Kubernetes监控手册08-监控scheduler

[root@tt-fc-dev01.nj ~]# ss -tlnp|grep kube-sche
LISTEN 0      128                *:10259            *:*    users:(("kube-scheduler",pid=2782518,fd=7))

[root@tt-fc-dev01.nj ~]# curl localhost:10259/metrics
Client sent an HTTP request to an HTTPS server.

[root@tt-fc-dev01.nj ~]# curl -s -k https://localhost:10259/metrics
{
  "kind": "Status",
  "apiVersion": "v1",
  "metadata": {},
  "status": "Failure",
  "message": "forbidden: User \"system:anonymous\" cannot get path \"/metrics\"",
  "reason": "Forbidden",
  "details": {},
  "code": 403
}

[root@tt-fc-dev01.nj qinxiaohui]# token=`kubectl get secret categraf-token-6whbs -n flashcat -o jsonpath={.data.token} | base64 -d`

[root@tt-fc-dev01.nj qinxiaohui]# curl -s -k -H "Authorization: Bearer $token" https://localhost:10259/metrics > scheduler.metrics

[root@tt-fc-dev01.nj qinxiaohui]# head -n 6 scheduler.metrics
# HELP apiserver_audit_event_total [ALPHA] Counter of audit events generated and sent to the audit backend.
# TYPE apiserver_audit_event_total counter
apiserver_audit_event_total 0
# HELP apiserver_audit_requests_rejected_total [ALPHA] Counter of apiserver requests rejected due to an error in audit logging backend.
# TYPE apiserver_audit_requests_rejected_total counter
apiserver_audit_requests_rejected_total 0

apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-agent-conf
  labels:
    name: prometheus-agent-conf
  namespace: flashcat
data:
  prometheus.yml: |-
    global:
      scrape_interval: 15s
      evaluation_interval: 15s

    scrape_configs:
      - job_name: 'apiserver'
        kubernetes_sd_configs:
        - role: endpoints
        scheme: https
        tls_config:
          insecure_skip_verify: true
        authorization:
          credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
        - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
          action: keep
          regex: default;kubernetes;https

      - job_name: 'controller-manager'
        kubernetes_sd_configs:
        - role: endpoints
        scheme: https
        tls_config:
          insecure_skip_verify: true
        authorization:
          credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
        - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
          action: keep
          regex: kube-system;kube-controller-manager;https

      - job_name: 'scheduler'
        kubernetes_sd_configs:
        - role: endpoints
        scheme: https
        tls_config:
          insecure_skip_verify: true
        authorization:
          credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
        - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
          action: keep
          regex: kube-system;kube-scheduler;https
    remote_write:
    - url: 'http://10.206.0.16:19000/prometheus/v1/write'    

[root@tt-fc-dev01.nj qinxiaohui]# kubectl get endpoints -n kube-system | grep sche
kube-scheduler            10.206.0.16:10259                                                    134d

[root@tt-fc-dev01.nj qinxiaohui]# kubectl get endpoints -n kube-system kube-scheduler -o yaml
apiVersion: v1
kind: Endpoints
metadata:
  annotations:
    control-plane.alpha.kubernetes.io/leader: '{"holderIdentity":"tt-fc-dev01.nj_859c205c-0bf9-4f3e-a41e-6da8dcb90308","leaseDurationSeconds":15,"acquireTime":"2022-10-27T06:53:19Z","renewTime":"2022-12-02T06:24:16Z","leaderTransitions":9}'
    endpoints.kubernetes.io/last-change-trigger-time: "2022-07-20T10:25:10Z"
  creationTimestamp: "2022-07-20T10:24:54Z"
  labels:
    k8s-app: kube-scheduler
    service.kubernetes.io/headless: ""
  name: kube-scheduler
  namespace: kube-system
  resourceVersion: "129050770"
  uid: a963d2bd-6ef3-4e93-b4dc-4b95d2aea890
subsets:
- addresses:
  - ip: 10.206.0.16
    nodeName: 10.206.0.16
    targetRef:
      kind: Pod
      name: kube-scheduler-10.206.0.16
      namespace: kube-system
      resourceVersion: "112211935"
      uid: 6a6c699e-008d-41b6-9480-7eed7f18ae2d
  ports:
  - name: https
    port: 10259
    protocol: TCP

