feat: add recoding rules

2026-07-16 17:51:08 +02:00 · 2025-09-23 14:31:48 +08:00
parent a8ac95ebad
commit 2961a9591a
8 changed files with 475 additions and 3 deletions
@@ -0,0 +1,8 @@
+# Alert Rules
+
+Alert rules are configurations that define conditions, scope, and actions for generating alerts from
+monitored signals, such as metrics, logs, or activity. When an alert rule's defined conditions are
+met for a specific resource within its scope, the system generates a triggered alert, which is the
+actual instance of the condition being met. These rules specify the data to monitor, the trigger
+threshold, and the resulting actions, like sending notifications to specific receivers or performing
+automated tasks.
@@ -0,0 +1,57 @@
+groups:
+  - name: general.rules
+    rules:
+      - alert: TargetDown
+        annotations:
+          description:
+            '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in
+            {{ $labels.namespace }} namespace are down.'
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown
+          summary: One or more targets are unreachable.
+        expr:
+          100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up) BY (cluster, job,
+          namespace, service)) > 10
+        for: 10m
+        labels:
+          severity: warning
+      - alert: Watchdog
+        annotations:
+          description: 'This is an alert meant to ensure that the entire alerting pipeline is
+            functional.
+
+            This alert is always firing, therefore it should always be firing in Alertmanager
+
+            and always fire against a receiver. There are integrations with various notification
+
+            mechanisms that send a notification when this alert is not firing. For example the
+
+            "DeadMansSnitch" integration in PagerDuty.'
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
+          summary:
+            An alert that should always be firing to certify that Alertmanager is working properly.
+        expr: vector(1)
+        labels:
+          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".'
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
+          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
@@ -0,0 +1,120 @@
+groups:
+  - name: kubernetes-resources
+    rules:
+      - 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{job="kube-state-metrics",}) 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.
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
+          summary: Cluster has overcommitted CPU resource requests.
+        expr: |-
+          sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) by (cluster)
+            /
+          sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) by (cluster)
+            > 1.5
+        for: 5m
+        labels:
+          severity: warning
+      - alert: KubeMemoryQuotaOvercommit
+        annotations:
+          description:
+            Cluster {{ $labels.cluster }}  has overcommitted memory resource requests for
+            Namespaces.
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
+          summary: Cluster has overcommitted memory resource requests.
+        expr: |-
+          sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster)
+            /
+          sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)
+            > 1.5
+        for: 5m
+        labels:
+          severity: warning
+      - alert: KubeQuotaAlmostFull
+        annotations:
+          description:
+            Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{
+            $labels.resource }} quota.
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
+          summary: Namespace quota is going to be full.
+        expr: |-
+          kube_resourcequota{job="kube-state-metrics", type="used"}
+            / ignoring(instance, job, type)
+          (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
+            > 0.9 < 1
+        for: 15m
+        labels:
+          severity: info
+      - alert: KubeQuotaFullyUsed
+        annotations:
+          description:
+            Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{
+            $labels.resource }} quota.
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
+          summary: Namespace quota is fully used.
+        expr: |-
+          kube_resourcequota{job="kube-state-metrics", type="used"}
+            / ignoring(instance, job, type)
+          (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
+            == 1
+        for: 15m
+        labels:
+          severity: info
+      - alert: KubeQuotaExceeded
+        annotations:
+          description:
+            Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{
+            $labels.resource }} quota.
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
+          summary: Namespace quota has exceeded the limits.
+        expr: |-
+          kube_resourcequota{job="kube-state-metrics", type="used"}
+            / ignoring(instance, job, type)
+          (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
+            > 1
+        for: 15m
+        labels:
+          severity: warning
+      - alert: CPUThrottlingHigh
+        annotations:
+          description:
+            "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace
+            }} for container {{ $labels.container }} in pod {{ $labels.pod }}."
+          runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
+          summary: Processes experience elevated CPU throttling.
+        expr: |-
+          sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace)
+            /
+          sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace)
+            > ( 25 / 100 )
+        for: 15m
+        labels:
+          severity: info