1. prometheus-添加监控linux服务器

• prometheus添加监控linux服务器

  • node_exporter：用于监控Linux系统的指标采集器。
  • 常用指标：
    • CPU
    • 内存
    • 硬盘
    • 网络流量
    • 文件描述符
    • 系统负载
    • 系统服务
  • 数据接口：http://IP:9100
  • 使用文档：https://prometheus.io/docs/guides/node-exporter/
  • GitHub：https://github.com/prometheus/node_exporter

• 安装部署

  • 下载node_exporter包

    https://github.com/prometheus/node_exporter/releases/download/v1.1.2/node_exporter-1.1.2.linux-amd64.tar.gz

  • 监控端主机下载

    [root@VM-0-17-centos ~]# wget https://github.com/prometheus/node_exporter/releases/download/v1.1.2/node_exporter-1.1.2.linux-amd64.tar.gz

  • 解压

    [root@VM-0-17-centos ~]# tar  -xvf node_exporter-1.1.2.linux-amd64.tar.gz
    node_exporter-1.1.2.linux-amd64/
    node_exporter-1.1.2.linux-amd64/LICENSE
    node_exporter-1.1.2.linux-amd64/NOTICE
    node_exporter-1.1.2.linux-amd64/node_exporter

  • 拷贝到opt目录下存放

    [root@VM-0-17-centos ~]# mv node_exporter-1.1.2.linux-amd64 /opt/
    [root@VM-0-17-centos ~]# ll /opt/node_exporter-1.1.2.linux-amd64/
    total 18748
    -rw-r--r-- 1 3434 3434    11357 Mar  5 17:41 LICENSE
    -rwxr-xr-x 1 3434 3434 19178528 Mar  5 17:29 node_exporter
    -rw-r--r-- 1 3434 3434      463 Mar  5 17:41 NOTICE
    [root@VM-0-17-centos ~]# mv /opt/node_exporter-1.1.2.linux-amd64 /opt/node_exporter

  • 切换目录

    [root@VM-0-17-centos ~]# cd /opt/node_exporter/
    [root@VM-0-17-centos node_exporter]# ll
    total 18748
    -rw-r--r-- 1 3434 3434    11357 Mar  5 17:41 LICENSE
    -rwxr-xr-x 1 3434 3434 19178528 Mar  5 17:29 node_exporter
    -rw-r--r-- 1 3434 3434      463 Mar  5 17:41 NOTICE

  • 启动服务尝试

    [root@VM-0-17-centos node_exporter]# ./node_exporter
    level=info ts=2021-05-19T07:00:05.583Z caller=node_exporter.go:178 msg="Starting node_exporter" version="(version=1.1.2, branch=HEAD, revision=b597c1244d7bef49e6f3359c87a56dd7707f6719)"
    level=info ts=2021-05-19T07:00:05.583Z caller=node_exporter.go:179 msg="Build context" build_context="(go=go1.15.8, user=root@f07de8ca602a, date=20210305-09:29:10)"
    level=warn ts=2021-05-19T07:00:05.583Z caller=node_exporter.go:181 msg="Node Exporter is running as root user. This exporter is designed to run as unpriviledged user, root is not required."
    level=info ts=2021-05-19T07:00:05.583Z caller=filesystem_common.go:74 collector=filesystem msg="Parsed flag --collector.filesystem.ignored-mount-points" flag=^/(dev|proc|sys|var/lib/docker/.+)($|/)
    level=info ts=2021-05-19T07:00:05.583Z caller=filesystem_common.go:76 collector=filesystem msg="Parsed flag --collector.filesystem.ignored-fs-types" flag=^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:106 msg="Enabled collectors"
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=arp
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=bcache
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=bonding
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=btrfs
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=conntrack
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=cpu
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=cpufreq
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=diskstats
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=edac
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=entropy
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=fibrechannel
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=filefd
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=filesystem
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=hwmon
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=infiniband
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=ipvs
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=loadavg
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=mdadm
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=meminfo
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=netclass
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=netdev
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=netstat
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=nfs
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=nfsd
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=powersupplyclass
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=pressure
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=rapl
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=schedstat
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=sockstat
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=softnet
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=stat
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=textfile
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=thermal_zone
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=time
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=timex
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=udp_queues
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=uname
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=vmstat
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=xfs
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:113 collector=zfs
    level=info ts=2021-05-19T07:00:05.584Z caller=node_exporter.go:195 msg="Listening on" address=:9100
    level=info ts=2021-05-19T07:00:05.584Z caller=tls_config.go:191 msg="TLS is disabled." http2=false

