apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  labels:
    prometheus: k8s
    role: alert-rules
  name: prometheus-k8s-rules
  namespace: monitoring
spec:
  groups:
  - name: node-exporter.rules
    rules:
    - expr: |
        count without (cpu) (
          count without (mode) (
            node_cpu_seconds_total{job="node-exporter"}
          )
        )
      record: instance:node_num_cpu:sum
    - expr: |
        1 - avg without (cpu, mode) (
          rate(node_cpu_seconds_total{job="node-exporter", mode="idle"}[1m])
        )
      record: instance:node_cpu_utilisation:rate1m
    - 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"}
        /
          node_memory_MemTotal_bytes{job="node-exporter"}
        )
      record: instance:node_memory_utilisation:ratio
    - expr: |
        rate(node_vmstat_pgmajfault{job="node-exporter"}[1m])
      record: instance:node_vmstat_pgmajfault:rate1m
    - expr: |
        rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])
      record: instance_device:node_disk_io_time_seconds:rate1m
    - expr: |
        rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])
      record: instance_device:node_disk_io_time_weighted_seconds:rate1m
    - expr: |
        sum without (device) (
          rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[1m])
        )
      record: instance:node_network_receive_bytes_excluding_lo:rate1m
    - expr: |
        sum without (device) (
          rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[1m])
        )
      record: instance:node_network_transmit_bytes_excluding_lo:rate1m
    - expr: |
        sum without (device) (
          rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[1m])
        )
      record: instance:node_network_receive_drop_excluding_lo:rate1m
    - expr: |
        sum without (device) (
          rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m])
        )
      record: instance:node_network_transmit_drop_excluding_lo:rate1m
  - name: kube-apiserver.rules
    rules:
    - expr: |
        histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
      labels:
        quantile: "0.99"
      record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
      labels:
        quantile: "0.9"
      record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
      labels:
        quantile: "0.5"
      record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
  - name: k8s.rules
    rules:
    - expr: |
        sum(rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container!="POD"}[5m])) by (namespace)
      record: namespace:container_cpu_usage_seconds_total:sum_rate
    - expr: |
        sum by (namespace, pod, container) (
          rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container!="POD"}[5m])
        ) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
      record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate
    - expr: |
        container_memory_working_set_bytes{job="kubelet", image!=""}
        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
      record: node_namespace_pod_container:container_memory_working_set_bytes
    - expr: |
        container_memory_rss{job="kubelet", image!=""}
        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
      record: node_namespace_pod_container:container_memory_rss
    - expr: |
        container_memory_cache{job="kubelet", image!=""}
        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
      record: node_namespace_pod_container:container_memory_cache
    - expr: |
        container_memory_swap{job="kubelet", image!=""}
        * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
      record: node_namespace_pod_container:container_memory_swap
    - expr: |
        sum(container_memory_usage_bytes{job="kubelet", image!="", container!="POD"}) by (namespace)
      record: namespace:container_memory_usage_bytes:sum
    - expr: |
        sum by (namespace, label_name) (
            sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)) by (namespace, pod)
          * on (namespace, pod)
            group_left(label_name) kube_pod_labels{job="kube-state-metrics"}
        )
      record: namespace:kube_pod_container_resource_requests_memory_bytes:sum
    - expr: |
        sum by (namespace, label_name) (
            sum(kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)) by (namespace, pod)
          * on (namespace, pod)
            group_left(label_name) kube_pod_labels{job="kube-state-metrics"}
        )
      record: namespace:kube_pod_container_resource_requests_cpu_cores:sum
    - expr: |
        sum(
          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) kube_replicaset_owner{job="kube-state-metrics"},
            "workload", "$1", "owner_name", "(.*)"
          )
        ) by (namespace, workload, pod)
      labels:
        workload_type: deployment
      record: mixin_pod_workload
    - expr: |
        sum(
          label_replace(
            kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"},
            "workload", "$1", "owner_name", "(.*)"
          )
        ) by (namespace, workload, pod)
      labels:
        workload_type: daemonset
      record: mixin_pod_workload
    - expr: |
        sum(
          label_replace(
            kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"},
            "workload", "$1", "owner_name", "(.*)"
          )
        ) by (namespace, workload, pod)
      labels:
        workload_type: statefulset
      record: mixin_pod_workload
  - name: kube-scheduler.rules
    rules:
    - expr: |
        histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.99"
      record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.99"
      record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.99"
      record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.9"
      record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.9"
      record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.9"
      record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.5"
      record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.5"
      record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile
    - expr: |
        histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
      labels:
        quantile: "0.5"
      record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
  - name: node.rules
    rules:
    - expr: sum(min(kube_pod_info) by (node))
      record: ':kube_pod_info_node_count:'
    - expr: |
        max(label_replace(kube_pod_info{job="kube-state-metrics"}, "pod", "$1", "pod", "(.*)")) by (node, namespace, pod)
      record: 'node_namespace_pod:kube_pod_info:'
    - expr: |
        count by (node) (sum by (node, cpu) (
          node_cpu_seconds_total{job="node-exporter"}
        * on (namespace, pod) group_left(node)
          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"}
          )
        )
      record: :node_memory_MemAvailable_bytes:sum
  - name: kube-prometheus-node-recording.rules
    rules:
    - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY
        (instance)
      record: instance:node_cpu:rate:sum
    - expr: sum((node_filesystem_size_bytes{mountpoint="/"} - node_filesystem_free_bytes{mountpoint="/"}))
        BY (instance)
      record: instance:node_filesystem_usage: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"}[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"}[5m]))
      record: cluster:node_cpu:sum_rate5m
    - expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total)
        BY (instance, cpu))
      record: cluster:node_cpu:ratio
  - name: node-exporter
    rules:
    - alert: NodeFilesystemSpaceFillingUp
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available space left and is filling
          up.
        summary: "預計文件系統將在接下來的24小時內用完空間。"
      expr: |
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 40
        and
          predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemSpaceFillingUp
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available space left and is filling
          up fast.
        summary: "預計文件系統將在接下來的4個小時內用完空間。"
      expr: |
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 20
        and
          predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeFilesystemAlmostOutOfSpace
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available space left.
        summary: "文件系統剩餘空間不到5％。"
      expr: |
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 5
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemAlmostOutOfSpace
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available space left.
        summary: "文件系統剩餘空間不到3％。"
      expr: |
        (
          node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 3
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeFilesystemFilesFillingUp
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available inodes left and is filling
          up.
        summary: "預計文件系統將在接下來的24小時內用盡inodes。"
      expr: |
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 40
        and
          predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemFilesFillingUp
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available inodes left and is filling
          up fast.
        summary: "預計文件系統將在接下來的4小時內用盡inodes。"
      expr: |
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 20
        and
          predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeFilesystemAlmostOutOfFiles
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available inodes left.
