4.prometheus监控--监控linux服务器

一、监控linux服务器

1.1 二进制安装

# 客户端操作
wget https://github.com/prometheus/node_exporter/releases/download/v1.7.0/node_exporter-1.7.0.linux-amd64.tar.gz

tar xvf node_exporter-1.7.0.linux-amd64.tar.gz

ls -l

mv node_exporter-1.7.0.linux-amd64/* /opt/prometheus/node_exporter
useradd -M -s /usr/sbin/nologin prometheus
chown prometheus:prometheus -R /opt/prometheus/node_exporter

# 创建system服务
cat > /etc/systemd/system/node_exporter.service <<"EOF"
[Unit]
Description=node_exporter
Documentation=https://prometheus.io/
After=network.target
[Service]
User=prometheus
Group=prometheus
ExecStart=/opt/prometheus/node_exporter/node_exporter
Restart=on-failure
[Install]
WantedBy=multi-user.target
EOF

# 启动服务
systemctl daemon-reload
systemctl start node_exporter.service
systemctl enable node_exporter.service
systemctl status node_exporter.service
journalctl -u node_exporter.service -f  # 查看日志

服务端操作

# 修改prometheus配置
nano /opt/prometheus/prometheus/prometheus.yml

# 再scrape_configs这行下面添加如下配置：
  #node-exporter配置
  - job_name: 'node-exporter'
    scrape_interval: 15s
    static_configs:
    - targets: ['192.168.10.14:9100']
      labels:
        instance: test服务器

# 重载prometheus
curl -X POST http://localhost:9090/-/reload

1.2 docker 或docker-compose安装客户端

# docker安装
docker run -d -p 9100:9100 \
 -v "/proc:/host/proc:ro" \
 -v "/sys:/host/sys:ro" \
 -v "/:/rootfs:ro" \
 --net="host" \
 prom/node-exporter

# docker-compose安装
mkdir /data/node_exporter -p

cd /data/node_exporter

cat > docker-compose.yaml <<"EOF"
version: '3.3'
services:
  node_exporter:
    image: prom/node-exporter:v1.5.0
    container_name: node-exporter
    restart: always
    network_mode: "host"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--web.listen-address=:9100'
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - "--path.rootfs=/rootfs"
      - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc|rootfs/var/lib/docker)($$|/)'
EOF

# 启动和检查
docker-compose up -d

docker ps
或：
docker logs -f node-exporter

http://192.168.10.100:9100/metrics

修改服务端prometheus.yml配置文件

# 增加
  - job_name: 'node-exporter'
    scrape_interval: 15s
    static_configs:
    - targets: ['node_exporter:9100']
      labels:
        instance: Prometheus服务器
    - targets: ['192.168.10.100:9100']
      labels:
        instance: test服务器

# 重载服务端配置
curl -X POST http://localhost:9090/-/reload

二、常用监控指标

查看：http://192.168.10.14:9090/graph

2.1 cpu采集

node_cpu_seconds_total

名称	含义
node_load1	1分钟内cpu负载
node_load5	5分钟内cpu负载
node_load15	15分钟内cpu负载

2.2 内存采集/proc/meminfo文件

node_memory_

node_memory_MemTotal_bytes 内存总大小

node_memory_MemAvailable_bytes 空闲可使用内存大小(=free+buffer+cache)

node_memory_MemFree_bytes 空闲物理内存大小

2.3 磁盘采集

node_disk_

node_disk_read_bytes_total  自exporter启动以来从磁盘读取的总字节数

node_disk_written_bytes_total 自exporter启动以来写入到磁盘的总字节数

2.4 文件系统采集

node_filesystem_avail_bytes 空闲磁盘大小，单位字节  /1024/1024=MB，/1024/1024/1024=GB

node_filesystem_size_bytes 磁盘总大小

node_filesystem_files_free  空inode大小，单位个

node_filesystem_files inode总大小，大卫个

2.5 网络采集

node_network_

node_network_transmit_bytes_total    网络流出流量，单位字节（Byte）/1024/1024=Mb/s

node_network_receive_bytes_tota      网络流入流量，单位字节（Byte）

2.6 文件描述符

node_filefd_allocated: 已分配的文件描述符数。通过cat /proc/sys/fs/file-nr查看
node_filefd_maximum: 系统支持的最大文件描述符数,通过/proc/sys/fs/file-max或/proc/sys/fs/file-nr