• 配置为系统服务管理

  • 编写系统配置服务

    [root@iZj6cbgktk3zjpge312vq1Z node_exporter]# vim  /usr/lib/systemd/system/node_exporter.service
    [root@iZj6cbgktk3zjpge312vq1Z node_exporter]# cat  /usr/lib/systemd/system/node_exporter.service
    [Unit]
    Description=node_exporter
    [Service]
    # 添加认证密码文件/opt/node_exporter/config.yml ，默认可以不需要
    ExecStart=/opt/node_exporter/node_exporter --web.config=/opt/node_exporter/config.yml
    ExecReload=/bin/kill -HUP $MAINPID
    KillMode=process
    Restart=on-failure
    [Install]
    WantedBy=multi-user.target

  • 添加config配置文件

    [root@VM-0-17-centos node_exporter]# yum install httpd-tools –y
    [root@VM-0-17-centos node_exporter]# htpasswd -nBC 12 '' | tr -d ':\n'
    New password:       #这里输入的123456
    Re-type new password:    #这里输入的123456
    $2y$12$.YGKNPkYfSOsm.JataWRUe4vWdTS8nW6YtPQI0Jr14eTv6E5Fpdga          # 这段是生成的key

  • 编写启动配置文件

    [root@iZj6cbgktk3zjpge312vq1Z node_exporter]# vim config.yml
    [root@iZj6cbgktk3zjpge312vq1Z node_exporter]# cat config.yml
    basic_auth_users:
      prometheus: $2y$12$.YGKNPkYfSOsm.JataWRUe4vWdTS8nW6YtPQI0Jr14eTv6E5Fpdga

  • 启动服务

    systemctl daemon-reload
    systemctl start node_exporter
    systemctl enable node_exporter

• 在prometheus添加主机

  • 添加配置文件

    [root@iZj6cbgktk3zjpge312vq2Z prometheus]# vim prometheus.yml
    [root@iZj6cbgktk3zjpge312vq2Z prometheus]# cat prometheus.yml
    # my global config
    global:
      scrape_interval:     15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
      evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
      # scrape_timeout is set to the global default (10s).
    
    # Alertmanager configuration
    alerting:
      alertmanagers:
      - static_configs:
        - targets:
          # - alertmanager:9093
    
    # Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
    rule_files:
      # - "first_rules.yml"
      # - "second_rules.yml"
    
    # A scrape configuration containing exactly one endpoint to scrape:
    # Here it's Prometheus itself.
    scrape_configs:
      # The job name is added as a label `job=<job_name>` to any timeseries scraped from this config.
      - job_name: 'prometheus'
    # metrics_path defaults to '/metrics'
    # scheme defaults to 'http'.
    
    static_configs:
    - targets: ['127.0.0.1:9090']
      - job_name: linux
        # 添加监控主机的用户和密码
        basic_auth:
          username: prometheus
          password: 123456
        static_configs:
          - targets: ['10.1.2.211:9100']
            labels:
              prod: web

  • 重启服务

    [root@iZj6cbgktk3zjpge312vq2Z prometheus]# /bin/systemctl restart prometheus

• 在Prometheus配置文件添加被监控端：

  • 验证prometheus配置文件

  • 验证发现已经有数据了

• 使用Grafana展示node_exporter数据指标，仪表盘ID：9276

  • 导入仪表盘

  • 添加