{"id":2355,"date":"2022-08-14T21:56:18","date_gmt":"2022-08-14T13:56:18","guid":{"rendered":"https:\/\/199604.com\/?p=2355"},"modified":"2022-08-14T21:56:18","modified_gmt":"2022-08-14T13:56:18","slug":"prometheusgrafana%e5%91%8a%e8%ad%a6%e7%bb%84%e4%bb%b6%e5%8d%95%e8%8a%82%e7%82%b9%e9%83%a8%e7%bd%b2%e9%aa%8c%e8%af%81","status":"publish","type":"post","link":"https:\/\/199604.com\/2355","title":{"rendered":"Prometheus+grafana\u544a\u8b66\u7ec4\u4ef6\u5355\u8282\u70b9\u90e8\u7f72\u9a8c\u8bc1"},"content":{"rendered":"

Prometheus+grafana\u544a\u8b66\u7ec4\u4ef6\u5355\u8282\u70b9\u90e8\u7f72\u9a8c\u8bc1<\/h1>\n

\u6b64\u6b21\u90e8\u7f72\u662f\u4f7f\u7528docker\u5feb\u901f\u9a8c\u8bc1\u90e8\u7f72,\u4e3b\u8981\u9a8c\u8bc1\u4e86Prometheus+grafana<\/code>\u544a\u8b66\u63a8\u9001\u90ae\u4ef6<\/code>\u548c\u9489\u9489<\/code><\/p>\n

\u4f7f\u7528\u4e862\u53f0\u673a\u5668<\/p>\n\n\n\n\n\n\n
IP<\/th>\n\u4f5c\u7528<\/th>\n\u5907\u6ce8<\/th>\n<\/tr>\n<\/thead>\n
10.80.210.56<\/td>\nprometheus-master<\/td>\n\u4e3b\u8981\u4f5c\u4e3a\u4e3b\u91c7\u96c6\u8282\u70b9<\/td>\n<\/tr>\n
10.80.210.122<\/td>\nprometheus-node<\/td>\n\u4e3b\u8981\u4f5c\u4e3a\u5404\u79cdxxx-exporter\u7684\u6570\u636e\u4e0a\u62a5\u8282\u70b9<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

prometheus-master\u90e8\u7f72<\/h2>\n

docker-compose.yml<\/code>\u6587\u4ef6\u5185\u5bb9\uff1a<\/h3>\n
version: '3'\n\nservices:\n  prometheus:\n    image: prom\/prometheus:v2.37.0\n    container_name: prometheus\n    hostname: prometheus\n    restart: always\n    user: \"0\"\n    command:\n      - '--config.file=\/etc\/prometheus\/prometheus.yml'\n      - '--storage.tsdb.path=\/prometheus'\n      - '--web.console.libraries=\/usr\/share\/prometheus\/console_libraries'\n      - '--web.console.templates=\/usr\/share\/prometheus\/consoles'\n      - '--storage.tsdb.retention.time=7d'\n#      - '--web.external-url=prometheus'\n    volumes:\n      - .\/prometheus\/prometheus.yml:\/etc\/prometheus\/prometheus.yml\n      - .\/prometheus\/rules\/:\/rules\/\n      - .\/prometheus\/data\/:\/prometheus\/\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    ports:\n      - \"9090:9090\"\n    networks:\n      - monitor\n\n  alertmanager:\n    image: prom\/alertmanager:v0.24.0\n    container_name: alertmanager\n    hostname: alertmanager\n    restart: always\n    user: '0'\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n      - .\/alertmanager\/alertmanager.yml:\/etc\/alertmanager\/alertmanager.yml\n      - .\/alertmanager\/template\/:\/etc\/alertmanager\/template\/\n      - .\/alertmanager\/data\/:\/alertmanager\n    ports:\n      - \"9093:9093\"\n    networks:\n      - monitor\n\n  grafana:\n    image: grafana\/grafana:8.5.9\n    container_name: grafana\n    hostname: grafana\n    restart: always\n    user: \"0\"\n    environment:\n      GF_SECURITY_ADMIN_USER: xinsec\n      GF_SECURITY_ADMIN_PASSWORD: DB.xinsec\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n#      - .\/grafana\/config:\/etc\/grafana\n      - .\/grafana\/data:\/var\/lib\/grafana\n      - .\/grafana\/log:\/var\/log\/grafana\n    ports:\n      - \"3000:3000\"\n    networks:\n      - monitor\n\n  node-exporter:\n    #image: quay.io\/prometheus\/node-exporter:v1.4.0-rc.0\n    image: prom\/node-exporter:v1.4.0-rc.0\n    container_name: node-exporter\n    hostname: node-exporter\n    restart: always\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    ports:\n      - \"9100:9100\"\n    networks:\n      - monitor\n\n  pushgateway:\n    image: prom\/pushgateway:v1.4.3\n    container_name: pushgateway\n    hostname: pushgateway\n    restart: always\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    ports:\n      - \"9091:9091\"\n    networks:\n      - monitor\n\n  cadvisor:\n    image: google\/cadvisor:latest\n    