# HELP rest_client_request_duration_seconds [ALPHA] Request latency in seconds. Broken down by verb and URL.
# TYPE rest_client_request_duration_seconds histogram
请求apiserver的延迟分布

# HELP rest_client_requests_total [ALPHA] Number of HTTP requests, partitioned by status code, method, and host.
# TYPE rest_client_requests_total counter
请求apiserver的总数 ,按照host code method 统计

# HELP leader_election_master_status [ALPHA] Gauge of if the reporting system is master of the relevant lease, 0 indicates backup, 1 indicates master. 'name' is the string used to identify the lease. Please make sure to group by name.
# TYPE leader_election_master_status gauge
调度器的选举状态，0表示backup， 1表示master

# HELP scheduler_queue_incoming_pods_total [STABLE] Number of pods added to scheduling queues by event and queue type.
# TYPE scheduler_queue_incoming_pods_total counter
进入调度队列的pod数

# HELP scheduler_preemption_attempts_total [STABLE] Total preemption attempts in the cluster till now
# TYPE scheduler_preemption_attempts_total counter
调度器驱逐容器的次数

# HELP scheduler_scheduler_cache_size [ALPHA] Number of nodes, pods, and assumed (bound) pods in the scheduler cache.
# TYPE scheduler_scheduler_cache_size gauge
调度器cache中node pod和绑定pod的数目

# HELP scheduler_pending_pods [STABLE] Number of pending pods, by the queue type. 'active' means number of pods in activeQ; 'backoff' means number of pods in backoffQ; 'unschedulable' means number of pods in unschedulableQ.
# TYPE scheduler_pending_pods gauge
调度pending的pod数量，按照queue type分别统计

# HELP scheduler_plugin_execution_duration_seconds [ALPHA] Duration for running a plugin at a specific extension point.
# TYPE scheduler_plugin_execution_duration_seconds histogram
调度插件在每个扩展点的执行时间，按照extension_point+plugin+status 分别统计

# HELP scheduler_e2e_scheduling_duration_seconds [ALPHA] (Deprecated since 1.23.0) E2e scheduling latency in seconds (scheduling algorithm + binding). This metric is replaced by scheduling_attempt_duration_seconds.
# TYPE scheduler_e2e_scheduling_duration_seconds histogram
调度延迟分布，1.23.0 以后会被scheduling_attempt_duration_seconds替代

# HELP scheduler_framework_extension_point_duration_seconds [STABLE] Latency for running all plugins of a specific extension point.
# TYPE scheduler_framework_extension_point_duration_seconds histogram
调度框架的扩展点延迟分布,按extension_point(扩展点Bind Filter Permit PreBind/PostBind PreFilter/PostFilter Reseve)
+profile（调度器）+ status(调度成功) 统计

# HELP scheduler_pod_scheduling_attempts [STABLE] Number of attempts to successfully schedule a pod.
# TYPE scheduler_pod_scheduling_attempts histogram
pod调度成功前，调度重试的次数分布

# HELP scheduler_schedule_attempts_total [STABLE] Number of attempts to schedule pods, by the result. 'unschedulable' means a pod could not be scheduled, while 'error' means an internal scheduler problem.
# TYPE scheduler_schedule_attempts_total counter
按照调度结果统计的调度重试次数。 "unschedulable" 表示无法调度，"error"表示调度器内部错误

# HELP scheduler_scheduler_goroutines [ALPHA] Number of running goroutines split by the work they do such as binding.
# TYPE scheduler_scheduler_goroutines gauge
按照功能(binding filter之类)统计的goroutine数量

# HELP scheduler_scheduling_algorithm_duration_seconds [ALPHA] Scheduling algorithm latency in seconds
# TYPE scheduler_scheduling_algorithm_duration_seconds histogram
调度算法的耗时分布

# HELP scheduler_scheduling_attempt_duration_seconds [STABLE] Scheduling attempt latency in seconds (scheduling algorithm + binding)
# TYPE scheduler_scheduling_attempt_duration_seconds histogram
调度算法+binding的耗时分布

# HELP scheduler_scheduler_goroutines [ALPHA] Number of running goroutines split by the work they do such as binding.
# TYPE scheduler_scheduler_goroutines gauge
调度器的goroutines数目