2.7 进程文件描述符

process_max_fds: 进程可打开的最大文件描述符数。
process_open_fds: node_exporter进程当前打开的文件描述符数。 通过ls /proc/$PID/fd 2>/dev/null | wc -l 计算

2.8 socket

node_sockstat_sockets_used # 使用的 Socket 数
node_sockstat_TCP_inuse # 监听的 TCP Socket 数
node_sockstat_TCP_tw

2.9 TCP/UDP协议

node_netstat_Tcp_CurrEstab # ESTABLISHED 加 CLOSE_WAIT 状态的 TCP 连接数
node_netstat_Tcp_InSegs # 接收的 TCP 包数（包括错误的）
node_netstat_Tcp_InErrs # 接收的 TCP 错误包数（比如校验和错误）
node_netstat_Tcp_OutSegs # 发送的 TCP 包数
node_netstat_Udp_InDatagrams # 接收的 UDP 包数
node_netstat_Udp_InErrors # 接收的 UDP 错误包数
node_netstat_Udp_OutDatagrams # 发送的 UDP 包数

三、触发器设置

cd /data/docker-prometheus/

cat >> prometheus/alert.yml <<"EOF"
- name: node-exporter
  rules:
  - alert: HostOutOfMemory
    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "主机内存不足,实例:{{ $labels.instance }}"
      description: "内存可用率<10%，当前值：{{ $value }}"
  - alert: HostMemoryUnderMemoryPressure
    expr: rate(node_vmstat_pgmajfault[1m]) > 1000
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "内存压力不足,实例:{{ $labels.instance }}"
      description: "节点内存压力大。 重大页面错误率高，当前值为：{{ $value }}"
  - alert: HostUnusualNetworkThroughputIn
    expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "异常流入网络吞吐量,实例:{{ $labels.instance }}"
      description: "网络流入流量 > 100 MB/s，当前值：{{ $value }}"
  - alert: HostUnusualNetworkThroughputOut
    expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "异常流出网络吞吐量，实例:{{ $labels.instance }}"
      description: "网络流出流量 > 100 MB/s，当前值为：{{ $value }}"
  - alert: HostUnusualDiskReadRate
    expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) / 1024 / 1024 > 50
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "异常磁盘读取,实例:{{ $labels.instance }}"
      description: "磁盘读取> 50 MB/s，当前值：{{ $value }}"
  - alert: HostUnusualDiskWriteRate
    expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) / 1024 / 1024 > 50
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "异常磁盘写入,实例:{{ $labels.instance }}"
      description: "磁盘写入> 50 MB/s，当前值：{{ $value }}"
  - alert: HostOutOfDiskSpace
    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "磁盘空间不足告警,实例:{{ $labels.instance }}"
      description: "剩余磁盘空间< 10% ，当前值：{{ $value }}"
  - alert: HostDiskWillFillIn24Hours
    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) predict_linear(node_filesystem_avail_bytes{fstype!~"tmpfs"}[1h], 24 * 3600) < 0 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "磁盘空间将在24小时内耗尽,实例:{{ $labels.instance }}"
      description: "以当前写入速率预计磁盘空间将在 24 小时内耗尽，当前值：{{ $value }}"
  - alert: HostOutOfInodes
    expr: node_filesystem_files_free{mountpoint ="/"} / node_filesystem_files{mountpoint="/"} * 100 < 10 and ON (instance, device, mountpoint) node_filesystem_readonly{mountpoint="/"} == 0
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "磁盘Inodes不足,实例:{{ $labels.instance }}"
      description: "剩余磁盘 inodes < 10%，当前值： {{ $value }}"
  - alert: HostUnusualDiskReadLatency
    expr: rate(node_disk_read_time_seconds_total[1m]) / rate(node_disk_reads_completed_total[1m]) > 0.1 and rate(node_disk_reads_completed_total[1m]) > 0
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "异常磁盘读取延迟,实例:{{ $labels.instance }}"
