通过docker-compose部署prometheus、node-exporter、alertmanager和grafana。prometheus最新版本：2.19.2
mkdir -p /home/prom/{prometheus,prometheus/data,alertmanager,grafana}chmod 777 /home/prom/{prometheus/data,grafana}cd /home/prom
tree ..├── alertmanager │ ├── alertmanager.yml │ └── config.yml ├── docker-compose.yml ├── grafana └── prometheus ├── alert-rules.yml ├── data └── prometheus.yml 4 directories, 5 files
Prometheus
vim /home/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 }}"
vim /home/prom/prometheus/prometheus.yml
global: scrape_interval: 15s evaluation_interval: 15salerting: alertmanagers: - static_configs: - targets: - alertmanager:9093rule_files: - "*rules.yml" scrape_configs: - job_name: 'prometheus' static_configs: - targets: ['prometheus:9090'] - job_name: 'node' static_configs: - targets: ['node-exporter:9100'] - job_name: 'alertmanager' static_configs: - targets: ['alertmanager:9093']
Alertmanager
vim /home/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
vim /home/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: 'alert@163.com' #发送邮箱名称 smtp_auth_username: 'alert@163.com' #邮箱名称 smtp_auth_password: 'password' #邮箱密码或授权码 smtp_require_tls: falseroute: 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: 'receiver@163.com' send_resolved: true webhook_configs: - url: 'http://dingtalk:8060/dingtalk/webhook/send' send_resolved: true
docker-compose.yml
vim /home/prom/docker-compose.yml
version: '3.7'services: node-exporter: image: prom/node-exporter:latest ports: - "9100:9100" 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: - "9090:9090" networks: - prom grafana: depends_on: - prometheus image: grafana/grafana:latest volumes: - type: volume source: grafana target: /var/lib/grafana ports: - "3000:3000" networks: - promvolumes: prometheus: driver: local driver_opts: type: none o: bind device: /home/prom/prometheus/data grafana: driver: local driver_opts: type: none o: bind device: /home/prom/grafana networks: prom: driver: bridge
docker-compose up -d docker-compose ps Name Command State Ports -------------------------------------------------------------------------------------------------------------- prom_alertmanager_1 /bin/alertmanager --config ... Up 0.0.0.0:9093->9093/tcp, 0.0.0.0:9094->9094/tcp prom_dingtalk_1 /bin/prometheus-webhook-di ... Up 0.0.0.0:8060->8060/tcp prom_grafana_1 /run.sh Up 0.0.0.0:3000->3000/tcp prom_node-exporter_1 /bin/node_exporter Up 0.0.0.0:9100->9100/tcp prom_prometheus_1 /bin/prometheus --config.f ... Up 0.0.0.0:9090->9090/tcp docker psCONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES c1ec4cc9c41f grafana/grafana:latest "/run.sh" 36 seconds ago Up 36 seconds 0.0.0.0:3000->3000/tcp prom_grafana_1 8cd521c327d8 prom/prometheus:latest "/bin/prometheus --c…" 37 seconds ago Up 36 seconds 0.0.0.0:9090->9090/tcp prom_prometheus_1 ef93c8c06ca0 prom/alertmanager:latest "/bin/alertmanager -…" 37 seconds ago Up 37 seconds 0.0.0.0:9093-9094->9093-9094/tcp prom_alertmanager_1 d358a2a39b8d timonwong/prometheus-webhook-dingtalk:latest "/bin/prometheus-web…" 38 seconds ago Up 37 seconds 0.0.0.0:8060->8060/tcp prom_dingtalk_1 366ff81e7a65 prom/node-exporter:latest "/bin/node_exporter" 38 seconds ago Up 37 seconds 0.0.0.0:9100->9100/tcp prom_node-exporter_1
容器启动正常，访问ip:9090，
访问ip:3000，
可以看到，prometheus各组件状态正常。
node-exporter
其实node-exporter不需要通过docker-compose启动，对于每个要监控的主机，直接docker启动node-exporter：
docker pull prom/node-exporter:latest docker run -d -p 9100:9100 --name node-exporter prom/node-exporter:latest
之后修改prometheus.yml，重启所有容器：
docker-compose restart
测试告警
docker stop prom_node-exporter_1 docker-compose ps Name Command State Ports --------------------------------------------------------------------------------------------------------------- prom_alertmanager_1 /bin/alertmanager --config ... Up 0.0.0.0:9093->9093/tcp, 0.0.0.0:9094->9094/tcp prom_dingtalk_1 /bin/prometheus-webhook-di ... Up 0.0.0.0:8060->8060/tcp prom_grafana_1 /run.sh Up 0.0.0.0:3000->3000/tcp prom_node-exporter_1 /bin/node_exporter Exit 2 prom_prometheus_1 /bin/prometheus --config.f ... Up 0.0.0.0:9090->9090/tcp
收到钉钉和邮件故障告警，
docker start prom_node-exporter_1 docker-compose ps Name Command State Ports -------------------------------------------------------------------------------------------------------------- prom_alertmanager_1 /bin/alertmanager --config ... Up 0.0.0.0:9093->9093/tcp, 0.0.0.0:9094->9094/tcp prom_dingtalk_1 /bin/prometheus-webhook-di ... Up 0.0.0.0:8060->8060/tcp prom_grafana_1 /run.sh Up 0.0.0.0:3000->3000/tcp prom_node-exporter_1 /bin/node_exporter Up 0.0.0.0:9100->9100/tcp prom_prometheus_1 /bin/prometheus --config.f ... Up 0.0.0.0:9090->9090/tcp
收到钉钉和邮件恢复告警，
测试宕机完成，告警没有问题。
docker-compose部署 prometheus + grafana 完成，整个部署过程相比传统部署方式要简便很多。已存放至个人github：docker-compose