Prometheus docker-compose安装部署文档

移动开发 2023-04-08 11:06:14 阅读次数: 0

备注：以下操作均在root权限下进行的操作

安装前置环境：

已安装docker

已安装docker-compose

在/opt目录新建目录prom

在对应的prom目录下分别创建prometheus、alertmanager，grafana相关目录

mkdir -p /opt/prom/{prometheus,prometheus/data,alertmanager,grafana}
#prom目录结构
prom/
├── alertmanager
├── grafana
└── prometheus
    └── data

赋予相关目录对应的权限

chmod 777 /opt/prom/{prometheus/data,grafana}

编写docker-compose.yml文件，放在目录/opt/prom下

touch /opt/prom/docker-compose.yml
vim /opt/prom/docker-compose.yml

docker-compose.yml文件内容

version: '3.3'
 
services:
  node-exporter:
    image: prom/node-exporter:latest
    ports:
      - "9101:9100"         #node-exporter默认端口9100，不过由于metersphere的node-exporter已经占用了9100了，这里调整为9101
    networks:
      - prom
 
  dingtalk:
    image: timonwong/prometheus-webhook-dingtalk:latest
    volumes:
      - type: bind
        source: ./alertmanager/config.yml
        target: /etc/prometheus-webhook-dingtalk/config.yml
        read_only: true
    ports:
      - "8060:8060"
    networks:
      - prom
 
  alertmanager:
    depends_on:
      - dingtalk
    image: prom/alertmanager:latest
    volumes:
      - type: bind
        source: ./alertmanager/alertmanager.yml
        target: /etc/alertmanager/alertmanager.yml
        read_only: true
    ports:
      - "9093:9093"
      - "9094:9094"
    networks:
      - prom
 
  prometheus:
    depends_on:
      - alertmanager
    image: prom/prometheus:latest
    volumes:
      - type: bind
        source: ./prometheus/prometheus.yml
        target: /etc/prometheus/prometheus.yml
        read_only: true
      - type: bind
        source: ./prometheus/alert-rules.yml
        target: /etc/prometheus/alert-rules.yml
        read_only: true
      - type: volume
        source: prometheus
        target: /prometheus
    ports:
      - "9200:9090"         #prometheus默认端口9090，不过ms-prometheus占用该端口，这里换成9200
    networks:
      - prom
 
  grafana:
    depends_on:
      - prometheus
    image: grafana/grafana:latest
    volumes:
      - type: volume
        source: grafana
        target: /var/lib/grafana
    ports:
      - "3000:3000"
    networks:
      - prom
 
volumes:
  prometheus:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/prom/prometheus/data
  grafana:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/prom/grafana
 
networks:
  prom:
    driver: bridge

编写prometheus的配置文件prometheus.yml，放在/opt/prom/prometheus目录下

touch /opt/prom/prometheus/prometheus.yml
vim /opt/prom/prometheus/prometheus.yml
global:
  scrape_interval:     15s
  evaluation_interval: 15s
 
alerting:
  alertmanagers:
  - static_configs:
    - targets:
      - alertmanager:9093
 
rule_files:
  - "*rules.yml"
 
scrape_configs:
  - job_name: 'prometheus'
    static_configs:
    - targets: ['prometheus:9091']
 
  - job_name: 'node_prom_localhost'
    static_configs:
    - targets: ['node-exporter:9101']
 
  - job_name: 'alertmanager'
    static_configs:
    - targets: ['alertmanager:9093']

编写告警规则alert-rules.yml文件，放在目录/opt/prom/prometheus下

touch /opt/prom/prometheus/alert-rules.yml
vim /opt/prom/prometheus/alert-rules.yml
groups:
  - name: node-alert
    rules:
    - alert: NodeDown
      expr: up{job="node"} == 0
      for: 5m
      labels:
        severity: critical
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} down"
        description: "Instance: {
   
   { $labels.instance }} 已经宕机 5分钟"
        value: "{
   
   { $value }}"
 