        summary: "文件系統僅剩不到5％的inodes。"
      expr: |
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 5
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: warning
    - alert: NodeFilesystemAlmostOutOfFiles
      annotations:
        platform: "測試平台"
        description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
          has only {{ printf "%.2f" $value }}% available inodes left.
        summary: "文件系統僅剩不到3％的inodes。"
      expr: |
        (
          node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 3
        and
          node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
        )
      for: 1h
      labels:
        severity: critical
    - alert: NodeNetworkReceiveErrs
      annotations:
        platform: "測試平台"
        description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
          {{ printf "%.0f" $value }} receive errors in the last two minutes.'
        summary: "網路介面報告許多接收錯誤。"
      expr: |
        increase(node_network_receive_errs_total[2m]) > 10
      for: 1h
      labels:
        severity: warning
    - alert: NodeNetworkTransmitErrs
      annotations:
        platform: "測試平台"
        description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
          {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
        summary: "網路介面報告許多傳輸錯誤。"
      expr: |
        increase(node_network_transmit_errs_total[2m]) > 10
      for: 1h
      labels:
        severity: warning
  - name: kubernetes-apps
    rules:
    - alert: KubePodCrashLooping
      annotations:
        platform: "測試平台"
        message: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
          }}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
      expr: |
        rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) * 60 * 5 > 0
      for: 15m
      labels:
        severity: critical
    - alert: KubePodNotReady
      annotations:
        platform: "測試平台"
        message: "Pod {{$labels.namespace}}/{{$labels.pod}}處於未就緒狀態的時間超過15分鐘。"
      expr: |
        sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown"} * on(namespace, pod) group_left(owner_kind) kube_pod_owner{owner_kind!="Job"}) > 0
      for: 15m
      labels:
        severity: critical
    - alert: KubeDeploymentGenerationMismatch
      annotations:
        platform: "測試平台"
        message: "Deployment {{$labels.namespace}}/{{$labels.deployment}}生成不匹配，這表明Deployment已失敗但尚未回滾。"
      expr: |
        kube_deployment_status_observed_generation{job="kube-state-metrics"}
          !=
        kube_deployment_metadata_generation{job="kube-state-metrics"}
      for: 15m
      labels:
        severity: critical
    - alert: KubeDeploymentReplicasMismatch
      annotations:
        platform: "測試平台"
        message: "Deployment{{$labels.namespace}}/{{$labels.deployment}}超過15分鐘未匹配預期的副本數。"
      expr: |
        kube_deployment_spec_replicas{job="kube-state-metrics"}
          !=
        kube_deployment_status_replicas_available{job="kube-state-metrics"}
      for: 15m
      labels:
        severity: critical
    - alert: KubeStatefulSetReplicasMismatch
      annotations:
        platform: "測試平台"
        message: "StatefulSet {{$labels.namespace}}/{{$labels.statefulset}}超過15分鐘未匹配預期的副本數。"
      expr: |
        kube_statefulset_status_replicas_ready{job="kube-state-metrics"}
          !=
        kube_statefulset_status_replicas{job="kube-state-metrics"}
      for: 15m
      labels:
        severity: critical
    - alert: KubeStatefulSetGenerationMismatch
      annotations:
        platform: "測試平台"
        message: "StatefulSet {{$labels.namespace}}/{{$labels.statefulset}}生成不匹配，這表明StatefulSet已失敗但尚未回滾。"
      expr: |
        kube_statefulset_status_observed_generation{job="kube-state-metrics"}
          !=
        kube_statefulset_metadata_generation{job="kube-state-metrics"}
      for: 15m
      labels:
        severity: critical
    - alert: KubeStatefulSetUpdateNotRolledOut
      annotations:
        platform: "測試平台"
        message: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update
          has not been rolled out.
      expr: |
        max without (revision) (
          kube_statefulset_status_current_revision{job="kube-state-metrics"}
            unless
          kube_statefulset_status_update_revision{job="kube-state-metrics"}
        )
          *
        (
          kube_statefulset_replicas{job="kube-state-metrics"}
            !=
          kube_statefulset_status_replicas_updated{job="kube-state-metrics"}
        )
      for: 15m
      labels:
        severity: critical
    - alert: KubeDaemonSetRolloutStuck
      annotations:
        platform: "測試平台"
        message: Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet
          {{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready.
      expr: |
        kube_daemonset_status_number_ready{job="kube-state-metrics"}
          /
        kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} < 1.00
      for: 15m
      labels:
        severity: critical
    - alert: KubeContainerWaiting
      annotations:
        platform: "測試平台"
        message: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}}
          has been in waiting state for longer than 1 hour.
      expr: |
        sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
      for: 1h
      labels:
        severity: warning
    - alert: KubeDaemonSetNotScheduled
      annotations:
        platform: "測試平台"
        message: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
          }} are not scheduled.'
      expr: |
        kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
          -
        kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0
      for: 10m
      labels:
        severity: warning
    - alert: KubeDaemonSetMisScheduled
      annotations:
        platform: "測試平台"
        message: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
          }} are running where they are not supposed to run.'
      expr: |
        kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
      for: 10m
      labels:
        severity: warning
    - alert: KubeCronJobRunning
      annotations:
        platform: "測試平台"
        message: CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more
          than 1h to complete.
      expr: |
        time() - kube_cronjob_next_schedule_time{job="kube-state-metrics"} > 3600
      for: 1h
      labels:
        severity: warning
    - alert: KubeJobCompletion
      annotations:
        platform: "測試平台"
        message: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more
          than one hour to complete.
      expr: |
        kube_job_spec_completions{job="kube-state-metrics"} - kube_job_status_succeeded{job="kube-state-metrics"}  > 0
      for: 1h
      labels:
        severity: warning
    - alert: KubeJobFailed
      annotations:
        platform: "測試平台"
        message: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
      expr: |
        kube_job_failed{job="kube-state-metrics"}  > 0
      for: 15m
      labels:
        severity: warning
    - alert: KubeHpaReplicasMismatch
      annotations:
        platform: "測試平台"
        message: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the
          desired number of replicas for longer than 15 minutes.
      expr: |
        (kube_hpa_status_desired_replicas{job="kube-state-metrics"}
          !=
        kube_hpa_status_current_replicas{job="kube-state-metrics"})
          and
        changes(kube_hpa_status_current_replicas[15m]) == 0
      for: 15m
      labels:
        severity: warning
    - alert: KubeHpaMaxedOut
      annotations:
        platform: "測試平台"
        message: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at
          max replicas for longer than 15 minutes.
      expr: |
        kube_hpa_status_current_replicas{job="kube-state-metrics"}
          ==
        kube_hpa_spec_max_replicas{job="kube-state-metrics"}
      for: 15m
      labels:
        severity: warning
  - name: kubernetes-resources
    rules:
    - alert: KubeCPUOvercommit
      annotations:
        platform: "測試平台"
        message: "群集已超額使用Pod的CPU資源請求，因此無法容忍節點故障。"
      expr: |
        sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum)
          /
        sum(kube_node_status_allocatable_cpu_cores)
          >
        (count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)
      for: 5m
      labels:
        severity: warning
    - alert: KubeMemOvercommit
      annotations:
        platform: "測試平台"
        message: "群集已過量使用Pod的記憶體資源請求，因此無法容忍節點故障。"
      expr: |
        sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum)
          /
        sum(kube_node_status_allocatable_memory_bytes)
          >
        (count(kube_node_status_allocatable_memory_bytes)-1)
          /
        count(kube_node_status_allocatable_memory_bytes)
      for: 5m
      labels:
        severity: warning
    - alert: KubeCPUOvercommit
      annotations:
        platform: "測試平台"
        message: "群集已超額使用了對命名空間的CPU資源請求。"
      expr: |
        sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"})
          /
        sum(kube_node_status_allocatable_cpu_cores)
          > 1.5
      for: 5m
      labels:
        severity: warning
    - alert: KubeMemOvercommit
      annotations:
        platform: "測試平台"
        message: "群集已過量使用了對命名空間的記憶體資源請求。"
      expr: |
        sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"})
          /
        sum(kube_node_status_allocatable_memory_bytes{job="node-exporter"})
          > 1.5
      for: 5m
      labels:
        severity: warning
    - alert: KubeQuotaExceeded
      annotations:
        platform: "測試平台"