container_name: cadvisor\n    hostname: cadvisor\n    restart: always\n    volumes:\n      - \/:\/rootfs:ro #\u7ed9cAdvisor\u5bf9root\u6587\u4ef6\u7cfb\u7edf\u7684\u53ea\u8bfb\u6743\u9650,\u4ee5\u4fbf\u68c0\u6d4b\u5bbf\u4e3b\u673a\u4fe1\u606f\n      - \/var\/run:\/var\/run:rw\n      - \/sys:\/sys:ro\n      - \/var\/lib\/docker\/:\/var\/lib\/docker:ro\n      - \/dev\/disk\/:\/dev\/disk:ro\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    ports:\n      - \"18080:8080\"\n    networks:\n      - monitor\n\n  webhook-dingding:\n    image: timonwong\/prometheus-webhook-dingtalk:v1.4.0\n    container_name: webhook-dingding\n    hostname: webhook-dingding\n    restart: always\n    volumes:\n      - \/data\/docker\/prometheus\/alertmanager\/template\/dingding.tmpl:\/etc\/alertmanager\/template\/dingding.tmpl\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    ports:\n      - \"8060:8060\"\n    entrypoint: \/bin\/prometheus-webhook-dingtalk --template.file=\"\/etc\/alertmanager\/template\/dingding.tmpl\" --ding.profile=\"webhook1=https:\/\/oapi.dingtalk.com\/robot\/send?access_token=xxx\"\n    networks:\n      - monitor\n\nnetworks:\n  monitor:\n    driver: bridge\n<\/code><\/pre>\n
\u8bf4\u660e\uff1a<\/h4>\n
\u4f7f\u7528\u4e86\u4ee5\u4e0b\u5bb9\u5668\uff1a<\/h5>\n
    \n
  1. prometheus<\/li>\n
  2. alertmanager #\u544a\u8b66\u6a21\u5757<\/li>\n
  3. pushgateway # \u7a0b\u5e8f\u4e3b\u52a8\u63a8\u9001\u9700\u8981\u8bbe\u7f6e\u7684\u7ec4\u4ef6\uff0cprometheus \u9ed8\u8ba4\u662fpull\u6a21\u5f0f<\/li>\n
  4. grafana # \u5c55\u793a\u6570\u636e\u754c\u9762<\/li>\n
  5. node-exporter #\u91c7\u96c6\u865a\u62df\u673a\u6307\u6807<\/li>\n
  6. cadvisor #\u91c7\u96c6docker\u5bb9\u5668\u6307\u6807<\/li>\n
  7. webhook-dingding #\u544a\u8b66\u63a8\u9001<\/li>\n<\/ol>\n
    \u76ee\u5f55\u7ed3\u6784\u5982\u4e0b\uff1a<\/h5>\n
    [root@emqx prometheus]# tree\n\u251c\u2500\u2500 alertmanager\n\u2502\u00a0\u00a0 \u251c\u2500\u2500 alertmanager.yml\n\u2502\u00a0\u00a0 \u251c\u2500\u2500 data\n\u2502\u00a0\u00a0 \u2514\u2500\u2500 template\n\u2502\u00a0\u00a0     \u251c\u2500\u2500 dingding.tmpl\n\u2502\u00a0\u00a0     \u2514\u2500\u2500 email.tmpl\n\u251c\u2500\u2500 docker-compose.yml\n\u251c\u2500\u2500 grafana\n\u2502\u00a0\u00a0 \u251c\u2500\u2500 data\n\u2502\u00a0\u00a0 \u2514\u2500\u2500 log\n\u2514\u2500\u2500 prometheus\n    \u251c\u2500\u2500 data\n    \u251c\u2500\u2500 prometheus.yml\n    \u2514\u2500\u2500 rules\n        \u251c\u2500\u2500 mysql_rules.yml\n        \u251c\u2500\u2500 node_rules.yml\n        \u251c\u2500\u2500 redis_rules.yml\n        \u2514\u2500\u2500 vmware_rules.yml\n<\/code><\/pre>\n
    \u6bcf\u4e2a\u5bb9\u5668\u6620\u5c04\u6587\u4ef6\uff1a<\/h3>\n
    prometheus<\/h4>\n
    prometheus.yml<\/code>:<\/h5>\n
    $PWD\/prometheus\/prometheus.yml<\/code><\/p>\n
    # global\u6a21\u5757\u662f\u5168\u5c40\u914d\u7f6e\u4fe1\u606f\uff0c\u5b83\u5b9a\u4e49\u7684\u5185\u5bb9\u4f1a\u88abscrape_configs\u6a21\u5757\u4e2d\u7684\u6bcf\u4e2aJob\u5355\u72ec\u8986\u76d6\nglobal:\n  scrape_interval:     15s # pull \u9891\u7387\n  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.\n  scrape_timeout: 15s # \u8d85\u65f6\u65f6\u95f4\n\n# \u544a\u8b66\u6a21\u5757\uff0cPrometheus Server\u53d1\u9001\u8bf7\u6c42\u7ed9Alertmanager\u4e4b\u524d\u4e5f\u4f1a\u89e6\u53d1\u4e00\u6b21relabel\u64cd\u4f5c\nalerting:\n  alertmanagers:\n    - static_configs:\n        - targets:\n            - '10.80.210.56:9093'\n\n# \u544a\u8b66\u7684\u89c4\u5219-\u5b9a\u4e49\u544a\u8b66\u6587\u4ef6\n# Prometheus\u81ea\u5b9a\u4e49\u7684rule\u4e3b\u8981\u5206\u4e3aRecording rule\u548cAlerting rule\u4e24\u7c7b\nrule_files:\n  - \"\/rules\/*\"\n\n# A scrape configuration containing exactly one endpoint to scrape:\nscrape_configs:\n  # Job\u540d\u79f0\u5f88\u91cd\u8981\uff0cPrometheus\u4f1a\u5c06\u8be5\u540d\u79f0\u4f5c\u4e3aLabel\u8ffd\u52a0\u5230\u6293\u53d6\u7684\u6bcf\u6761\u65f6\u5e8f\u4e2d\n  - job_name: 'prometheus'\n    static_configs: # \u76d1\u63a7\u7684\u4e3b\u673a\u5730\u5740\u4e0e\u7aef\u53e3\u4fe1\u606f\n      - targets: ['10.80.210.56:9090']\n        labels:\n          instance: 'prometheus\u7a0b\u5e8f'\n\n  - job_name: 'pushgateway'\n    static_configs:\n      - targets: [ '10.80.210.56:9091' ]\n        labels:\n          instance: 'pushgateway\u7a0b\u5e8f'\n\n  # #\u76d1\u63a7\u4e3b\u673anode\u4fe1\u606f\uff0c\u4f9d\u8d56\u63d2\u4ef6node_exporter\n  - job_name: 'node-exporter-\u670d\u52a1\u5668\u4fe1\u606f\u76d1\u63a7'\n    static_configs:\n      - targets: ['10.80.210.122:9100']\n        labels:\n          group: '\u6d4b\u8bd5docker'\n          instance: '10.80.210.122-node-exporter'\n      - targets: ['10.80.210.56:9100']\n        labels:\n          group: 'prometheus-master'\n          instance: '10.80.210.56-node-exporter'\n\n  - job_name: 'cadvisor-docker\u5bb9\u5668\u76d1\u63a7'\n    scrape_interval: 120s\n    static_configs:\n      - targets: [ '10.80.210.56:18080']\n        labels:\n          group: 'prometheus-master'\n          instance: '10.80.210.56-cadvisor'\n      - targets: ['10.80.210.122:18080']\n        labels:\n          group: '\u6d4b\u8bd5docker'\n          instance: '10.80.210.122-cadvisor'\n\n  # \u76d1\u63a7\u4e3b\u673amysql\u4fe1\u606f\uff0c\u4f9d\u8d56\u63d2\u4ef6mysql_exporter\n  - job_name: 'mysql\u6570\u636e\u5e93\u4fe1\u606f\u76d1\u63a7'\n    static_configs:\n      - targets: ['10.80.210.122:9104']\n        labels:\n          instance: '10.80.210.122-redis'\n\n  # \u76d1\u63a7\u4e3b\u673aredis\u4fe1\u606f\uff0c\u4f9d\u8d56\u63d2\u4ef6redis-exporter\n  - job_name: 'redis\u7f13\u5b58\u6570\u636e\u5e93\u4fe1\u606f\u76d1\u63a7'\n    static_configs:\n      - targets: ['10.80.210.122:9121']\n        labels:\n          instance: '10.80.210.122-redis\u670d\u52a1'\n\n  # \u76d1\u63a7\u4e3b\u673ajava\u7a0b\u5e8f\u4fe1\u606f\uff0c\u9700\u8981\u7a0b\u5e8f\u5f00\u653e\u7aef\u53e3\u8fdb\u884c\u76d1\u63a7\n  - job_name: 'prometheus-java-demo-java\u76d1\u63a7'\n    metrics_path: '\/sms\/actuator\/prometheus'\n    static_configs:\n      - targets: ['10.80.210.56:28084']\n        labels:\n          instance: 'prometheus-java-demo-java'\n\n  # \u4fee\u6539nacos application.properties\n  # \u5f00\u542f\uff1amanagement.endpoints.web.exposure.include=*\n  - job_name: 'nacos\u4fe1\u606f\u76d1\u63a7'\n    scrape_interval: 60s\n    metrics_path: '\/nacos\/actuator\/prometheus'\n    static_configs:\n      - targets: ['10.80.210.122:8848']\n        labels:\n          instance: '10.80.210.122-nacos'\n\n  # \u53c2\u8003\uff1ahttps:\/\/blog.csdn.net\/qq_37696855\/article\/details\/123484069\n  - job_name: 'jenkins\u76d1\u63a7'\n    metrics_path: '\/prometheus'\n    scheme: http\n    static_configs:\n      - targets: [ '10.80.210.171' ]\n        labels:\n          instance: '10.80.210.171-jenkens\u670d\u52a1'\n\n  # \u76d1\u63a7\u4e3b\u673avmware\u4fe1\u606f\uff0c\u4f9d\u8d56\u63d2\u4ef6pryorda\/vmware_exporter\n  - job_name: 'vmware_vcenter'\n    metrics_path: '\/metrics'\n    scheme: http\n    scrape_interval: 60s\n    scrape_timeout: 30s\n    static_configs:\n      - targets:\n          - '10.80.210.122:9272'\n        labels:\n          host_name: 10.80.211.77\n      - targets:\n          - '10.80.210.122:9273'\n        labels:\n          host_name: 10.80.210.80\n      - targets:\n          - '10.80.210.122:9274'\n        labels:\n          host_name: 10.80.210.100\n      - targets:\n          - '10.80.210.122:9275'\n        labels:\n          host_name: 10.80.210.180\n      - targets:\n          - '10.80.210.122:9276'\n        labels:\n          host_name: 10.80.210.200\n      - targets:\n          - '10.80.210.122:9277'\n        labels:\n          host_name: 10.80.210.210\n<\/code><\/pre>\n
