ansible-playbook -i host_file  service_deploy.yaml  -e "tgz=prometheus-2.25.2.linux-amd64.tar.gz" -e "app=prometheus"


查看页面

# 全局配置段
global:
  # 采集间隔 
  scrape_interval:     15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
  # 计算报警和预聚合间隔
  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
  # 采集超时时间
  scrape_timeout: 10s 
  # 查询日志，包含各阶段耗时统计
  query_log_file: /opt/logs/prometheus_query_log
  # 全局标签组
  # 通过本实例采集的数据都会叠加下面的标签
  external_labels:
    account: 'huawei-main'
    region: 'beijng-01'


# Alertmanager信息段
alerting:
  alertmanagers:
  - scheme: http
    static_configs:
    - targets:
      - "localhost:9093"

# 告警、预聚合配置文件段
rule_files:
    - /etc/prometheus/rules/record.yml
    - /etc/prometheus/rules/alert.yml

# 采集配置段
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: 'prometheus'

    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.

    static_configs:
    - targets: ['localhost:9090']

# 远程查询段
remote_read:
  # prometheus 
  - url: http://prometheus/v1/read
    read_recent: true

  # m3db 
  - url: "http://m3coordinator-read:7201/api/v1/prom/remote/read"
    read_recent: true

# 远程写入段
remote_write:
  - url: "http://m3coordinator-write:7201/api/v1/prom/remote/write"
    queue_config:
      capacity: 10000
      max_samples_per_send: 60000
    write_relabel_configs:
      - source_labels: [__name__]
        separator: ;
        # 标签key前缀匹配到的drop
        regex: '(kubelet_|apiserver_|container_fs_).*'
        replacement: $1
        action: drop

准备prometheus配置文件，配置采集两个node_exporter

global:
  scrape_interval: 15s
  scrape_timeout: 10s
  evaluation_interval: 15s
alerting:
  alertmanagers:
  - scheme: http
    timeout: 10s
    api_version: v1
    static_configs:
    - targets: []
scrape_configs:
- job_name: prometheus
  honor_timestamps: true
  scrape_interval: 15s
  scrape_timeout: 10s
  metrics_path: /metrics
  scheme: http
  static_configs:
  - targets:
    - localhost:9090
- job_name: node_exporter
  honor_timestamps: true
  scrape_interval: 15s
  scrape_timeout: 10s
  metrics_path: /metrics
  scheme: http
  static_configs:
  - targets:
    - 172.16.58.79:9100
    - 172.16.58.78:9100



热更新配置
# 命令行开启  --web.enable-lifecycle
curl -X POST http://localhost:9090/-/reload 

页面查看targets up情况

# coding=UTF-8


import requests


def print_targets(targets):
    index = 1
    all = len(targets)
    for i in targets:
        scrapeUrl = i.get("scrapeUrl")
        state = i.get("health")
        labels = i.get("labels")
        lastScrape = i.get("lastScrape")
        lastScrapeDuration = i.get("lastScrapeDuration")
        lastError = i.get("lastError")
        if state=="up":
            up_type = "正常"
        else:
            up_type = "异常"
        msg = "状态:{} num:{}/{} endpoint:{} state:{} labels:{} lastScrape:{} lastScrapeDuration:{} lastError:{}".format(

            up_type,
            index,
            all,
            scrapeUrl,
            state,
            str(labels),
            lastScrape,
            lastScrapeDuration,
            lastError,

        )
        print(msg)
        index+=1

def get_targets(t):
    f_data = {}
    try:
        uri = 'http://{}/api/v1/targets'.format(t)
        res = requests.get(uri)

        data = res.json().get("data")
        activeTargets = data.get("activeTargets")
        droppedTargets = data.get("droppedTargets")

        ups = []
        downs = []
        print_targets(activeTargets)
        print_targets(droppedTargets)


    except Exception as e:
        print(e)


get_targets("prometheus.master01.wiswrt.com:9090")