        message: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
          }} of its {{ $labels.resource }} quota.
      expr: |
        kube_resourcequota{job="kube-state-metrics", type="used"}
          / ignoring(instance, job, type)
        (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
          > 0.90
      for: 15m
      labels:
        severity: warning
    # - alert: CPUThrottlingHigh
      # annotations:
        # message: '{{ $value | humanizePercentage }} throttling of CPU in namespace
          # {{ $labels.namespace }} for container {{ $labels.container }} in pod {{
          # $labels.pod }}.'
      # expr: |
        # sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace)
          # /
        # sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)
          # > ( 25 / 100 )
      # for: 15m
      # labels:
        # severity: warning
  - name: kubernetes-storage
    rules:
    - alert: KubePersistentVolumeUsageCritical
      annotations:
        platform: "測試平台"
        message: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim
          }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage
          }} free.
      expr: |
        kubelet_volume_stats_available_bytes{job="kubelet"}
          /
        kubelet_volume_stats_capacity_bytes{job="kubelet"}
          < 0.03
      for: 1m
      labels:
        severity: critical
    - alert: KubePersistentVolumeFullInFourDays
      annotations:
        platform: "測試平台"
        message: "根據最近的抽樣，{{$labels.persistentvolumeclaim}}在命名空間{{$labels.namespace}}中聲明的PersistentVolume預計將在四天內填滿，目前{{$value | humanizePercentage}}可用。"
      expr: |
        (
          kubelet_volume_stats_available_bytes{job="kubelet"}
            /
          kubelet_volume_stats_capacity_bytes{job="kubelet"}
        ) < 0.15
        and
        predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0
      for: 1h
      labels:
        severity: critical
    - alert: KubePersistentVolumeErrors
      annotations:
        platform: "測試平台"
        message: The persistent volume {{ $labels.persistentvolume }} has status {{
          $labels.phase }}.
      expr: |
        kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
      for: 5m
      labels:
        severity: critical
  - name: kubernetes-system
    rules:
    - alert: KubeVersionMismatch
      annotations:
        platform: "測試平台"
        message: There are {{ $value }} different semantic versions of Kubernetes
          components running.
      expr: |
        count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"gitVersion","$1","gitVersion","(v[0-9]*.[0-9]*.[0-9]*).*"))) > 1
      for: 15m
      labels:
        severity: warning
    - alert: KubeClientErrors
      annotations:
        platform: "測試平台"
        message: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance
          }}' is experiencing {{ $value | humanizePercentage }} errors.'
      expr: |
        (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job)
          /
        sum(rate(rest_client_requests_total[5m])) by (instance, job))
        > 0.01
      for: 15m
      labels:
        severity: warning
  - name: kubernetes-system-apiserver
    rules:
    - alert: KubeAPILatencyHigh
      annotations:
        platform: "測試平台"
        message: The API server has a 99th percentile latency of {{ $value }} seconds
          for {{ $labels.verb }} {{ $labels.resource }}.
      expr: |
        cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|PROXY|CONNECT"} > 1
      for: 10m
      labels:
        severity: warning
    - alert: KubeAPILatencyHigh
      annotations:
        platform: "測試平台"
        message: The API server has a 99th percentile latency of {{ $value }} seconds
          for {{ $labels.verb }} {{ $labels.resource }}.
      expr: |
        cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|PROXY|CONNECT"} > 4
      for: 10m
      labels:
        severity: critical
    - alert: KubeAPIErrorsHigh
      annotations:
        platform: "測試平台"
        message: API server is returning errors for {{ $value | humanizePercentage
          }} of requests.
      expr: |
        sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m]))
          /
        sum(rate(apiserver_request_total{job="apiserver"}[5m])) > 0.03
      for: 10m
      labels:
        severity: critical
    - alert: KubeAPIErrorsHigh
      annotations:
        platform: "測試平台"
        message: API server is returning errors for {{ $value | humanizePercentage
          }} of requests.
      expr: |
        sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m]))
          /
        sum(rate(apiserver_request_total{job="apiserver"}[5m])) > 0.01
      for: 10m
      labels:
        severity: warning
    - alert: KubeAPIErrorsHigh
      annotations:
        platform: "測試平台"
        message: API server is returning errors for {{ $value | humanizePercentage
          }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource
          }}.
      expr: |
        sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb)
          /
        sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.10
      for: 10m
      labels:
        severity: critical
    - alert: KubeAPIErrorsHigh
      annotations:
        platform: "測試平台"
        message: API server is returning errors for {{ $value | humanizePercentage
          }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource
          }}.
      expr: |
        sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb)
          /
        sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.05
      for: 10m
      labels:
        severity: warning
    - alert: KubeClientCertificateExpiration
      annotations:
        platform: "測試平台"
        message: "用於驗證apiserver的客戶端證書的有效期限少於7.0天。"
      expr: |
        apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
      labels:
        severity: warning
    - alert: KubeClientCertificateExpiration
      annotations:
        platform: "測試平台"
        message: "用於驗證apiserver的客戶端證書的有效期限少於24.0小時。"
      expr: |
        apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
      labels:
        severity: critical
    - alert: KubeAPIDown
      annotations:
        platform: "測試平台"
        message: "KubeAPI已從Prometheus目標發現中消失。"
      expr: |
        absent(up{job="apiserver"} == 1)
      for: 15m
      labels:
        severity: critical
  - name: kubernetes-system-kubelet
    rules:
    - alert: KubeNodeNotReady
      annotations:
        platform: "測試平台"
        message: "{{$labels.node}}尚未準備就緒超過15分鐘。"
      expr: |
        kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
      for: 15m
      labels:
        severity: warning
    - alert: KubeNodeUnreachable
      annotations:
        platform: "測試平台"
        message: "{{$labels.node}}無法訪問，某些工作負荷可能會重新安排。"
      expr: |
        kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} == 1
      labels:
        severity: warning
    - alert: KubeletTooManyPods
      annotations:
        platform: "測試平台"
        message: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage
          }} of its Pod capacity.
      expr: |
        max(max(kubelet_running_pod_count{job="kubelet"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"}) by(node) > 0.95
      for: 15m
      labels:
        severity: warning
    - alert: KubeletDown
      annotations:
        platform: "測試平台"
        message: "Kubelet已從Prometheus目標發現中消失。"
      expr: |
        absent(up{job="kubelet"} == 1)
      for: 15m
      labels:
        severity: critical
  # - name: kubernetes-system-scheduler
    # rules:
    # - alert: KubeSchedulerDown
      # annotations:
        # message: KubeScheduler has disappeared from Prometheus target discovery.
        # runbook_url: //github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown
      # expr: |
        # absent(up{job="kube-scheduler"} == 1)
      # for: 15m
      # labels:
        # severity: critical
  # - name: kubernetes-system-controller-manager
    # rules:
    # - alert: KubeControllerManagerDown
      # annotations:
        # message: KubeControllerManager has disappeared from Prometheus target discovery.
        # runbook_url: //github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown
      # expr: |
        # absent(up{job="kube-controller-manager"} == 1)
      # for: 15m
      # labels:
        # severity: critical
  - name: prometheus
    rules:
    - alert: PrometheusBadConfig
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to
          reload its configuration.
        summary: "Prometheus配置重新載入失敗。"
      expr: |
        # Without max_over_time, failed scrapes could create false negatives, see
        # //www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
        max_over_time(prometheus_config_last_reload_successful{job="prometheus-k8s",namespace="monitoring"}[5m]) == 0
      for: 10m
      labels:
        severity: critical
    - alert: PrometheusNotificationQueueRunningFull
      annotations:
        platform: "測試平台"
        description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}}
          is running full.
        summary: "Prometheus警報通知隊列預計將在30m以內用完。"
      expr: |
        # Without min_over_time, failed scrapes could create false negatives, see
        # //www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
        (
          predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s",namespace="monitoring"}[5m], 60 * 30)
        >
          min_over_time(prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="monitoring"}[5m])
        )
      for: 15m
      labels:
