes-resources",
             "rules": [
-               {
-                  "alert": "ClusterAutoscalerNodeGroupsEnabled",
-                  "annotations": {
-                     "description": "Inhibitor rule if the Cluster Autoscaler found at least one node group",
-                     "summary": "Cluster Autoscaler found at least one node group."
-                  },
-                  "expr": "cluster_autoscaler_node_groups_count{job=\"addons-aws-cluster-autoscaler\",node_group_type=\"autoscaled\"} > 0",
-                  "for": "5m",
-                  "labels": {
-                     "severity": "none"
-                  }
-               },
-               {
-                  "alert": "KubeCPUOvercommit",
-                  "annotations": {
-                     "description": "Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.",
-                     "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit",
-                     "summary": "Cluster has overcommitted CPU resource requests."
-                  },
-                  "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\"}) by (cluster) - max(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\"}) by (cluster)) > 0\nand\n(sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\"}) by (cluster) - max(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\"}) by (cluster)) > 0\n",
-                  "for": "10m",
-                  "labels": {
-                     "severity": "warning"
-                  }
-               },
-               {
-                  "alert": "KubeMemoryOvercommit",
-                  "annotations": {
-                     "description": "Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure.",
-                     "runbook_url": "https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit",
-                     "summary": "Cluster has overcommitted memory resource requests."
-                  },
-                  "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"}) by (cluster) - max(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"}) by (cluster)) > 0\nand\n(sum(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"}) by (cluster) - max(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"}) by (cluster)) > 0\n",
-                  "for": "10m",
-                  "labels": {
-                     "severity": "warning"
-                  }
-               },
                {
                   "alert": "KubeCPUQuotaOvercommit",
                   "annotations": {
@@ -343,6 +305,18 @@
                   "labels": {
                      "severity": "info"
                   }
+               },
+               {
+                  "alert": "ClusterAutoscalerNodeGroupsEnabled",
+                  "annotations": {
+                     "description": "Inhibitor rule if the Cluster Autoscaler found at least one node group",
+                     "summary": "Cluster Autoscaler found at least one node group."
+                  },
+                  "expr": "cluster_autoscaler_node_groups_count{job=\"addons-aws-cluster-autoscaler\",node_group_type=\"autoscaled\"} > 0",
+                  "for": "5m",
+                  "labels": {
+                     "severity": "none"
+                  }
                }
             ]
          },

charts/kubezero-metrics/templates/rules/kubernetes.yaml

@@ -166,44 +166,6 @@ spec:
         severity: warning
   - name: kubernetes-resources
     rules:
-    - alert: ClusterAutoscalerNodeGroupsEnabled
-      annotations:
-        description: Inhibitor rule if the Cluster Autoscaler found at least one node group
-        summary: Cluster Autoscaler found at least one node group.
-      expr: cluster_autoscaler_node_groups_count{job="addons-aws-cluster-autoscaler",node_group_type="autoscaled"} > 0
-      for: 5m
-      labels:
-        severity: none
-    - alert: KubeCPUOvercommit
-      annotations:
-        description: Cluster {{`{{`}} $labels.cluster {{`}}`}} has overcommitted CPU resource requests for Pods by {{`{{`}} $value {{`}}`}} CPU shares and cannot tolerate node failure.
-        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
-        summary: Cluster has overcommitted CPU resource requests.
-      expr: 'sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
-
-        and
-
-        (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
-
-        '
-      for: 10m
-      labels:
-        severity: warning
-    - alert: KubeMemoryOvercommit
-      annotations:
-        description: Cluster {{`{{`}} $labels.cluster {{`}}`}} has overcommitted memory resource requests for Pods by {{`{{`}} $value | humanize {{`}}`}} bytes and cannot tolerate node failure.
-        runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
-        summary: Cluster has overcommitted memory resource requests.
-      expr: 'sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
-
-        and
-
-        (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
-
-        '
-      for: 10m
-      labels:
-        severity: warning
     - alert: KubeCPUQuotaOvercommit
       annotations:
         description: Cluster {{`{{`}} $labels.cluster {{`}}`}}  has overcommitted CPU resource requests for Namespaces.
@@ -258,6 +220,14 @@ spec:
       for: 15m
       labels:
         severity: info
+    - alert: ClusterAutoscalerNodeGroupsEnabled
+      annotations:
+        description: Inhibitor rule if the Cluster Autoscaler found at least one node group
+        summary: Cluster Autoscaler found at least one node group.
+      expr: cluster_autoscaler_node_groups_count{job="addons-aws-cluster-autoscaler",node_group_type="autoscaled"} > 0
+      for: 5m
+      labels:
+        severity: none
   - name: kubernetes-storage
     rules:
     - alert: KubePersistentVolumeFillingUp

charts/kubezero-metrics/values.yaml

@@ -252,11 +252,6 @@ kube-prometheus-stack:
         - alertname = InfoInhibitor
         target_matchers:
         - severity = info
-      # Disable cluster overcommit alerts if we have cluster autoscaler available
-      - source_matchers:
-        - alertname = ClusterAutoscalerNodeGroupsEnabled
-        target_matchers:
-        - alertname =~ "KubeCPUOvercommit|KubeMemoryOvercommit"
     alertmanagerSpec:
       # externalUrl:
       logFormat: json