    rule\u544a\u8b66\u89c4\u5219\u6587\u4ef6<\/h5>\n
    $PWD\/prometheus\/rules\/<\/code><\/p>\n
    mysql_rules.yml<\/code><\/h6>\n
    ---\ngroups:\n  - name: Mysql alert\n    rules:\n      - alert: MySQL \u8fd0\u884c\u60c5\u51b5\n        expr: mysql_up == 0\n        for: 1m\n        labels:\n          severity: \u4e25\u91cd\n        annotations:\n          summary: \"{{ $labels.instance }} MySQL is down\"\n          description: \"MySQL database is down.\"\n<\/code><\/pre>\n
    node_rules.yml<\/code><\/h6>\n
    groups:\n  - name: Node alert\n    rules:\n      - alert: job\u8282\u70b9\u72b6\u6001\u5b95\u673a\n        expr: up == 0\n        for: 1m\n        labels:\n          severity: \u4e25\u91cd\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"{{ $labels.app }}\u5df2\u505c\u6b62\u8fd0\u884c\u8d85\u8fc71\u5206\u949f!\"\n          description: \"\u8282\u70b9 {{$labels.instance}} \u5b95\u673a\u5df2\u8d85\u8fc71\u5206\u949f\u8bf7\u8fdb\u884c\u4eba\u5de5\u5904\u7406\u3002\"\n\n      - alert: \u670d\u52a1\u5668\u5b9e\u4f8b\u4f7f\u7528\u60c5\u51b5\n        expr: node_load5 > 4\n        for: 5m\n        labels:\n          severity: \u8b66\u544a\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"\u670d\u52a1\u5668\u5b9e\u4f8b {{ $labels.app }} \u5e73\u5747\u8d1f\u8f7d\u8fc7\u9ad8\"\n          description: \"\u4e3b\u673a\u8d1f\u8f7d5\u5206\u949f\u8d85\u8fc74.\"\n\n      - alert: Memory \u4f7f\u7528\u60c5\u51b5\n        expr: (1 - (node_memory_MemAvailable_bytes \/ (node_memory_MemTotal_bytes))) * 100 > 90\n        for: 5m # \u544a\u8b66\u6301\u7eed\u65f6\u95f4\uff0c\u8d85\u8fc7\u8fd9\u4e2a\u65f6\u95f4\u624d\u4f1a\u53d1\u9001\u7ed9alertmanager\n        labels:\n          severity: \u8b66\u544a\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"\u670d\u52a1\u5668\u5b9e\u4f8b {{ $labels.app }}\u5185\u5b58\u4f7f\u7528\u7387\u8fc7\u9ad8\"\n          description: \"{{ $labels.app }}\u7684\u5185\u5b58\u4f7f\u7528\u7387\u8d85\u8fc790%\uff0c\u5f53\u524d\u4f7f\u7528\u7387[{{ $value }}].\"\n\n      - alert: CPU \u4f7f\u7528\u60c5\u51b5\n        expr: 100-avg(irate(node_cpu_seconds_total{mode=\"idle\"}[5m])) by(instance)*100 > 90\n        for: 5m\n        labels:\n          severity: \u8b66\u544a\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"\u670d\u52a1\u5668\u5b9e\u4f8b {{ $labels.app }} cpu\u4f7f\u7528\u7387\u8fc7\u9ad8\"\n          description: \"{{ $labels.app }}\u7684cpu\u4f7f\u7528\u7387\u8d85\u8fc790%,\u5f53\u524d\u4f7f\u7528\u7387[{{ $value }}].\"\n\n      - alert: \u78c1\u76d8\u5bb9\u91cf\n        expr: 100 - node_filesystem_avail_bytes{fstype=~\"ext4|xfs\",mountpoint=\"\/\"}  * 100 \/ node_filesystem_size_bytes{fstype=~\"ext4|xfs\",mountpoint=\"\/\"} > 80\n        for: 5m\n        labels:\n          severity: \u8b66\u544a\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"\u670d\u52a1\u5668\u5b9e\u4f8b {{ $labels.app }} \u78c1\u76d8\u4f7f\u7528\u7387\u8fc7\u9ad8\"\n          description: \"{{ $labels.app }}\u7684disk\u4f7f\u7528\u7387\u8d85\u8fc780%,\u5f53\u524d\u4f7f\u7528\u7387[{{ $value }}].\"\n\n      - alert: IO \u6027\u80fd\u60c5\u51b5\n        expr: 100 - (avg(irate(node_disk_io_time_seconds_total[5m])) by(instance)* 100) < 20\n        for: 2m\n        labels:\n          severity: \u8b66\u544a\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"{{$labels.instance}} \u6d41\u5165\u78c1\u76d8IO\u4f7f\u7528\u7387\u8fc7\u9ad8\uff01\"\n          description: \"{{$labels.instance }} \u6d41\u5165\u78c1\u76d8IO\u5927\u4e8e80%(\u76ee\u524d\u4f7f\u7528:{{$value}})\"\n\n      - alert: TCP\u4f1a\u8bdd\n        expr: node_netstat_Tcp_CurrEstab > 1000\n        for: 1m\n        labels:\n          severity: \u8b66\u544a\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"{{$labels.instance}} TCP_ESTABLISHED\u8fc7\u9ad8\uff01\"\n          description: \"{{$labels.instance }} TCP_ESTABLISHED\u5927\u4e8e1000%(\u76ee\u524d\u4f7f\u7528:{{$value}}%)\"\n\n      - alert: Network \u63a5\u6536(receive)\u60c5\u51b5\n        expr: ((sum(rate (node_network_receive_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) \/ 100) > 102400\n        for: 5m\n        labels:\n          severity: \u63d0\u9192\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"{{$labels.instance}} \u6d41\u5165\u7f51\u7edc\u5e26\u5bbd\u8fc7\u9ad8\uff01\"\n          description: \"{{$labels.instance }} \u6d41\u5165\u7f51\u7edc\u5e26\u5bbd\u6301\u7eed5\u5206\u949f\u9ad8\u4e8e100M. RX\u5e26\u5bbd\u4f7f\u7528\u7387{{$value}}\"\n\n      - alert: Network \u4f20\u8f93(transmit)\u60c5\u51b5\n        expr: ((sum(rate (node_network_transmit_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) \/ 100) > 102400\n        for: 1m\n        labels:\n          severity: \u63d0\u9192\n          nodename: \"{{ $labels.app }}\"\n        annotations:\n          summary: \"{{$labels.instance}} \u6d41\u51fa\u7f51\u7edc\u5e26\u5bbd\u8fc7\u9ad8\uff01\"\n          description: \"{{$labels.instance }}\u6d41\u51fa\u7f51\u7edc\u5e26\u5bbd\u6301\u7eed2\u5206\u949f\u9ad8\u4e8e100M. RX\u5e26\u5bbd\u4f7f\u7528\u7387{{$value}}\"\n\n<\/code><\/pre>\n
    redis_rules.yml<\/code><\/h6>\n
    groups:\n  # -- \u6570\u636e\u5e93\u76d1\u63a7\u89c4\u5219\n  - name: Redis alert\n    rules:\n      - alert: Redis \u5185\u5b58\u60c5\u51b5\n        # redis_memory_used_bytes: redis \u5df2\u4f7f\u7528\u7684\u5b57\u8282\n        # redis_config_maxmemory: redis \u914d\u7f6e\u6587\u4ef6\u4e2d\u6700\u5927\u4f7f\u7528\u5185\u5b58\u5b57\u8282 \u9ed8\u8ba4\u4e3a0\n        # expr: 100 * (redis_memory_used_bytes \/ redis_config_maxmemory) > 90\n        expr: 100 * (redis_memory_used_bytes \/ 2147483648) > 90\n        for: 1m\n        labels:\n          severity: \u63d0\u9192\n          status: \u8b66\u544a\n        annotations:\n          summary: \"Redis {{ $labels.instance }} memory userd over 90\"\n          description: \"Redis memory used over 90 duration above 1m\"\n<\/code><\/pre>\n
    vmware_rules.yml<\/code><\/h6>\n
    groups:\n  - name: Vmware status\n    rules:\n      - alert: EXSi\u4e3b\u673a\u72b6\u6001\n        expr: vmware_host_power_state ==0\n        for: 5m\n        labels:\n          type: lost\n          severity: \u4e25\u91cd\n        annotations:\n          summary: \"EXSi\u4e3b\u673a {{$labels.host_name}} \u5931\u8054\"\n          description: \"EXSi\u4efb\u52a1 {{$labels.job}} \u4e0b\u7684\u4e3b\u673a {{$labels.host_name}} \u5df2\u7ecf\u8d85\u8fc7\u4e94\u5206\u949f\u6ca1\u6709\u6570\u636e\u4e86.\"\n          monitor_url: \"http:\/\/10.80.210.56:3000\/d\/q1yCDNbWz\/vmware-stats?orgId=1\"\n\n      - alert: \u865a\u62df\u673a\u5185\u5b58\u8b66\u544a  #\u865a\u62df\u673a\u5185\u5b58\u8b66\u544a\u6a21\u677f\n        expr: vmware_vm_mem_usage_average \/ 100 >= 80 and vmware_vm_mem_usage_average \/ 100 < 50\n        for: 30m\n        labels:\n          severity: \u8b66\u544a\n        annotations:\n          summary: \u865a\u62df\u673a\u5185\u5b58\u8b66\u544a (instance {{ $labels.instance }})\n          description: 'High memory usage on {{ $labels.instance }}: {{ $value | printf \"%.2f\"}}%n  VALUE = {{ $value }}n  VMware_Name = {{ $labels.vm_name }}'\n\n      - alert: \u865a\u62df\u673a\u5185\u5b58\u4e25\u91cd\u4e0d\u8db3 #\u865a\u62df\u673a\u5185\u5b58\u4e25\u91cd\u6a21\u677f\n        expr: vmware_vm_mem_usage_average \/ 100 >= 90\n        for: 30m\n        labels:\n          severity: \u4e25\u91cd\n        annotations:\n          summary: \u865a\u62df\u673a\u5185\u5b58\u4e25\u91cd\u4e0d\u8db3 (instance {{ $labels.instance }})\n          description: 'High memory usage on {{ $labels.host_name }}: {{ $value | printf \"%.2f\"}}%n  VALUE = {{ $value }}n  VMware_Name = {{ $labels.vm_name }}'\n\n      - alert: EXSi\u4e3b\u673a\u5185\u5b58\u4f7f\u7528\n        #esxi\u5185\u5b58\u4f7f\u7528\u767e\u5206\u6bd4\u6a21\u677f\n        expr: ((vmware_host_memory_usage \/ vmware_host_memory_max) * 100) > 85\n        for: 5m\n        labels:\n          severity: \u8b66\u544a\n        annotations:\n          summary: \"EXSi\u4e3b\u673a {{ $labels.host_name }} \u7684\u5185\u5b58\u4f7f\u7528\u7387\u544a\u8b66\"\n          description: \"EXSi\u4e3b\u673a {{ $labels.host_name }} \u7684\u5185\u5b58\u4f7f\u7528\u7387\u8d85\u8fc7 85%, \u5f53\u524d\u503c\u4e3a\uff1a {{ $value }}\"\n\n      - alert: EXSi\u4e3b\u673aCPU\u4f7f\u7528\u60c5\u51b5\n        expr: ((vmware_host_cpu_usage \/ vmware_host_cpu_max) * 100) > 80\n        for: 5m\n        labels:\n          type: cpu\n          severity: \u8b66\u544a\n        annotations:\n          summary: \"EXSi\u4e3b\u673a {{ $labels.host_name }} \u7684 CPU \u4f7f\u7528\u7387\u544a\u8b66\"\n          description: \"EXSi\u4e3b\u673a {{ $labels.host_name }} CPU \u4f7f\u7528\u7387\u8d85\u8fc7 80%, \u5f53\u524d\u503c\u4e3a\uff1a {{ $value }}\"\n\n<\/code><\/pre>\n
    \"image-20220814215051471\"<\/div><\/p>\n
    alertmanager<\/h4>\n
    alertmanager.yml<\/code><\/h5>\n
    global:\n  # -\u90ae\u4ef6\u901a\u77e5\u76f8\u5173\u914d\u7f6e\n  resolve_timeout: 5m\n#  smtp_smarthost: 'smtp.139.com:465'\n#  smtp_from: 'xxx@139.com'\n#  smtp_auth_username: 'xxx@139.com'\n#  # \u6388\u6743\u7801\n#  smtp_auth_password: 'xxx'\n#  # \u4e0d\u4f7f\u7528\u52a0\u5bc6\u8ba4\u8bc1\n#  smtp_require_tls: false\n\n# \u544a\u8b66\u6a21\u677f\ntemplates:\n  - \"\/etc\/alertmanager\/template\/*.tmpl\"\n\nroute:\n  group_by: ['alertname']\n  group_wait: 10s\n  group_interval: 10s\n  repeat_interval: 30m #30\u5206\u949f\u91cd\u590d\u4e00\u6b21\n  receiver: 'ding-hook'\n\nreceivers:\n#  - name: 'mail-receiver'\n#    email_configs:\n#      - to: 'xxx@qq.com'\n#        html: '{{ template \"email.to.html\" .}}'\n#        headers: { Subject: \"[WARN]\u544a\u8b66\" }\n#        send_resolved: true # \u8868\u793a\u670d\u52a1\u6062\u590d\u540e\u4f1a\u6536\u5230\u6062\u590d\u544a\u8b66\n  - name: 'ding-hook'\n    webhook_configs:\n      - url: 'http:\/\/10.80.210.56:8060\/dingtalk\/webhook1\/send'\n        send_resolved: true\n\n# \u544a\u8b66\u6291\u5236\u89c4\u5219\ninhibit_rules:\n  - source_match:\n      severity: 'critical'\n    target_match:\n      severity: 'warning'\n    equal: ['alertname', 'dev', 'instance']\n<\/code><\/pre>\n
    template\u544a\u8b66\u6a21\u677f<\/h5>\n
    dingding.tmpl<\/code><\/h6>\n
    {{ define \"__subject\" }}[{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .GroupLabels.SortedPairs.Values | join \" \" }} {{ if gt (len .CommonLabels) (len .GroupLabels) }}({{ with .CommonLabels.Remove .GroupLabels.Names }}{{ .Values | join \" \" }}{{ end }}){{ end }}{{ end }}\n{{ define \"__alertmanagerURL\" }}{{ .ExternalURL }}\/#\/alerts?receiver={{ .Receiver }}{{ end }}\n\n{{ define \"__text_alert_list\" }}{{ range . }}\n**\u544a\u8b66\u7a0b\u5e8f**\uff1a{{ .Labels.job }}\n\n**\u544a\u8b66\u7ea7\u522b**\uff1a{{ .Labels.severity }} \u7ea7\n\n**\u544a\u8b66\u7c7b\u578b**\uff1a{{ .Labels.alertname }}\n\n**\u6545\u969c\u4e3b\u673a**: {{ .Labels.instance }}\n\n**\u544a\u8b66\u4e3b\u9898**: {{ .Annotations.summary }}\n\n**\u544a\u8b66\u63cf\u53d9**: {{ .Annotations.description }}\n\n**\u544a\u8b66\u65f6\u95f4**: {{ (.StartsAt.Add 28800e9).Format \"2006-01-02 15:04:05\" }}\n\n------------------------\n\n{{ end }}{{ end }}\n\n{{ define \"__text_resolve_list\" }}{{ range .  }}\n**\u6062\u590d\u7a0b\u5e8f**\uff1a{{ .Labels.alertname }}\n\n**\u6545\u969c\u4e3b\u673a**: {{ .Labels.instance }}\n\n**\u544a\u8b66\u4e3b\u9898**\uff1a{{ .Annotations.summary }}\n\n**\u6062\u590d\u63cf\u53d9**: {{ .Annotations.description }}\n\n**\u544a\u8b66\u65f6\u95f4**: {{ (.StartsAt.Add 28800e9).Format \"2006-01-02 15:04:05\" }}\n\n**\u6062\u590d\u65f6\u95f4**: {{ (.EndsAt.Add 28800e9).Format \"2006-01-02 15:04:05\" }}\n\n------------------------\n\n{{ end }}{{ end }}\n\n\n{{ define \"ding.link.title\" }}{{ template \"__subject\" . }}{{ end }}\n{{ define \"ding.link.content\" }}#### \\[{{ .Status | toUpper }}{{ if eq .Status \"firing\" }}:{{ .Alerts.Firing | len }}{{ end }}\\] **[{{ index .GroupLabels \"alertname\" }}]({{ template \"__alertmanagerURL\" . }})**\n{{ if gt (len .Alerts.Firing) 0 -}}\n![\u8b66\u62a5 \u56fe\u6807](https:\/\/qn.199604.com\/typoraImg\/20220810120050.png)\n\n**====\u4fa6\u6d4b\u5230{{ .Alerts.Firing | len  }}\u4e2a\u6545\u969c====**\n\n{{ template \"__text_alert_list\" .Alerts.Firing }}\n{{- end }}\n{{ if gt (len .Alerts.Resolved) 0 -}}\n\u6062\u590d\u5217\u8868:\n{{ template \"__text_resolve_list\" .Alerts.Resolved }}\n{{- end }}\n{{- end }}\n<\/code><\/pre>\n
    \u6548\u679c\uff1a<\/p>\n
    \"image-20220814162535568\"<\/div><\/p>\n
    email.tmpl<\/code><\/h6>\n
    {{ define \"email.to.html\" }}\n{{ if gt (len .Alerts.Firing) 0 }}{{ range .Alerts }}\n@\u544a\u8b66\n\u544a\u8b66\u7a0b\u5e8f: prometheus_alert <br>\n\u544a\u8b66\u7ea7\u522b: {{ .Labels.severity }} \u7ea7 <br>\n\u544a\u8b66\u7c7b\u578b: {{ .Labels.alertname }} <br>\n\u6545\u969c\u4e3b\u673a: {{ .Labels.instance }} <br>\n\u544a\u8b66\u4e3b\u9898: {{ .Annotations.summary }} <br>\n\u544a\u8b66\u8be6\u60c5: {{ .Annotations.description }} <br>\n\u89e6\u53d1\u65f6\u95f4: {{ .StartsAt.Format \"2006-01-02 15:04:05\" }} <br>\n{{ end }}\n{{ end }}\n{{ if gt (len .Alerts.Resolved) 0 }}{{ range .Alerts }}\n@\u6062\u590d\uff1a\n\u6545\u969c\u4e3b\u673a\uff1a{{ .Labels.instance }} <br>\n\u544a\u8b66\u4e3b\u9898\uff1a{{ .Annotations.summary }} <br>\n\u6062\u590d\u65f6\u95f4: {{ .EndsAt.Format \"2006-01-02 15:04:05\" }} <br>\n{{ end }}\n{{ end }}\n{{ end }}\n<\/code><\/pre>\n
    \"image-20220814215003299\"<\/div><\/p>\n
    prometheus-node\u90e8\u7f72<\/h2>\n
    docker-compose.yml<\/code>\u6587\u4ef6\u5185\u5bb9\uff1a<\/h3>\n
    version: '3'\n\nservices:\n  node-exporter:\n    image: prom\/node-exporter:v1.4.0-rc.0\n    container_name: node-exporter\n    hostname: node-exporter\n    restart: always\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    ports:\n      - \"9100:9100\"\n    networks:\n      - monitor\n\n  mysqld-exporter:\n    image: prom\/mysqld-exporter:v0.13.0\n    container_name: mysqld-exporter\n    hostname: mysqld-exporter\n    restart: always\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    environment:\n      # \u6570\u636e\u5e93\u8d26\u53f7:\u5bc6\u7801@ip:\u7aef\u53e3\/\n      DATA_SOURCE_NAME: user:passwd@(ip:port)\/\n    ports:\n      - \"9104:9104\"\n    networks:\n      - monitor\n\n  redis-exporter:\n    image: bitnami\/redis-exporter:1.43.0\n    container_name: redis-exporter\n    hostname: redis-exporter\n    restart: always\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    environment:\n      redis.addr: redis:\/\/10.80.210.122:6379\n      redis.password: abc123456\n    command: #\u53c2\u8003\uff1ahttps:\/\/github.com\/bitnami\/bitnami-docker-redis-exporter https:\/\/github.com\/oliver006\/redis_exporter\n      - '--redis.addr=redis:\/\/10.80.210.122:6379'\n      - '--redis.password=abc123456'\n    ports:\n      - \"9121:9121\"\n    networks:\n      - monitor\n\n  cadvisor:\n    image: google\/cadvisor:latest\n    container_name: cadvisor\n    hostname: cadvisor\n    restart: always\n    volumes:\n      - \/:\/rootfs:ro\n      - \/var\/run:\/var\/run:rw\n      - \/sys:\/sys:ro\n      - \/var\/lib\/docker\/:\/var\/lib\/docker:ro\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    ports:\n      - \"18080:8080\"\n    networks:\n      - monitor\n\n  vmware-exporter-77:\n    image: pryorda\/vmware_exporter:v0.18.3\n    container_name: vmware-exporter-77\n    restart: unless-stopped\n    ports:\n      - '9272:9272'\n    environment:\n      VSPHERE_HOST: \"10.80.211.77\"\n      VSPHERE_IGNORE_SSL: \"True\"\n      VSPHERE_USER: \"user\"\n      VSPHERE_PASSWORD: \"passwd\"\n    volumes:\n      - \/etc\/localtime:\/etc\/localtime:ro\n      - \/etc\/timezone:\/etc\/timezone:ro\n    networks:\n      - monitor\n\nnetworks:\n  monitor:\n    driver: bridge\n<\/code><\/pre>\n
    \u8bf4\u660e\uff1a<\/h4>\n
    \u4f7f\u7528\u4e86\u4ee5\u4e0b\u5bb9\u5668\uff1a<\/h5>\n
      \n
    1. node-exporter #\u91c7\u96c6\u865a\u62df\u673a\u6307\u6807<\/li>\n
    2. mysqld-exporter #mysql\u6570\u636e\u5e93\u91c7\u96c6<\/li>\n
    3. redis-exporter # redis\u6570\u636e\u91c7\u96c6<\/li>\n
    4. cadvisor #\u91c7\u96c6docker\u5bb9\u5668\u6307\u6807<\/li>\n
    5. vmware-exporter #vm\u865a\u62df\u673a\u91c7\u96c6<\/li>\n<\/ol>\n
      Grafana\u5e38\u7528\u6a21\u677f<\/h2>\n
      \u670d\u52a1\u5668\u7cfb\u7edf\u6027\u80fd\u76d1\u63a7\uff1a8919<\/h3>\n
      \"image-20220807145926338\"<\/div><\/p>\n
      \u5fae\u670d\u52a1\u6027\u80fd\u76d1\u63a7\uff1a4701 \u6216 \u6c49\u5316\uff1a12856 \u6216 SpringBoot\u76d1\u63a7\uff1a12900<\/h3>\n
      \"image-20220807150026860\"<\/div><\/p>\n
      Docker\u73af\u5883\u6027\u80fd\u76d1\u63a7\uff1a893<\/h3>\n
      \"image-20220807150123573\"<\/div><\/p>\n
      nacos\u6027\u80fd\u76d1\u63a7\uff1a13221<\/h3>\n
      \"image-20220807150450831\"<\/div><\/p>\n
      mysql\u6027\u80fd\u76d1\u63a7\uff1a9362<\/h3>\n
      \"image-20220807150359831\"<\/div><\/p>\n
      nginx\u6027\u80fd\u76d1\u63a7\uff1a9614<\/h3>\n
      \"image-20220807150246390\"<\/div><\/p>\n
      neo4j\u6027\u80fd\u76d1\u63a7\uff1a10371(\u4f01\u4e1a\u7248\u624d\u652f\u6301)<\/h3>\n
      \"image-20220807150552700\"<\/div><\/p>\n
      Redis\u76d1\u63a7\uff1a763<\/h3>\n
      \"image-20220807151910393\"<\/div><\/p>\n
      tomcat\u76d1\u63a7\uff1a\u6682\u65f6\u5ffd\u60a0<\/h3>\n
      HikariCP\u6570\u636e\u6e90\u76d1\u63a7\uff1a6083\/Druid\u6570\u636e\u6e90\u76d1\u63a7\uff1a11157<\/h3>\n
      \"image-20220807154922411\"<\/div><\/p>\n
      \"image-20220807154938146\"<\/div><\/p>\n
      Jenkins\u76d1\u63a7\uff1a9964<\/h3>\n
      \"image-20220809103518691\"<\/div><\/p>\n
      VMware \u76d1\u63a7\uff1a11243<\/h3>\n
      \"image-20220810172835004\"<\/div><\/p>\n","protected":false},"excerpt":{"rendered":"
      Prometheus+grafana\u544a\u8b66\u7ec4\u4ef6\u5355\u8282\u70b9\u90e8\u7f72\u9a8c\u8bc1 \u6b64\u6b21\u90e8\u7f72\u662f\u4f7f\u7528docker\u5feb\u901f\u9a8c\u8bc1\u90e8\u7f72,\u4e3b\u8981\u9a8c\u8bc1\u4e86 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[402,403],"tags":[226,368,369],"class_list":["post-2355","post","type-post","status-publish","format-standard","hentry","category-grafana","category-prometheus","tag-docker","tag-grafana","tag-prometheus"],"_links":{"self":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts\/2355","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/comments?post=2355"}],"version-history":[{"count":1,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts\/2355\/revisions"}],"predecessor-version":[{"id":2356,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/posts\/2355\/revisions\/2356"}],"wp:attachment":[{"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/media?parent=2355"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/categories?post=2355"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/199604.com\/wp-json\/wp\/v2\/tags?post=2355"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}