        severity: warning
    - alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
      annotations:
        platform: "測試平台"
        description: '{{ printf "%.1f" $value }}% errors while sending alerts from
          Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.'
        summary: "Prometheus在將警報發送到特定的Alertmanager時遇到了超過1％的錯誤。"
      expr: |
        (
          rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
        /
          rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
        )
        * 100
        > 1
      for: 15m
      labels:
        severity: warning
    - alert: PrometheusErrorSendingAlertsToAnyAlertmanager
      annotations:
        platform: "測試平台"
        description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts
          from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
        summary: "Prometheus在將警報發送到任何Alertmanager時遇到3％以上的錯誤。"
      expr: |
        min without(alertmanager) (
          rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
        /
          rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
        )
        * 100
        > 3
      for: 15m
      labels:
        severity: critical
    - alert: PrometheusNotConnectedToAlertmanagers
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected
          to any Alertmanagers.
        summary: "Prometheus未與任何Alertmanager連接。"
      expr: |
        # Without max_over_time, failed scrapes could create false negatives, see
        # //www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
        max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s",namespace="monitoring"}[5m]) < 1
      for: 10m
      labels:
        severity: warning
    - alert: PrometheusTSDBReloadsFailing
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
          {{$value | humanize}} reload failures over the last 3h.
        summary: "Prometheus從磁碟重新載入塊時遇到問題。"
      expr: |
        increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
      for: 4h
      labels:
        severity: warning
    - alert: PrometheusTSDBCompactionsFailing
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
          {{$value | humanize}} compaction failures over the last 3h.
        summary: "Prometheus在壓縮塊時遇到問題。"
      expr: |
        increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
      for: 4h
      labels:
        severity: warning
    - alert: PrometheusNotIngestingSamples
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting
          samples.
        summary: "Prometheus沒有獲取到樣本"
      expr: |
        rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
      for: 10m
      labels:
        severity: warning
    - alert: PrometheusDuplicateTimestamps
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
          {{ printf "%.4g" $value  }} samples/s with different values but duplicated
          timestamp.
        summary: "Prometheus正在刪除帶有重複時間戳的樣本。"
      expr: |
        rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
      for: 10m
      labels:
        severity: warning
    - alert: PrometheusOutOfOrderTimestamps
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
          {{ printf "%.4g" $value  }} samples/s with timestamps arriving out of order.
        summary: "Prometheus丟棄帶有亂序時間戳的樣本。"
      expr: |
        rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
      for: 10m
      labels:
        severity: warning
    - alert: PrometheusRemoteStorageFailures
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send
          {{ printf "%.1f" $value }}% of the samples to queue {{$labels.queue}}.
        summary: "Prometheus無法將樣本發送到遠程存儲。"
      expr: |
        (
          rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m])
        /
          (
            rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m])
          +
            rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m])
          )
        )
        * 100
        > 1
      for: 15m
      labels:
        severity: critical
    - alert: PrometheusRemoteWriteBehind
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
          is {{ printf "%.1f" $value }}s behind for queue {{$labels.queue}}.
        summary: "Prometheus遠程寫入落後了。"
      expr: |
        # Without max_over_time, failed scrapes could create false negatives, see
        # //www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
        (
          max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
        - on(job, instance) group_right
          max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
        )
        > 120
      for: 15m
      labels:
        severity: critical
    - alert: PrometheusRemoteWriteDesiredShards
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
          desired shards calculation wants to run {{ $value }} shards, which is more
          than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
          $labels.instance | query | first | value }}.
        summary: "Prometheus遠程寫入所需的分片計算要比配置的最大分片運行更多。"
      expr: |
        # Without max_over_time, failed scrapes could create false negatives, see
        # //www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
        (
          max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m])
        >
          max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m])
        )
      for: 15m
      labels:
        severity: warning
    - alert: PrometheusRuleFailures
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to
          evaluate {{ printf "%.0f" $value }} rules in the last 5m.
        summary: "Prometheus無法通過規則評估。"
      expr: |
        increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
      for: 15m
      labels:
        severity: critical
    - alert: PrometheusMissingRuleEvaluations
      annotations:
        platform: "測試平台"
        description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{
          printf "%.0f" $value }} rule group evaluations in the last 5m.
        summary: "Prometheus由於規則組評估速度慢而缺少規則評估。"
      expr: |
        increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
      for: 15m
      labels:
        severity: warning
  - name: alertmanager.rules
    rules:
    - alert: AlertmanagerConfigInconsistent
      annotations:
        platform: "測試平台"
        message: "Alertmanager {{$labels.service}}實例的配置不同步。"
      expr: |
        count_values("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"}) BY (service) / ON(service) GROUP_LEFT() label_replace(max(prometheus_operator_spec_replicas{job="prometheus-operator",namespace="monitoring",controller="alertmanager"}) by (name, job, namespace, controller), "service", "alertmanager-$1", "name", "(.*)") != 1
      for: 5m
      labels:
        severity: critical
    - alert: AlertmanagerFailedReload
      annotations:
        platform: "測試平台"
        message: "Alertmanager {{$labels.namespace}}/{{$labels.pod}}重新載入配置失敗。"
      expr: |
        alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"} == 0
      for: 10m
      labels:
        severity: warning
    - alert: AlertmanagerMembersInconsistent
      annotations:
        platform: "測試平台"
        message: "Alertmanager尚未找到集群的所有其他成員。"
      expr: |
        alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}
          != on (service) GROUP_LEFT()
        count by (service) (alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"})
      for: 5m
      labels:
        severity: critical
  # - name: general.rules
    # rules:
    # - alert: TargetDown
      # annotations:
        # platform: "測試平台"
        # message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }} targets in
          # {{ $labels.namespace }} namespace are down.'
      # expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job,
        # namespace, service)) > 10
      # for: 10m
      # labels:
        # severity: warning
    # - alert: Watchdog
      # annotations:
        # platform: "測試平台"
        # message: "此警報始終處於觸髮狀態，旨在確保整個警報管道均正常運行。"
        # runbook_url: //github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md
      # expr: vector(1)
      # labels:
        # severity: none
  - name: node-time
    rules:
    - alert: ClockSkewDetected
      annotations:
        platform: "測試平台"
        message: Clock skew detected on node-exporter {{ $labels.namespace }}/{{ $labels.pod
          }}. Ensure NTP is configured correctly on this host.
      expr: |
        abs(node_timex_offset_seconds{job="node-exporter"}) > 0.05
      for: 2m
      labels:
        severity: warning
  - name: node-network
    rules:
    - alert: NodeNetworkInterfaceFlapping
      annotations:
        platform: "測試平台"
        message: Network interface "{{ $labels.device }}" changing it's up status
          often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}"
      expr: |
        changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2
      for: 2m
      labels:
        severity: warning
  - name: prometheus-operator
    rules:
    - alert: PrometheusOperatorReconcileErrors
      annotations:
        platform: "測試平台"
        message: Errors while reconciling {{ $labels.controller }} in {{ $labels.namespace
          }} Namespace.
      expr: |
        rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
      for: 10m
      labels:
        severity: warning
    - alert: PrometheusOperatorNodeLookupErrors
      annotations:
        platform: "測試平台"
        message: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
      expr: |
        rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
      for: 10m
      labels:
        severity: warning

