prometheus FEDERATION将多个prometheus监控聚合

发表评论
5,127

A+

所属分类：K8S

官方文档：

https://prometheus.io/docs/prometheus/latest/federation/

功能：

多个prometheus聚合到一起监控
集中存储监控数据
统一报警

# my global config
global:
  scrape_interval:     30s # 30秒更新一次
  evaluation_interval: 2m #这个和报警想对应，2分钟报警从inactive到pending然后2分钟在到fire，期间收集到数据如果变正常，则不再触发报警
  scrape_timeout: 30s  #pull超时30秒，默认10S

# Alertmanager configuration
alerting:  #Alertmanager 配置
  alertmanagers:
  - static_configs:
    - targets: ["172.22.1.14:8080"]

# 报警规则配置
rule_files:  
  - "/etc/prometheus/rule.yml"
  # - "first_rules.yml"
  # - "second_rules.yml"


# job配置
scrape_configs:
  # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
  - job_name: 'prometheus'   #常规的监控服务器
    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.
    static_configs:
    - targets: ['127.0.0.1:9090']

  - job_name: "alertmanager"
    static_configs:
    - targets: ['172.22.1.14:8080']

  - job_name: 'federate-sdorica'  #聚合监控，通过其他prometheus拉取数据
    scrape_interval: 30s         #30秒拉取1次
    honor_labels: true            #不覆盖原来的标签
    metrics_path: '/federate'     #采集路径这个不改
    params:                       
      'match[]':                   #筛选原来prometheus下面的标签
        - '{job=~"kubernetes-.*"}'
        - '{job=~"traefik.*"}'
    static_configs:                #原来prometheus的配置
      - targets: ['1.1.1.1:30090']
        labels:                    #给原来prometheus加一个标签，防止多了不知道是哪个集群的机器
          k8scluster: sdorica-k8s

  - job_name: 'federate-soe.demon.hj5'
    scrape_interval: 30s
    honor_labels: true
    metrics_path: '/federate'
    params:
      'match[]':
        - '{job=~"kubernetes-.*"}'
    static_configs:
      - targets: ['3.3.3.3:30090']
        labels:
          k8scluster: soe-demon-hj5-k8s

  - job_name: 'federate-jcyfb.av'
    scrape_interval: 30s
    honor_labels: true
    metrics_path: '/federate'
    params:
      'match[]':
        - '{job=~"kubernetes-.*"}'
        - '{job=~"traefik.*"}'
    static_configs:
      - targets: ['2.2.2.2:30090']
        labels:
          k8scluster: jcyfb-av-k8s

# my global config

global:

scrape_interval: 30s # 30秒更新一次

evaluation_interval: 2m #这个和报警想对应，2分钟报警从inactive到pending然后2分钟在到fire，期间收集到数据如果变正常，则不再触发报警

scrape_timeout: 30s #pull超时30秒，默认10S

# Alertmanager configuration

alerting: #Alertmanager 配置

alertmanagers:

- static_configs:

- targets: ["172.22.1.14:8080"]

# 报警规则配置

rule_files:

- "/etc/prometheus/rule.yml"

# - "first_rules.yml"

# - "second_rules.yml"

# job配置

scrape_configs:

# The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.

- job_name: 'prometheus' #常规的监控服务器

# metrics_path defaults to '/metrics'

# scheme defaults to 'http'.

static_configs:

- targets: ['127.0.0.1:9090']

- job_name: "alertmanager"

static_configs:

- targets: ['172.22.1.14:8080']

- job_name: 'federate-sdorica' #聚合监控，通过其他prometheus拉取数据

scrape_interval: 30s #30秒拉取1次

honor_labels: true #不覆盖原来的标签

metrics_path: '/federate' #采集路径这个不改

params:

'match[]': #筛选原来prometheus下面的标签

- '{job=~"kubernetes-.*"}'

- '{job=~"traefik.*"}'

static_configs: #原来prometheus的配置

- targets: ['1.1.1.1:30090']

labels: #给原来prometheus加一个标签，防止多了不知道是哪个集群的机器

k8scluster: sdorica-k8s

- job_name: 'federate-soe.demon.hj5'

scrape_interval: 30s

honor_labels: true

metrics_path: '/federate'

params:

'match[]':

- '{job=~"kubernetes-.*"}'

static_configs:

- targets: ['3.3.3.3:30090']

labels:

k8scluster: soe-demon-hj5-k8s

- job_name: 'federate-jcyfb.av'

scrape_interval: 30s

honor_labels: true

metrics_path: '/federate'

params:

'match[]':

- '{job=~"kubernetes-.*"}'

- '{job=~"traefik.*"}'

static_configs:

- targets: ['2.2.2.2:30090']

labels:

k8scluster: jcyfb-av-k8s

我的微信
这是我的微信扫一扫

我的微信公众号
我的微信公众号扫一扫

发表评论取消回复

登录 注册

登录注册