prometheus+grafana+consul监控系统

安装

cat > docker-compose.yml<<EOF
version: '3'
services:
  node-exporter:
    image: prom/node-exporter:latest
    ports:
      - "9100:9100"
    volumes:
      - /:/host
    restart: always
    command: "--web.listen-address=:9100 --path.rootfs=/host --path.procfs=/host/proc --path.sysfs=/host/sys"
    networks:
      - prom

  dingtalk:
    image: timonwong/prometheus-webhook-dingtalk:latest
    volumes:
    - "./alertmanager/config.yml:/etc/prometheus-webhook-dingtalk/config.yml"
    ports:
      - "8060:8060"
    networks:
      - prom
  alertmanager:
    depends_on:
      - dingtalk
    image: prom/alertmanager:latest
    volumes:
    - "./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml"

    ports:
      - "9093:9093"
      - "9094:9094"
    networks:
      - prom
  prometheus:
    depends_on:
      - alertmanager
      - consul
    image: prom/prometheus:latest
    volumes:
    - "./prometheus/:/etc/prometheus/"
    ports:
      - "9090:9090"
    networks:
      - prom
  grafana:
    depends_on:
      - prometheus
    image: grafana/grafana:latest
    volumes:
    - "/var/lib/grafana:/var/lib/grafana"
    ports:
      - "3000:3000"
    networks:
      - prom
  consul:
    image: consul
    ports: 
      - "8500:8500"
    networks:
      - prom
networks:
  prom:
    driver: bridge

EOF

cat >   alertmanager/alertmanager.yml <<EOF
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: 'password'                #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'
    send_resolved: true

EOF


cat > alertmanager/config.yml <<EOF
targets:
  webhook:
    url: https://oapi.dingtalk.com/robot/send?access_token=xxx
    mention:
      all: true

EOF

cat >  prometheus/prometheus.yml <<EOF
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:9090']
  - job_name: 'consul-prometheus'
    consul_sd_configs:
    - server: 'consul:8500'
      services: [] 
  - job_name: 'node'
    static_configs:
    - targets: ['node-exporter:9100']

  - job_name: 'alertmanager'
    static_configs:
    - targets: ['alertmanager:9093']

EOF
cat > prometheus/alert-rules.yml <<EOF
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 }}"

EOF
docker-compose up -d 

           

curl -X PUT -d ‘{“id”: “172.16.0.204”,“name”: “logstash”,“address”: “172.16.0.204”,“port”: 9100,“tags”: [“logstash”],“checks”: [{“http”: “http://172.16.0.204:9100”, “interval”: “5s”}]}’ http://172.16.0.115:8500/v1/agent/service/register

注册服务

consul

#注册
curl -X PUT -d '{"id": "node-exporter","name": "host1","address": "node-exporter","port": 9100,"tags": ["host1"],"checks": [{"http": "http://node-exporter:9100", "interval": "5s"}]}'  http://127.0.0.1:8500/v1/agent/service/register
#删除服务
curl -X PUT http://127.0.0.1:8500/v1/agent/service/deregister/node-exporter


           

画仪表盘

grafana

wget https://gitee.com/huangchengwu/blog-demo/raw/master/prometheus/chart.json

导入到仪表盘中

页面效果

#j=1

for ip in

cat host |grep -v "hdgg"

do

tag=“hdgg”

echo $ip $tag

curl -X PUT -d ‘{“id”: “‘ i p ′ " , " n a m e " : " ′ ip'","name": "' ip′","name":"′tag’”,“address”: “‘ i p ′ " , " p o r t " : 9100 , " t a g s " : [ " ′ ip'","port": 9100,"tags": ["' ip′","port":9100,"tags":["′tag’”],“checks”: [{“http”: "http://’$ip’:9100", “interval”: “5s”}]}’ http://172.16.0.115:8500/v1/agent/service/register

#j=$((j+1))

done