- job_name: 'node_export_others'
  static_configs:
    - targets:
      - *.*.*.118:9591
      - *.*.*.137:9591
      - *.*.*.138:9591
      - *.*.*.139:9591
      - *.*.*.153:9591
      - *.*.*.154:9591
      - *.*.*.156:9591
      - *.*.*.159:9591
      - *.*.*.166:9591
      - *.*.*.167:9591
      - *.*.*.168:9591
      - *.*.*.169:9591
      - *.*.*.175:9591
      - *.*.*.177:9591
      - *.*.*.179:9591
      - *.*.*.180:9591
      - *.*.*.181:9591

- job_name: 'nginx'
  static_configs:
    - targets:
      - *.*.*.159:9593

- job_name: 'mysql'
  static_configs:
    - targets:
      - *.*.*.156:9592

- job_name: 'pushgateway-flink'
  static_configs:
    - targets:
      - *.*.*.137:9091

- job_name: 'kafka_jmx_export'
  static_configs:
    - targets:
      - *.*.*.118:9991
      - *.*.*.138:9991
      - *.*.*.139:9991

- job_name: 'zookeeper_cdh_export'
  static_configs:
    - targets:
      - *.*.*.118:9595
      - *.*.*.138:9595
      - *.*.*.139:9595

- job_name: 'hdfs_namenode_cdh'
  static_configs:
    - targets:
      - *.*.*.137:9600
      - *.*.*.139:9600

- job_name: 'hdfs_datanode_cdh'
  static_configs:
    - targets:
      - *.*.*.118:9601
      - *.*.*.138:9601
      - *.*.*.139:9601

- job_name: 'yarn_resourcemanager_cdh'
  static_configs:
    - targets:
      - *.*.*.137:9602
      - *.*.*.139:9602