    - alert: NodeCpuHigh
      expr: (1 - avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="idle"}[5m]))) * 100 > 80
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} cpu使用率过高"
        description: "CPU 使用率超过 80%"
        value: "{
   
   { $value }}"
 
    - alert: NodeCpuIowaitHigh
      expr: avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="iowait"}[5m])) * 100 > 50
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} cpu iowait 使用率过高"
        description: "CPU iowait 使用率超过 50%"
        value: "{
   
   { $value }}"
 
    - alert: NodeLoad5High
      expr: node_load5 > (count by (instance) (node_cpu_seconds_total{job="node",mode='system'})) * 1.2
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} load(5m) 过高"
        description: "Load(5m) 过高，超出cpu核数 1.2倍"
        value: "{
   
   { $value }}"
 
    - alert: NodeMemoryHigh
      expr: (1 - node_memory_MemAvailable_bytes{job="node"} / node_memory_MemTotal_bytes{job="node"}) * 100 > 90
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} memory 使用率过高"
        description: "Memory 使用率超过 90%"
        value: "{
   
   { $value }}"
 
    - alert: NodeDiskRootHigh
      expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"}) * 100 > 90
      for: 10m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk(/ 分区) 使用率过高"
        description: "Disk(/ 分区) 使用率超过 90%"
        value: "{
   
   { $value }}"
 
    - alert: NodeDiskBootHigh
      expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk(/boot 分区) 使用率过高"
        description: "Disk(/boot 分区) 使用率超过 80%"
        value: "{
   
   { $value }}"
 
    - alert: NodeDiskReadHigh
      expr: irate(node_disk_read_bytes_total{job="node"}[5m]) > 20 * (1024 ^ 2)
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk 读取字节数 速率过高"
        description: "Disk 读取字节数 速率超过 20 MB/s"
        value: "{
   
   { $value }}"
 
    - alert: NodeDiskWriteHigh
      expr: irate(node_disk_written_bytes_total{job="node"}[5m]) > 20 * (1024 ^ 2)
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk 写入字节数 速率过高"
        description: "Disk 写入字节数 速率超过 20 MB/s"
        value: "{
   
   { $value }}"
 
    - alert: NodeDiskReadRateCountHigh
      expr: irate(node_disk_reads_completed_total{job="node"}[5m]) > 3000
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk iops 每秒读取速率过高"
        description: "Disk iops 每秒读取速率超过 3000 iops"
        value: "{
   
   { $value }}"
 
    - alert: NodeDiskWriteRateCountHigh
      expr: irate(node_disk_writes_completed_total{job="node"}[5m]) > 3000
      for: 5m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk iops 每秒写入速率过高"
        description: "Disk iops 每秒写入速率超过 3000 iops"
        value: "{
   
   { $value }}"
 
    - alert: NodeInodeRootUsedPercentHigh
      expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk(/ 分区) inode 使用率过高"
        description: "Disk (/ 分区) inode 使用率超过 80%"
        value: "{
   
   { $value }}"
 
    - alert: NodeInodeBootUsedPercentHigh
      expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/boot"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/boot"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} disk(/boot 分区) inode 使用率过高"
        description: "Disk (/boot 分区) inode 使用率超过 80%"
        value: "{
   
   { $value }}"
 
    - alert: NodeFilefdAllocatedPercentHigh
      expr: node_filefd_allocated{job="node"} / node_filefd_maximum{job="node"} * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} filefd 打开百分比过高"
        description: "Filefd 打开百分比 超过 80%"
        value: "{
   
   { $value }}"
 
    - alert: NodeNetworkNetinBitRateHigh
      expr: avg by (instance) (irate(node_network_receive_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
      for: 3m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} network 接收比特数 速率过高"
        description: "Network 接收比特数 速率超过 20MB/s"
        value: "{
   
   { $value }}"
 
    - alert: NodeNetworkNetoutBitRateHigh
      expr: avg by (instance) (irate(node_network_transmit_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
      for: 3m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} network 发送比特数 速率过高"
        description: "Network 发送比特数 速率超过 20MB/s"
        value: "{
   