      description: "磁盘读取延迟 > 100ms，当前值：{{ $value }}"
  - alert: HostUnusualDiskWriteLatency
    expr: rate(node_disk_write_time_seconds_total[1m]) / rate(node_disk_writes_completed_total[1m]) > 0.1 and rate(node_disk_writes_completed_total[1m]) > 0
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "异常磁盘写入延迟,实例:{{ $labels.instance }}"
      description: "磁盘写入延迟 > 100ms，当前值：{{ $value }}"
  - alert: high_load
    expr: node_load1 > 4
    for: 2m
    labels:
      severity: page
    annotations:
      summary: "CPU1分钟负载过高,实例:{{ $labels.instance }}"
      description: "CPU1分钟负载>4，已经持续2分钟。当前值为：{{ $value }}"
  - alert: HostCpuIsUnderUtilized
    expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "cpu负载高,实例:{{ $labels.instance }}"
      description: "cpu负载> 80%，当前值：{{ $value }}"
  - alert: HostCpuStealNoisyNeighbor
    expr: avg by(instance) (rate(node_cpu_seconds_total{mode="steal"}[5m])) * 100 > 10
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: "CPU窃取率异常,实例:{{ $labels.instance }}"
      description: "CPU 窃取率 > 10%。 嘈杂的邻居正在扼杀 VM 性能，或者 Spot 实例可能失去信用，当前值：{{ $value }}"
  - alert: HostSwapIsFillingUp
    expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "磁盘swap空间使用率异常,实例:{{ $labels.instance }}"
      description: "磁盘swap空间使用率>80%"
  - alert: HostNetworkReceiveErrors
    expr: rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "异常网络接收错误,实例:{{ $labels.instance }}"
      description: "网卡{{ $labels.device }}在过去2分钟接收错误率大于0.01，当前值:{{ $value }}"
  - alert: HostNetworkTransmitErrors
    expr: rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "异常网络传输错误,实例:{{ $labels.instance }}"
      description: "网卡{{ $labels.device }}在过去2分钟传输错误率大于0.01，当前值:{{ $value }}"
  - alert: HostNetworkInterfaceSaturated
    expr: (rate(node_network_receive_bytes_total{device!~"^tap.*"}[1m]) + rate(node_network_transmit_bytes_total{device!~"^tap.*"}[1m])) / node_network_speed_bytes{device!~"^tap.*"} > 0.8 < 10000
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "异常网络接口饱和,实例:{{ $labels.instance }}"
      description: "网卡{{ $labels.device }}正在超载，当前值{{ $value }}"
  - alert: HostConntrackLimit
    expr: node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 0.8
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "异常连接数,实例:{{ $labels.instance }}"
      description: "连接数过大，当前连接数：{{ $value }}"
  - alert: HostClockSkew
    expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "异常时钟偏差,实例:{{ $labels.instance }}"
      description: "检测到时钟偏差，时钟不同步。值为：{{ $value }}"
  - alert: HostClockNotSynchronising
    expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: "时钟不同步,实例:{{ $labels.instance }}"
      description: "时钟不同步"
  - alert: NodeFileDescriptorLimit
    expr: node_filefd_allocated / node_filefd_maximum * 100 > 80
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "预计内核将很快耗尽文件描述符限制"
      description: "{{ $labels.instance }}｝已分配的文件描述符数超过了限制的80%，当前值为：{{ $value }}"
EOF

检查rule配置文件是否有问题：

docker exec -it prometheus promtool check config /etc/prometheus/prometheus.yml

# 重载配置
curl -X POST http://localhost:9090/-/reload

查看：http://192.168.10.14:9090/alerts?search=，可以发现alters多了刚才定义的

四、grafana展示node-exporter数据

由于grafana已经添加了1860模版，可以直接登录查看

http://192.168.10.14:3000/login