feat: add recoding rules

2026-07-13 08:02:40 +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 +1,7 @@
+# Recording Rules
+
+Recording rules are pre-defined queries, often complex or computationally expensive, that are
+evaluated periodically to create new, pre-computed time series metrics.
+
+These rules store the results in a metric backend, significantly speeding up queries for dashboards
+and other alerts, and reducing system load by avoiding the re-computation of data.
@@ -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
@@ -0,0 +1,128 @@
+groups:
+  - name: kube-prometheus-node-recording.rules
+    rules:
+      - expr:
+          sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY
+          (instance)
+        record: instance:node_cpu:rate:sum
+      - expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
+        record: instance:node_network_receive_bytes:rate:sum
+      - expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
+        record: instance:node_network_transmit_bytes:rate:sum
+      - expr:
+          sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT
+          (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance,
+          cpu)) BY (instance)
+        record: instance:node_cpu:ratio
+      - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
+        record: cluster:node_cpu:sum_rate5m
+      - expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
+        record: cluster:node_cpu:ratio
+
+  - name: node-exporter.rules
+    rules:
+      - expr: |-
+          count without (cpu, mode) (
+            node_cpu_seconds_total{job="node-exporter",mode="idle"}
+          )
+        record: instance:node_num_cpu:sum
+      - expr: |-
+          1 - avg without (cpu) (
+            sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m]))
+          )
+        record: instance:node_cpu_utilisation:rate5m
+      - expr: |-
+          (
+            node_load1{job="node-exporter"}
+          /
+            instance:node_num_cpu:sum{job="node-exporter"}
+          )
+        record: instance:node_load1_per_cpu:ratio
+      - expr: |-
+          1 - (
+            (
+              node_memory_MemAvailable_bytes{job="node-exporter"}
+              or
+              (
+                node_memory_Buffers_bytes{job="node-exporter"}
+                +
+                node_memory_Cached_bytes{job="node-exporter"}
+                +
+                node_memory_MemFree_bytes{job="node-exporter"}
+                +
+                node_memory_Slab_bytes{job="node-exporter"}
+              )
+            )
+          /
+            node_memory_MemTotal_bytes{job="node-exporter"}
+          )
+        record: instance:node_memory_utilisation:ratio
+      - expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m])
+        record: instance:node_vmstat_pgmajfault:rate5m
+      - expr:
+          rate(node_disk_io_time_seconds_total{job="node-exporter",
+          device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
+        record: instance_device:node_disk_io_time_seconds:rate5m
+      - expr:
+          rate(node_disk_io_time_weighted_seconds_total{job="node-exporter",
+          device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
+        record: instance_device:node_disk_io_time_weighted_seconds:rate5m
+      - expr: |-
+          sum without (device) (
+            rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m])
+          )
+        record: instance:node_network_receive_bytes_excluding_lo:rate5m
+      - expr: |-
+          sum without (device) (
+            rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m])
+          )
+        record: instance:node_network_transmit_bytes_excluding_lo:rate5m
+      - expr: |-
+          sum without (device) (
+            rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m])
+          )
+        record: instance:node_network_receive_drop_excluding_lo:rate5m
+      - expr: |-
+          sum without (device) (
+            rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m])
+          )
+        record: instance:node_network_transmit_drop_excluding_lo:rate5m
+
+  - name: node.rules
+    rules:
+      - expr: |-
+          topk by(cluster, namespace, pod) (1,
+            max by (cluster, node, namespace, pod) (
+              label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
+          ))
+        record: "node_namespace_pod:kube_pod_info:"
+      - expr: |-
+          count by (cluster, node) (
+            node_cpu_seconds_total{mode="idle",job="node-exporter"}
+            * on (namespace, pod) group_left(node)
+            topk by(namespace, pod) (1, node_namespace_pod:kube_pod_info:)
+          )
+        record: node:node_num_cpu:sum
+      - expr: |-
+          sum(
+            node_memory_MemAvailable_bytes{job="node-exporter"} or
+            (
+              node_memory_Buffers_bytes{job="node-exporter"} +
+              node_memory_Cached_bytes{job="node-exporter"} +
+              node_memory_MemFree_bytes{job="node-exporter"} +
+              node_memory_Slab_bytes{job="node-exporter"}
+            )
+          ) by (cluster)
+        record: :node_memory_MemAvailable_bytes:sum
+      - expr: |-
+          avg by (cluster, node) (
+            sum without (mode) (
+              rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal",job="node-exporter"}[5m])
+            )
+          )
+        record: node:node_cpu_utilization:ratio_rate5m
+      - expr: |-
+          avg by (cluster) (
+            node:node_cpu_utilization:ratio_rate5m
+          )
+        record: cluster:node_cpu:ratio_rate5m