- job_name: 'yarn_nodemanager_cdh'
  static_configs:
    - targets:
      - *.*.*.118:9603
      - *.*.*.138:9603
      - *.*.*.139:9603

- job_name: 'redis_exporter'
  static_configs:
    - targets:
      - *.*.*.166:9594

- job_name: 'elasticsearch'
  metrics_path: "/_prometheus/metrics"
  static_configs:
  - targets:
    - *.*.*.169:8970
    - *.*.*.175:8970
    - *.*.*.177:8970
    
- job_name: 'nacos'
  metrics_path: '/nacos/actuator/prometheus'
  static_configs:
    - targets:
      - *.*.*.166:8848
      - *.*.*.167:8848
      - *.*.*.168:8848
      
- job_name: 'redis_exporter_targets'
  static_configs:
    - targets:
      - redis://*.*.*.179:6179
      - redis://*.*.*.180:6179
      - redis://*.*.*.181:6179
      - redis://*.*.*.179:6178
      - redis://*.*.*.180:6178
      - redis://*.*.*.181:6178
      - redis://*.*.*.179:6177
      - redis://*.*.*.179:6176
  metrics_path: /scrape
  relabel_configs:
    - source_labels: [__address__]
      target_label: __param_target
    - source_labels: [__param_target]
      target_label: instance
    - target_label: __address__
      replacement: *.*.*.166:9594

