global:
  scrape_interval:     15s # By default, scrape targets every 15 seconds.

  # Attach these labels to any time series or alerts when communicating with
  # external systems (federation, remote storage, Alertmanager).
  external_labels:
    monitor: 'codelab-monitor'

# 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'

    # Override the global default and scrape targets from this job every 5 seconds.
    scrape_interval: 5s

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

  # 采集node exporter监控数据
  - job_name: 'vps2'
    static_configs:
      - targets: ['10.28.0.1:9100']

# 创建文件夹
mkdir -p /data/docker/prometheus/data

# 取得nobody的uid
docker run --rm quay.io/prometheus/busybox cat /etc/passwd
···
nobody:x:65534:65534:nobody:/home:/bin/false

# 配置文件夹权限
chown 65534:65534 -R /data/docker/prometheus/data

$ docker run -d \
    --name=prometheus \
    -p 9090:9090 \
    --network=myDefault \
    --restart always \
    --volume /data/docker/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml \
    --volume /data/docker/prometheus/data:/prometheus \
    prom/prometheus:v2.40.4 \
    --web.enable-lifecycle \
    --config.file=/etc/prometheus/prometheus.yml \
    --storage.tsdb.path=/prometheus \
    --storage.tsdb.retention=365d

$ docker run -d \
    --name=prometheus \
    -p 9090:9090 \
    --network=myDefault \
    --restart always \
    --volume /data/docker/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml \
    --volume /data/docker/prometheus/data:/prometheus \
    prom/prometheus:v2.40.4 \
    --web.enable-lifecycle \
    --config.file=/etc/prometheus/prometheus.yml \
    --storage.tsdb.path=/prometheus \
    --storage.tsdb.retention=365d
# --web.enable-lifecycle 允许热加载配置文件
# 注意放在镜像名后面的内容为映射到内部的配置标志

# x86
$ curl -OL https://github.com/prometheus/node_exporter/releases/download/v1.5.0/node_exporter-1.5.0.linux-amd64.tar.gz
$ tar -xzf node_exporter-1.5.0.linux-amd64.tar.gz
$ cp node_exporter-1.5.0.linux-amd64/node_exporter /usr/local/bin/
# arm64
$ curl -OL https://github.com/prometheus/node_exporter/releases/download/v1.5.0/node_exporter-1.5.0.linux-arm64.tar.gz
$ tar -xzf node_exporter-1.5.0.linux-arm64.tar.gz
$ cp node_exporter-1.5.0.linux-arm64/node_exporter /usr/local/bin/

$ sudo useradd -rs /bin/false nodeusr

$ echo "[Unit]
Description=Node Exporter
After=network.target

[Service]
User=nodeusr
Group=nodeusr
Type=simple
ExecStart=/usr/local/bin/node_exporter

[Install]
WantedBy=multi-user.target" > /etc/systemd/system/node_exporter.service

$ sudo systemctl daemon-reload
$ sudo systemctl enable node_exporter && systemctl start node_exporter

$ apt search node_exporter
Sorting... Done
Full Text Search... Done
prometheus-node-exporter-collectors/focal 0+git20200110.fc91c86-1 all
  Supplemental textfile collector scripts for Prometheus node_exporter

$ apt install -y prometheus-node-exporter-collectors

# 启动服务
$ systemctl enable prometheus-node-exporter.service && systemctl start prometheus-node-exporter.service
Synchronizing state of prometheus-node-exporter.service with SysV service script with /lib/systemd/systemd-sysv-install.
Executing: /lib/systemd/systemd-sysv-install enable prometheus-node-exporter

# OpenWRT
opkg update
opkg install prometheus-node-exporter-lua \
prometheus-node-exporter-lua-nat_traffic \
prometheus-node-exporter-lua-netstat \
prometheus-node-exporter-lua-openwrt \
prometheus-node-exporter-lua-wifi \
prometheus-node-exporter-lua-wifi_stations

curl localhost:9100/metrics

cat /etc/config/prometheus-node-exporter-lua
config prometheus-node-exporter-lua 'main'
        option listen_ipv6 '0'
        option listen_port '9100'
        option listen_interface 'lan'

/etc/init.d/prometheus-node-exporter-lua restart

# 方法一  使用 SIGHUP 信号
kill -HUP $(pidof prometheus)
# 方法二 使用 POST 请求，需 --web.enable-lifecycle
curl -X POST http://localhost:9090/-/reload
# 实测两种方法在 Docker 下均不生效，猜测外部修改必须重启才能映射入容器，原因待查

# 这里使用了我在 docker hub 镜像的官方 gcr 源镜像
# 避免无法拉取问题
# 普通 docker hub 镜像即可拉取
$ sudo docker run \
  --restart always \
  --volume=/:/rootfs:ro \
  --volume=/var/run:/var/run:ro \
  --volume=/sys:/sys:ro \
  --volume=/var/lib/docker/:/var/lib/docker:ro \
  --volume=/dev/disk/:/dev/disk:ro \
  --publish=8080:8080 \
  --detach=true \
  --name=cadvisor \
  --privileged \
  --device=/dev/kmsg \
  --net=myDefault \
  songtianlun/cadvisor:v0.46.0
$ curl http://localhost:8080

docker run -d \
    --name=grafana \
    -p 3000:3000 \
    --network=myDefault \
    --restart always \
    grafana/grafana