   { $value }}"
 
    - alert: NodeNetworkNetinPacketErrorRateHigh
      expr: avg by (instance) (irate(node_network_receive_errs_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
      for: 3m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} 接收错误包 速率过高"
        description: "Network 接收错误包 速率超过 15个/秒"
        value: "{
   
   { $value }}"
 
    - alert: NodeNetworkNetoutPacketErrorRateHigh
      expr: avg by (instance) (irate(node_network_transmit_packets_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
      for: 3m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} 发送错误包 速率过高"
        description: "Network 发送错误包 速率超过 15个/秒"
        value: "{
   
   { $value }}"
 
    - alert: NodeProcessBlockedHigh
      expr: node_procs_blocked{job="node"} > 10
      for: 10m
      labels:
        severity: warning
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} 当前被阻塞的任务的数量过多"
        description: "Process 当前被阻塞的任务的数量超过 10个"
        value: "{
   
   { $value }}"
 
    - alert: NodeTimeOffsetHigh
      expr: abs(node_timex_offset_seconds{job="node"}) > 3 * 60
      for: 2m
      labels:
        severity: info
        instance: "{
   
   { $labels.instance }}"
      annotations:
        summary: "instance: {
   
   { $labels.instance }} 时间偏差过大"
        description: "Time 节点的时间偏差超过 3m"
        value: "{
   
   { $value }}"

编写alertmanager配置文件alertmanager.yml

touch /opt/prom/alertmanager/alertmanager.yml
vim /opt/prom/alertmanager/alertmanager.yml
global:
  resolve_timeout: 5m
  smtp_smarthost: 'smtp.163.com:465'                #邮箱smtp服务器代理，启用SSL发信, 端口一般是465
  smtp_from: '[email protected]'                         #发送邮箱名称
  smtp_auth_username: '[email protected]'                #邮箱名称
  smtp_auth_password: 'test@123'                    #邮箱密码或授权码
  smtp_require_tls: false
 
route:
  receiver: 'default'
  group_wait: 10s
  group_interval: 1m
  repeat_interval: 1h
  group_by: ['alertname']
 
inhibit_rules:
- source_match:
    severity: 'critical'
  target_match:
    severity: 'warning'
  equal: ['alertname', 'instance']
 
receivers:
- name: 'default'
  email_configs:
  - to: '[email protected]'
    send_resolved: true
  webhook_configs:
  - url: 'http://dingtalk:8060/dingtalk/webhook/send'       #这里是钉钉的接口
    send_resolved: true

编写钉钉告警相关配置文件config.yml放在/opt/prom/alertmanager/目录下

touch /opt/prom/alertmanager/config.yml
vim /opt/prom/alertmanager/config.yml
targets:
  webhook:
    url: https://oapi.dingtalk.com/robot/send?access_token=xxxxxxxxxxxx             #修改为钉钉机器人的webhook
    mention:
      all: true

切到/opt/prom目录下，使用docker-compose up -d去起相关服务

docker-compose up -d

猜你喜欢

转载自blog.csdn.net/weixin_47614014/article/details/121164851
今日推荐
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
国产云输入法——仅华为无云端数据上传安全问题
开源日报 | 工业开源项目OGG 1.0；姐姐，你要和我一起配置火狐吗；苹果AI遥遥落后？Fedora 40
开放签电子签章：停止新增，优化体验，前进更进（五一假期前工作）
开源日报 | 中学生开源前端动画引擎；全球首个Llama3 8B中文版开源模型；联想电脑恐出局；Linus讽刺AI炒作
周排行
浏览器对同一域名进行请求的最大并发连接数
React Hook之自定义Hook
【转】MyBatis缓存机制
-Java-泛型
自动化测试常用脚本-发送邮件
LeetCode#859: Buddy Strings
java、Python处理字符串
第二篇の博客
Hadoop伪分布式环境安装
SQL Server进阶（十一）临时表、表变量
每日归档
更多
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)
2024-04-21(0)
2024-04-20(6)
2024-04-19(5)
2024-04-18(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022