{
  "annotations": {
    "list": [
      {
        "builtIn": 1,
        "datasource": "-- Grafana --",
        "enable": true,
        "hide": true,
        "iconColor": "rgba(0, 211, 255, 1)",
        "name": "Annotations & Alerts",
        "type": "dashboard"
      }
    ]
  },
  "description": "This dashboard provides cluster admins with the ability to monitor nodes and identify workload bottlenecks. It can be deployed with PSPs enabled using the following helm chart - //github.com/pivotal-cf/charts-grafana",
  "editable": true,
  "gnetId": 10000,
  "graphTooltip": 0,
  "id": 102,
  "iteration": 1597137794957,
  "links": [],
  "panels": [
    {
      "collapsed": false,
      "datasource": null,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 0
      },
      "id": 34,
      "panels": [],
      "repeat": null,
      "title": "Summary",
      "type": "row"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": true,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "editable": true,
      "error": false,
      "format": "percent",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": true,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 5,
        "w": 8,
        "x": 0,
        "y": 1
      },
      "height": "180px",
      "id": 4,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": "",
      "postfixFontSize": "50%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}) / sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"}) * 100",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "65, 90",
      "title": "Cluster memory usage",
      "type": "singlestat",
      "valueFontSize": "80%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": true,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "percent",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": true,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 5,
        "w": 8,
        "x": 8,
        "y": 1
      },
      "height": "180px",
      "id": 6,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": "",
      "postfixFontSize": "50%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (rate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[$interval])) / sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"}) * 100",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "",
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "65, 90",
      "title": "Cluster CPU usage",
      "type": "singlestat",
      "valueFontSize": "80%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": true,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "percent",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": true,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 5,
        "w": 8,
        "x": 16,
        "y": 1
      },
      "height": "180px",
      "id": 7,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": "",
      "postfixFontSize": "50%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (container_fs_usage_bytes{id=\"/\"}) / sum (container_fs_limit_bytes{id=\"/\"}) * 100",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "",
          "metric": "",
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "65, 90",
      "title": "Cluster filesystem usage",
      "type": "singlestat",
      "valueFontSize": "80%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": false,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "bytes",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": false,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 3,
        "w": 4,
        "x": 0,
        "y": 6
      },
      "height": "1px",
      "id": 9,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": "",
      "postfixFontSize": "20%",
      "prefix": "",
      "prefixFontSize": "20%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (container_memory_working_set_bytes{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"})",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "",
      "title": "Used",
      "type": "singlestat",
      "valueFontSize": "50%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": false,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "bytes",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": false,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 3,
        "w": 4,
        "x": 4,
        "y": 6
      },
      "height": "1px",
      "id": 10,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": "",
      "postfixFontSize": "50%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (machine_memory_bytes{kubernetes_io_hostname=~\"^$Node$\"})",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "",
      "title": "Total",
      "type": "singlestat",
      "valueFontSize": "50%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": false,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "none",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": false,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 3,
        "w": 4,
        "x": 8,
        "y": 6
      },
      "height": "1px",
      "id": 11,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": " cores",
      "postfixFontSize": "30%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (rate (container_cpu_usage_seconds_total{id=\"/\",kubernetes_io_hostname=~\"^$Node$\"}[$interval]))",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "",
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "",
      "title": "Used",
      "type": "singlestat",
      "valueFontSize": "50%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": false,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "none",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": false,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 3,
        "w": 4,
        "x": 12,
        "y": 6
      },
      "height": "1px",
      "id": 12,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": " cores",
      "postfixFontSize": "30%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (machine_cpu_cores{kubernetes_io_hostname=~\"^$Node$\"})",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "",
      "title": "Total",
      "type": "singlestat",
      "valueFontSize": "50%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": false,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "bytes",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": false,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 3,
        "w": 4,
        "x": 16,
        "y": 6
      },
      "height": "1px",
      "id": 13,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": "",
      "postfixFontSize": "50%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (container_fs_usage_bytes{id=\"/\"})",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "",
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "",
      "title": "Used",
      "type": "singlestat",
      "valueFontSize": "50%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "cacheTimeout": null,
      "colorBackground": false,
      "colorValue": false,
      "colors": [
        "rgba(50, 172, 45, 0.97)",
        "rgba(237, 129, 40, 0.89)",
        "rgba(245, 54, 54, 0.9)"
      ],
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "format": "bytes",
      "gauge": {
        "maxValue": 100,
        "minValue": 0,
        "show": false,
        "thresholdLabels": false,
        "thresholdMarkers": true
      },
      "gridPos": {
        "h": 3,
        "w": 4,
        "x": 20,
        "y": 6
      },
      "height": "1px",
      "id": 14,
      "interval": null,
      "links": [],
      "mappingType": 1,
      "mappingTypes": [
        {
          "name": "value to text",
          "value": 1
        },
        {
          "name": "range to text",
          "value": 2
        }
      ],
      "maxDataPoints": 100,
      "nullPointMode": "connected",
      "nullText": null,
      "options": {},
      "postfix": "",
      "postfixFontSize": "50%",
      "prefix": "",
      "prefixFontSize": "50%",
      "rangeMaps": [
        {
          "from": "null",
          "text": "N/A",
          "to": "null"
        }
      ],
      "sparkline": {
        "fillColor": "rgba(31, 118, 189, 0.18)",
        "full": false,
        "lineColor": "rgb(31, 120, 193)",
        "show": false
      },
      "tableColumn": "",
      "targets": [
        {
          "expr": "sum (container_fs_limit_bytes{id=\"/\"})",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "",
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": "",
      "title": "Total",
      "type": "singlestat",
      "valueFontSize": "50%",
      "valueMaps": [
        {
          "op": "=",
          "text": "N/A",
          "value": "null"
        }
      ],
      "valueName": "current"
    },
    {
      "collapsed": false,
      "datasource": null,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 9
      },
      "id": 35,
      "panels": [],
      "repeat": null,
      "title": "Memory",
      "type": "row"
    },
    {
      "aliasColors": {},
      "bars": false,
      "dashLength": 10,
      "dashes": false,
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "fill": 0,
      "fillGradient": 0,
      "grid": {},
      "gridPos": {
        "h": 7,
        "w": 24,
        "x": 0,
        "y": 10
      },
      "id": 25,
      "legend": {
        "alignAsTable": true,
        "avg": true,
        "current": true,
        "hideEmpty": false,
        "max": false,
        "min": false,
        "rightSide": true,
        "show": true,
        "sideWidth": 200,
        "sort": "current",
        "sortDesc": true,
        "total": false,
        "values": true
      },
      "lines": true,
      "linewidth": 1,
      "links": [],
      "nullPointMode": "connected",
      "options": {
        "dataLinks": []
      },
      "percentage": false,
      "pointradius": 5,
      "points": false,
      "renderer": "flot",
      "seriesOverrides": [],
      "spaceLength": 10,
      "stack": true,
      "steppedLine": false,
      "targets": [
        {
          "expr": "sum (container_memory_working_set_bytes{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}) by (pod)",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "{{ pod }}",
          "metric": "container_memory_usage:sort_desc",
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": [],
      "timeFrom": null,
      "timeRegions": [],
      "timeShift": null,
      "title": "Pods memory usage",
      "tooltip": {
        "msResolution": false,
        "shared": true,
        "sort": 2,
        "value_type": "cumulative"
      },
      "type": "graph",
      "xaxis": {
        "buckets": null,
        "mode": "time",
        "name": null,
        "show": true,
        "values": []
      },
      "yaxes": [
        {
          "format": "bytes",
          "label": null,
          "logBase": 1,
          "max": null,
          "min": null,
          "show": true
        },
        {
          "format": "short",
          "label": null,
          "logBase": 1,
          "max": null,
          "min": null,
          "show": false
        }
      ],
      "yaxis": {
        "align": false,
