feat: add recoding rules

2026-07-16 01:22:40 +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 +1,149 @@
+groups:
+  - name: k8s.rules
+    rules:
+      - expr: |-
+          sum by (cluster, namespace, pod, container) (
+            irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
+          ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
+            1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
+          )
+        record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
+      - expr: |-
+          container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
+          * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
+            max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
+          )
+        record: node_namespace_pod_container:container_memory_working_set_bytes
+      - expr: |-
+          container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
+          * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
+            max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
+          )
+        record: node_namespace_pod_container:container_memory_rss
+      - expr: |-
+          container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
+          * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
+            max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
+          )
+        record: node_namespace_pod_container:container_memory_cache
+      - expr: |-
+          container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
+          * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
+            max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
+          )
+        record: node_namespace_pod_container:container_memory_swap
+      - expr: |-
+          kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+          group_left() max by (namespace, pod, cluster) (
+            (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+          )
+        record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
+      - expr: |-
+          sum by (namespace, cluster) (
+              sum by (namespace, pod, cluster) (
+                  max by (namespace, pod, container, cluster) (
+                    kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}
+                  ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                    kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                  )
+              )
+          )
+        record: namespace_memory:kube_pod_container_resource_requests:sum
+      - expr: |-
+          kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+          group_left() max by (namespace, pod, cluster) (
+            (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+          )
+        record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
+      - expr: |-
+          sum by (namespace, cluster) (
+              sum by (namespace, pod, cluster) (
+                  max by (namespace, pod, container, cluster) (
+                    kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}
+                  ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                    kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                  )
+              )
+          )
+        record: namespace_cpu:kube_pod_container_resource_requests:sum
+      - expr: |-
+          kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+          group_left() max by (namespace, pod, cluster) (
+            (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+          )
+        record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits
+      - expr: |-
+          sum by (namespace, cluster) (
+              sum by (namespace, pod, cluster) (
+                  max by (namespace, pod, container, cluster) (
+                    kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}
+                  ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                    kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                  )
+              )
+          )
+        record: namespace_memory:kube_pod_container_resource_limits:sum
+      - expr: |-
+          kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}  * on (namespace, pod, cluster)
+          group_left() max by (namespace, pod, cluster) (
+            (kube_pod_status_phase{phase=~"Pending|Running"} == 1)
+            )
+        record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
+      - expr: |-
+          sum by (namespace, cluster) (
+              sum by (namespace, pod, cluster) (
+                  max by (namespace, pod, container, cluster) (
+                    kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}
+                  ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
+                    kube_pod_status_phase{phase=~"Pending|Running"} == 1
+                  )
+              )
+          )
+        record: namespace_cpu:kube_pod_container_resource_limits:sum
+      - expr: |-
+          max by (cluster, namespace, workload, pod) (
+            label_replace(
+              label_replace(
+                kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"},
+                "replicaset", "$1", "owner_name", "(.*)"
+              ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (
+                1, max by (replicaset, namespace, owner_name) (
+                  kube_replicaset_owner{job="kube-state-metrics"}
+                )
+              ),
+              "workload", "$1", "owner_name", "(.*)"
+            )
+          )
+        labels:
+          workload_type: deployment
+        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="DaemonSet"},
+              "workload", "$1", "owner_name", "(.*)"
+            )
+          )
+        labels:
+          workload_type: daemonset
+        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="StatefulSet"},
+              "workload", "$1", "owner_name", "(.*)"
+            )
+          )
+        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