# prometheus
mkdir -m=777 -p /data/{download,app_logs,app/prometheus}
cd /data/download
wget https://github.com/prometheus/prometheus/releases/download/v2.45.0-rc.0/prometheus-2.45.0-rc.0.linux-amd64.tar.gz
tar xvfz prometheus-*.tar.gz
ln -s /data/download/prometheus-2.45.0-rc.0.linux-amd64/prometheus /usr/bin/prometheus
cp /data/download/prometheus-2.45.0-rc.0.linux-amd64/prometheus.yml /data/app/prometheus/prometheus.yml 
prometheus --config.file=/data/app/prometheus/prometheus.yml --web.listen-address=:9090 --web.enable-lifecycle --storage.tsdb.path=/data/app/prometheus/data >>/data/app_logs/prometheus.log 2>&1 &
# node_exporter 在需要監(jiān)控的服務(wù)器里安裝
mkdir -m=777 -p /data/{download,app_logs,app/prometheus}
cd /data/download
wget https://github.com/prometheus/node_exporter/releases/download/v1.6.0/node_exporter-1.6.0.linux-amd64.tar.gz
tar xvfz node_exporter*
ln -s /data/download/node_exporter-1.6.0.linux-amd64/node_exporter /usr/bin/node_exporter
# 啟動(dòng)node_exporter,服務(wù)器暴露的端口是8080，同時(shí)服務(wù)器里有其他服務(wù)占用了8080端口，可以使用nginx將node_exporter獲取指標(biāo)的api暴露出去
# location /metrics {
#     proxy_pass http://127.0.0.1:9000/metrics;
# }
node_exporter --web.listen-address 127.0.0.1:9000 >>/data/app_logs/node_exporter.log 2>&1 &
# 添加node_exporter之后，需要更新prometheus.xml添加targets，然后運(yùn)行：curl -X PUT http://server_address:port/-/reload重新加載配置文件
# alert_manager可以和prometheus安裝到同一臺(tái)服務(wù)器
cd /data/download
wget https://github.com/prometheus/alertmanager/releases/download/v0.25.0/alertmanager-0.25.0.linux-amd64.tar.gz
tar xvfz alertmanager*
ln -s /data/download/alertmanager-0.25.0.linux-amd64/alertmanager /usr/bin/alertmanager
cp /data/download/alertmanager-0.25.0.linux-amd64/alertmanager.yml /data/app/prometheus/alertmanager.yml
alertmanager --config.file=/data/app/prometheus/alertmanager.yml --web.listen-address 127.0.0.1:9001 >>/data/app_logs/node_exporter.log 2>&1 &
# 將alert_manager的地址添加到prometheus.yml里的alertmanagers的targets里，然后運(yùn)行：curl -X PUT http://server_address:port/-/reload重新加載配置文件

# 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:
          - 127.0.0.1:9001
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
  # - "first_rules.yml"
  # - "second_rules.yml"
  - "/data/app/prometheus/alert.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'.
    scrape_interval: 5s
    static_configs:
            - targets: ["node1_ip:8080"]
            - targets: ["node2_ip:8080"]
              labels:
                groups: 'container'

groups:
- name: tcp-alert-group
  rules:
  - alert: TcpTimeWait
    expr: node_sockstat_TCP_tw > 10
    for: 10m
    labels:
      severity: warning
    annotations:
      summary: tcp time wait more than 10
      description: please check node_sockstat_TCP_tw metric
  - alert: MemoryUse
    expr: (node_memory_MemTotal_bytes-node_memory_MemFree_bytes-node_memory_Buffers_bytes-node_memory_Cached_bytes)/node_memory_MemTotal_bytes > 0.5
    for: 10m
    labels:
      severity: warning
    annotations:
      summary: memory use more than 50% for 10 min
      description: please check memory use

global:
  resolve_timeout: 5m
  smtp_smarthost: your_smpt_host:port
  smtp_from: alertmanager@your_email_domain
  smtp_require_tls: false
route:
  group_by: ['alertname']
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 10m
  receiver: 'email'
receivers:
  - name: 'email'
    email_configs:
    - to: 'receiver_email'
      send_resolved: true

# grafana可以和prometheus里安裝到同一臺(tái)服務(wù)器
yum install -y https://dl.grafana.com/enterprise/release/grafana-enterprise-10.0.0-1.x86_64.rpm
# grafana默認(rèn)啟動(dòng)的端口號(hào)是3000，如果服務(wù)器沒有暴露3000端口的話，需要修改grafana的配置文件
sed -i 's/3000/8080/g' /usr/share/grafana/conf/defaults.ini
grafana server >> /data/app_logs/grafana.log 2>&1 &
# grafana數(shù)據(jù)保存地址：/var/lib/grafana.db