prometheus针对blackbox-exporter监控

blackbox配置文件

modules:
  http_2xx:
    prober: http
  http_post_2xx:
    prober: http
    http:
      method: POST
  tcp_connect:
    prober: tcp
  pop3s_banner:
    prober: tcp
    tcp:
      query_response:
      - expect: "^+OK"
      tls: true
      tls_config:
        insecure_skip_verify: false
  ssh_banner:
    prober: tcp
    tcp:
      query_response:
      - expect: "^SSH-2.0-"
  irc_banner:
    prober: tcp
    tcp:
      query_response:
      - send: "NICK prober"
      - send: "USER prober prober prober :prober"
      - expect: "PING :([^ ]+)"
        send: "PONG ${1}"
      - expect: "^:[^ ]+ 001"
  icmp:
    prober: icmp

blackbox-exporter

apiVersion: v1
kind: Service
metadata:
annotations:
prometheus/scrape: "true"
labels:
name: blackbox-exporter
name: blackbox-exporter
namespace: kube-system
spec:
ports:
- name: blackbox-exporter
nodePort: 30115
port: 9115
protocol: TCP
targetPort: 9115
selector:
app: blackbox-exporter
sessionAffinity: ClientIP
sessionAffinityConfig:
clientIP:
timeoutSeconds: 10800
type: NodePort

---

apiVersion: apps/v1
kind: Deployment
metadata:
  annotations:
    deployment.kubernetes.io/revision: "21"
  generation: 1
  labels:
    app: blackbox-exporter
  name: blackbox-exporter
  namespace: kube-system 
spec:
  progressDeadlineSeconds: 600
  replicas: 1
  revisionHistoryLimit: 2
  selector:
    matchLabels:
      app: blackbox-exporter
  strategy:
    rollingUpdate:
      maxSurge: 25%
      maxUnavailable: 25%
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: blackbox-exporter
    spec:
      containers:
      - args:
        - --config.file=/config/blackbox/blackbox.yml   
        image: prom/blackbox-exporter
        imagePullPolicy: IfNotPresent
        livenessProbe:
          failureThreshold: 5
          initialDelaySeconds: 30
          periodSeconds: 60
          successThreshold: 1
          tcpSocket:
            port: 9115
          timeoutSeconds: 2
        name: blackbox-exporter
        ports:
        - containerPort: 9115
          protocol: TCP
        readinessProbe:
          failureThreshold: 3
          httpGet:
            path: /metrics
            port: 9115
            scheme: HTTP
          initialDelaySeconds: 30
          periodSeconds: 60
          successThreshold: 1
          timeoutSeconds: 10
        terminationMessagePath: /dev/termination-log
        terminationMessagePolicy: File
        volumeMounts:
        - mountPath: /config/blackbox
          name: blackbox-config
      dnsPolicy: ClusterFirst
      nodeSelector:
        com.zhonganonline.usefor: prometheus
      restartPolicy: Always
      schedulerName: default-scheduler
      terminationGracePeriodSeconds: 30
      volumes:
      - configMap:
          defaultMode: 420
          name: blackbox
        name: blackbox-config

prometheus配置文件

# Global config
global:
  # How frequently to scrape targets by default.
  scrape_interval:        60s

  # How long until a scrape request times out.
  scrape_timeout:         20s

  # How frequently to evaluate rules.
  evaluation_interval:    60s

  # Attach these labels to any time series or alerts when communicating with
  # external systems (federaten, remote storage, Alertmanager).
  external_labels:
      monitor: '10022-test-monitor' 

remote_write:
- url: "http://localhost:8080/receive"

rule_files:
  - "/etc/prometheus/platform/k8s-metrics.rules"
  - "/etc/prometheus/platform/k8s-alert.rules"
  - "/etc/prometheus/departments/*.rules"

scrape_configs:
- job_name: ecs-prometheus
  file_sd_configs:
  - files:
    - /etc/prometheus/ips/custom_sd.json
    refresh_interval: 10s
  metric_relabel_configs:
  - source_labels: [__name__]
    regex: node_cpu_seconds_total|node_disk_reads_completed_total|node_disk_writes_completed_total|node_disk_read_bytes_total|node_disk_written_bytes_total|node_filesystem_size_bytes|node_filesystem_avail_bytes|node_network_transmit_bytes_total|node_network_receive_bytes_total|up|node_netstat_Tcp_CurrEstab|node_memory_MemAvailable_bytes|node_memory_MemTotal_bytes|node_memory_MemFree_bytes
    action: keep

- job_name: process-prometheus
  file_sd_configs:
  - files:
    - /etc/prometheus/ips/process_sd.json
    refresh_interval: 10s
- job_name: 'traefik-prometheus'
  file_sd_configs:
  - files:
    - /etc/prometheus/ips/traefik_sd.json
    refresh_interval: 10s 

- job_name: 'ICMP'
  metrics_path: /probe
  params:
    module: [icmp]
  file_sd_configs:
    - files:
       #- /etc/prometheus/za-warden/ips/tcp.yml
         - /etc/prometheus/ips/custom_sd.json
      refresh_interval: 10m
  relabel_configs:
  - source_labels: [__address__]
    target_label: __param_target
  - source_labels: [__param_target]
    target_label: instance
  - target_label: __address__
    replacement: http://blackbox-exporter:9115 #配置blackbox的svc地址+端口
  - target_label: job
    replacement: TCP