CentOS7 编译安装Prometheus🪔

---

一、部署Prometheus

1.下载Prometheus安装包

[root@localhost ~]# wget https://github.com/prometheus/prometheus/releases/download/v2.27.1/prometheus-2.27.1.linux-amd64.tar.gz

2.解压至指定目录

[root@localhost ~]# tar -xvf prometheus-2.27.1.linux-amd64.tar.gz -C /usr/local/

[root@localhost ~]# cd /usr/local

[root@localhost local]# mv prometheus-2.27.1.linux-amd64/  prometheus

3.创建Prometheus用户

[root@localhost ~]# groupadd prometheus
[root@localhost ~]# useradd -g prometheus -s /sbin/nologin prometheus
[root@localhost ~]# mkdir -p /data/prometheus 
[root@localhost ~]# chown -R prometheus:prometheus /usr/local/prometheus/ /data/prometheus/

4.创建system启动服务

[root@localhost ~]# vim /usr/lib/systemd/system/prometheus.service

[Unit]
Description=Prometheus
After=network.target

[Service]
Type=simple
Environment="GOMAXPROCS=4"
User=prometheus
Group=prometheus
ExecReload=/bin/kill -HUP $MAINPID
ExecStart=/usr/local/prometheus/prometheus \
--config.file=/usr/local/prometheus/prometheus.yml \
--storage.tsdb.path=/data/prometheus \
--storage.tsdb.retention=30d \
--web.console.libraries=/usr/local/prometheus/console_libraries \
--web.console.templates=/usr/local/prometheus/consoles \
--web.listen-address=0.0.0.0:9090 \
--web.read-timeout=5m \
--web.max-connections=10 \
--query.max-concurrency=20 \
--query.timeout=2m \
--web.enable-lifecycle
PrivateTmp=true
PrivateDevices=true
ProtectHome=true
NoNewPrivileges=true
LimitNOFILE=infinity
ReadWriteDirectories=/data/prometheus
ProtectSystem=full

SyslogIdentifier=prometheus
Restart=always

[Install]
WantedBy=multi-user.target

5.启动Prometheus

[root@localhost ~]# systemctl daemon-reload

[root@localhost ~]# systemctl start prometheus

[root@localhost ~]# systemctl status prometheus

6.查看端口

[root@localhost ~]# netstat -tnpl | grep prometheus
tcp6       0      0 :::9090                 :::*                    LISTEN      1745/prometheus     

二、部署node_exporter （每台被监控机器需要部署）

1.下载node_exporter安装包

[root@localhost ~]# wget https://github.com/prometheus/node_exporter/releases/download/v1.0.1/node_exporter-1.0.1.linux-amd64.tar.gz

2.解压安装

[root@localhost ~]# tar -xvf node_exporter-1.0.1.linux-amd64.tar.gz -C /usr/local/

[root@localhost ~]# cd /usr/local/

[root@localhost ~]# mv node_exporter-1.0.1.linux-amd64/ node_exporter

3.创建Prometheus用户及目录属主

[root@localhost ~]# useradd -M -s /sbin/nologin prometheus

[root@localhost ~]# chown -R prometheus:prometheus /usr/local/node_exporter

4.编写system服务

[root@localhost ~]# vim /usr/lib/systemd/system/node_exporter.service

[Unit]
Description=node_exporter
After=network.target

[Service]
Type=simple
User=prometheus
Group=prometheus
ExecStart=/usr/local/node_exporter/node_exporter \
--web.listen-address=0.0.0.0:9100 \
--web.telemetry-path=/metrics \
--log.level=info \
--log.format=logfmt
Restart=always

[Install]
WantedBy=multi-user.target

5.开启node_exporter服务

[root@localhost ~]# systemctl daemon-reload

[root@localhost ~]# systemctl start node_exporter

[root@localhost ~]# systemctl status node_exporter

6.查看端口

[root@localhost ~]# netstat -tnlp | grep node_exporter
tcp6       0      0 :::9100                 :::*                    LISTEN      1845/node_exporter

 7.启动好node_exporter后，还需要配置prometheus才能访问node exporter指标

[root@localhost ~] # vim /usr/local/prometheus/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: ["localhost:9090"]
  
  - job_name: 'node'
    static_configs:
      - targets: ['localhost:9100', '192.168.172.141:9100', '192.168.172.142:9100']

8.重启Prometheus

[root@localhost ~]# systemctl restart prometheus

三、AlertManager部署

1.下载alertmanager安装包

[root@localhost ~]# wget https://github.com/prometheus/alertmanager/releases/download/v0.21.0/alertmanager-0.21.0.linux-amd64.tar.gz

2.解压安装

[root@localhost ~]# tar -xvf alertmanager-0.21.0.linux-amd64.tar.gz -C /usr/local

[root@localhost ~]# cd /usr/local

[root@localhost local]# mv alertmanager-0.21.0.linux-amd64 alertmanager

3.创建Prometheus用户及目录属主

[root@localhost ~]# useradd -M -s /sbin/nologin prometheus                         #若已创建，可省略该步
[root@localhost ~]# mkdir /usr/local/alertmanager/data
[root@localhost ~]# chown -R prometheus:prometheus /usr/local/alertmanager
[root@localhost ~]# mkdir -p /var/log/alertmanager                                 # 创建日志目录
[root@localhost ~]# chown prometheus:prometheus /var/log/alertmanager

4.创建system服务

[root@localhost ~]# vim /usr/lib/systemd/system/alertmanager.service 

[Unit]
Description=Alertmanager
After=network.target

[Service]
Type=simple
User=prometheus
Group=prometheus
ExecStart=/usr/local/alertmanager/alertmanager \
--config.file=/usr/local/alertmanager/alertmanager.yml \
--storage.path=/usr/local/alertmanager/data \
--web.listen-address=0.0.0.0:9093 \
--cluster.listen-address=0.0.0.0:9094 \
--log.level=info \
--log.format=logfmt
Restart=always
StandardOutput=file:/var/log/alertmanager/alertmanager.log
StandardError=file:/var/log/alertmanager/alertmanager-error.log

[Install]
WantedBy=multi-user.target

5.启动alertmanager

[root@localhost ~]# systemctl daemon-reload

[root@localhost ~]# systemctl start alertmanager

 6.配置alertmanager

[root@localhost ~]# vim /usr/local/prometheus/prometheus.yml 

global:
  scrape_interval:     15s
  evaluation_interval: 15s



alerting:
  alertmanagers:
  - static_configs:
    - targets:



rule_files:



scrape_configs:
  
  - job_name: 'prometheus'

    static_configs:
    - targets: ['localhost:9090']

  - job_name: 'node'
    
    static_configs:
    - targets: ['localhost:9100','192.168.0.169:9100','192.168.0.221:9100']

  - job_name: 'alertmanager'

    static_configs:
    - targets: ['192.168.0.169:9093']

7.重启Prometheus

[root@localhost ~]# systemctl restart prometheus