        "alignLevel": null
      }
    },
    {
      "collapsed": false,
      "datasource": null,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 17
      },
      "id": 37,
      "panels": [],
      "title": "CPU",
      "type": "row"
    },
    {
      "aliasColors": {},
      "bars": false,
      "dashLength": 10,
      "dashes": false,
      "datasource": "prometheus",
      "decimals": 3,
      "editable": true,
      "error": false,
      "fill": 0,
      "fillGradient": 0,
      "grid": {},
      "gridPos": {
        "h": 7,
        "w": 24,
        "x": 0,
        "y": 18
      },
      "height": "",
      "id": 17,
      "legend": {
        "alignAsTable": true,
        "avg": true,
        "current": true,
        "max": false,
        "min": false,
        "rightSide": true,
        "show": true,
        "sort": "current",
        "sortDesc": true,
        "total": false,
        "values": true
      },
      "lines": true,
      "linewidth": 1,
      "links": [],
      "nullPointMode": "connected",
      "options": {
        "dataLinks": []
      },
      "percentage": false,
      "pointradius": 5,
      "points": false,
      "renderer": "flot",
      "seriesOverrides": [],
      "spaceLength": 10,
      "stack": true,
      "steppedLine": false,
      "targets": [
        {
          "expr": "sum (rate (container_cpu_usage_seconds_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[$interval])) by (pod)",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "{{ pod }}",
          "metric": "container_cpu",
          "refId": "A",
          "step": 10
        }
      ],
      "thresholds": [],
      "timeFrom": null,
      "timeRegions": [],
      "timeShift": null,
      "title": "Pods CPU usage",
      "tooltip": {
        "msResolution": true,
        "shared": true,
        "sort": 2,
        "value_type": "cumulative"
      },
      "type": "graph",
      "xaxis": {
        "buckets": null,
        "mode": "time",
        "name": null,
        "show": true,
        "values": []
      },
      "yaxes": [
        {
          "format": "none",
          "label": "cores",
          "logBase": 1,
          "max": null,
          "min": null,
          "show": true
        },
        {
          "format": "short",
          "label": null,
          "logBase": 1,
          "max": null,
          "min": null,
          "show": false
        }
      ],
      "yaxis": {
        "align": false,
        "alignLevel": null
      }
    },
    {
      "collapsed": false,
      "datasource": null,
      "gridPos": {
        "h": 1,
        "w": 24,
        "x": 0,
        "y": 25
      },
      "id": 33,
      "panels": [],
      "repeat": null,
      "title": "Network I/O",
      "type": "row"
    },
    {
      "aliasColors": {},
      "bars": false,
      "dashLength": 10,
      "dashes": false,
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "fill": 1,
      "fillGradient": 0,
      "grid": {},
      "gridPos": {
        "h": 7,
        "w": 24,
        "x": 0,
        "y": 26
      },
      "id": 16,
      "legend": {
        "alignAsTable": true,
        "avg": true,
        "current": true,
        "max": false,
        "min": false,
        "rightSide": true,
        "show": true,
        "sideWidth": 200,
        "sort": "current",
        "sortDesc": true,
        "total": false,
        "values": true
      },
      "lines": true,
      "linewidth": 2,
      "links": [],
      "nullPointMode": "connected",
      "options": {
        "dataLinks": []
      },
      "percentage": false,
      "pointradius": 5,
      "points": false,
      "renderer": "flot",
      "seriesOverrides": [],
      "spaceLength": 10,
      "stack": false,
      "steppedLine": false,
      "targets": [
        {
          "expr": "sum (rate (container_network_receive_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[$interval])) by (pod)",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "-> {{ pod }}",
          "metric": "network",
          "refId": "A",
          "step": 10
        },
        {
          "expr": "- sum (rate (container_network_transmit_bytes_total{image!=\"\",name=~\"^k8s_.*\",kubernetes_io_hostname=~\"^$Node$\"}[$interval])) by (pod)",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "<- {{ pod }}",
          "metric": "network",
          "refId": "B",
          "step": 10
        }
      ],
      "thresholds": [],
      "timeFrom": null,
      "timeRegions": [],
      "timeShift": null,
      "title": "Pods network I/O",
      "tooltip": {
        "msResolution": false,
        "shared": true,
        "sort": 2,
        "value_type": "cumulative"
      },
      "type": "graph",
      "xaxis": {
        "buckets": null,
        "mode": "time",
        "name": null,
        "show": true,
        "values": []
      },
      "yaxes": [
        {
          "format": "Bps",
          "label": null,
          "logBase": 1,
          "max": null,
          "min": null,
          "show": true
        },
        {
          "format": "short",
          "label": null,
          "logBase": 1,
          "max": null,
          "min": null,
          "show": false
        }
      ],
      "yaxis": {
        "align": false,
        "alignLevel": null
      }
    },
    {
      "aliasColors": {},
      "bars": false,
      "dashLength": 10,
      "dashes": false,
      "datasource": "prometheus",
      "decimals": 2,
      "editable": true,
      "error": false,
      "fill": 1,
      "fillGradient": 0,
      "grid": {},
      "gridPos": {
        "h": 5,
        "w": 24,
        "x": 0,
        "y": 33
      },
      "height": "200px",
      "id": 32,
      "legend": {
        "alignAsTable": false,
        "avg": true,
        "current": true,
        "max": false,
        "min": false,
        "rightSide": false,
        "show": false,
        "sideWidth": 200,
        "sort": "current",
        "sortDesc": true,
        "total": false,
        "values": true
      },
      "lines": true,
      "linewidth": 2,
      "links": [],
      "nullPointMode": "connected",
      "options": {
        "dataLinks": []
      },
      "percentage": false,
      "pointradius": 5,
      "points": false,
      "renderer": "flot",
      "seriesOverrides": [],
      "spaceLength": 10,
      "stack": false,
      "steppedLine": false,
      "targets": [
        {
          "expr": "sum (rate (container_network_receive_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[$interval]))",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "Received",
          "metric": "network",
          "refId": "A",
          "step": 10
        },
        {
          "expr": "- sum (rate (container_network_transmit_bytes_total{kubernetes_io_hostname=~\"^$Node$\"}[$interval]))",
          "format": "time_series",
          "interval": "10s",
          "intervalFactor": 1,
          "legendFormat": "Sent",
          "metric": "network",
          "refId": "B",
          "step": 10
        }
      ],
      "thresholds": [],
      "timeFrom": null,
      "timeRegions": [],
      "timeShift": null,
      "title": "Network I/O pressure",
      "tooltip": {
        "msResolution": false,
        "shared": true,
        "sort": 0,
        "value_type": "cumulative"
      },
      "type": "graph",
      "xaxis": {
        "buckets": null,
        "mode": "time",
        "name": null,
        "show": true,
        "values": []
      },
      "yaxes": [
        {
          "format": "Bps",
          "label": null,
          "logBase": 1,
          "max": null,
          "min": null,
          "show": true
        },
        {
          "format": "Bps",
          "label": null,
          "logBase": 1,
          "max": null,
          "min": null,
          "show": false
        }
      ],
      "yaxis": {
        "align": false,
        "alignLevel": null
      }
    }
  ],
  "refresh": "10s",
  "schemaVersion": 20,
  "style": "dark",
  "tags": [
    "Prometheus",
    "Kubernetes"
  ],
  "templating": {
    "list": [
      {
        "auto": true,
        "auto_count": 20,
        "auto_min": "2m",
        "current": {
          "text": "auto",
          "value": "$__auto_interval_interval"
        },
        "hide": 2,
        "label": null,
        "name": "interval",
        "options": [
          {
            "selected": true,
            "text": "auto",
            "value": "$__auto_interval_interval"
          },
          {
            "selected": false,
            "text": "1m",
            "value": "1m"
          },
          {
            "selected": false,
            "text": "10m",
            "value": "10m"
          },
          {
            "selected": false,
            "text": "30m",
            "value": "30m"
          },
          {
            "selected": false,
            "text": "1h",
            "value": "1h"
          },
          {
            "selected": false,
            "text": "6h",
            "value": "6h"
          },
          {
            "selected": false,
            "text": "12h",
            "value": "12h"
          },
          {
            "selected": false,
            "text": "1d",
            "value": "1d"
          },
          {
            "selected": false,
            "text": "7d",
            "value": "7d"
          },
          {
            "selected": false,
            "text": "14d",
            "value": "14d"
          },
          {
            "selected": false,
            "text": "30d",
            "value": "30d"
          }
        ],
        "query": "1m,10m,30m,1h,6h,12h,1d,7d,14d,30d",
        "refresh": 2,
        "skipUrlSync": false,
        "type": "interval"
      },
      {
        "current": {
          "text": "prometheus",
          "value": "prometheus"
        },
        "hide": 0,
        "includeAll": false,
        "label": null,
        "multi": false,
        "name": "datasource",
        "options": [],
        "query": "prometheus",
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "type": "datasource"
      },
      {
        "allValue": ".*",
        "current": {
          "text": "All",
          "value": "$__all"
        },
        "datasource": "prometheus",
        "definition": "",
        "hide": 0,
        "includeAll": true,
        "label": null,
        "multi": false,
        "name": "Node",
        "options": [],
        "query": "label_values(kubernetes_io_hostname)",
        "refresh": 1,
        "regex": "",
        "skipUrlSync": false,
        "sort": 0,
        "tagValuesQuery": "",
        "tags": [],
        "tagsQuery": "",
        "type": "query",
        "useTags": false
      }
    ]
  },
  "time": {
    "from": "now-5m",
    "to": "now"
  },
  "timepicker": {
    "refresh_intervals": [
      "5s",
      "10s",
      "30s",
      "1m",
      "5m",
      "15m",
      "30m",
      "1h",
      "2h",
      "1d"
    ],
    "time_options": [
      "5m",
      "15m",
      "1h",
      "6h",
      "12h",
      "24h",
      "2d",
      "7d",
      "30d"
    ]
  },
  "timezone": "browser",
  "title": "育苗通K8S集群監控",
  "uid": "6KoW2MIGk",
  "version": 15
}