MENU

现代化监控系统单机部署

• 2022 年 12 月 01 日 • Grafana,Prometheus

现代化监控系统单机部署

 kubernetes会做系统中监控各个性能指标（比如节点cpu、内存、磁盘等），但是传统单机节点也需要从当初的catic、nagios、zabbix等转换到新的监控平台。这篇文章讲告诉大家如何通过容器化编排部署Prometheus+grafana+告警。

一.创建数据文件夹

mkdir -p /mnt/storage/prom/{prometheus,prometheus/data,alertmanager,grafana}
chmod 777 /mnt/storage/prom/{prometheus/data,grafana}
cd /mnt/storage/prom

二.创建配置文件

Prometheus

1.创建告警规则

vim /mnt/storage/prom/prometheus/alert-rules.yml
groups:
  - name: node-alert
    rules:
    - alert: NodeDown
      expr: up{job="node"} == 0
      for: 1m
      labels:
        severity: critical
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} down"
        description: "Instance: {{ $labels.instance }} 已经宕机 1分钟"
        value: "{{ $value }}"
        
    - alert: NodeCpuHigh
      expr: (1 - avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="idle"}[2m]))) * 100 > 85
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} cpu使用率过高"
        description: "CPU 使用率超过 80%"
        value: "{{ $value }}"
 
    - alert: NodeCpuIowaitHigh
      expr: avg by (instance) (irate(node_cpu_seconds_total{job="node",mode="iowait"}[2m])) * 100 > 80
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} cpu iowait 使用率过高"
        description: "CPU iowait 使用率超过 50%"
        value: "{{ $value }}"
 
    - alert: NodeLoad5High
      expr: node_load5 > (count by (instance) (node_cpu_seconds_total{job="node",mode='system'})) * 1.2
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} load(2m) 过高"
        description: "Load(2m) 过高，超出cpu核数 1.2倍"
        value: "{{ $value }}"
 
    - alert: NodeMemoryHigh
      expr: (1 - node_memory_MemAvailable_bytes{job="node"} / node_memory_MemTotal_bytes{job="node"}) * 100 > 90
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} memory 使用率过高"
        description: "Memory 使用率超过 90%"
        value: "{{ $value }}"
 
    - alert: NodeDiskRootHigh
      expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/"}) * 100 > 90
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/ 分区) 使用率过高"
        description: "Disk(/ 分区) 使用率超过 90%"
        value: "{{ $value }}"
 
    - alert: NodeDiskBootHigh
      expr: (1 - node_filesystem_avail_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"} / node_filesystem_size_bytes{job="node",fstype=~"ext.*|xfs",mountpoint ="/boot"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/boot 分区) 使用率过高"
        description: "Disk(/boot 分区) 使用率超过 80%"
        value: "{{ $value }}"
 
    - alert: NodeDiskReadHigh
      expr: irate(node_disk_read_bytes_total{job="node"}[2m]) > 20 * (1024 ^ 2)
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk 读取字节数 速率过高"
        description: "Disk 读取字节数 速率超过 20 MB/s"
        value: "{{ $value }}"
 
    - alert: NodeDiskWriteHigh
      expr: irate(node_disk_written_bytes_total{job="node"}[2m]) > 20 * (1024 ^ 2)
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk 写入字节数 速率过高"
        description: "Disk 写入字节数 速率超过 20 MB/s"
        value: "{{ $value }}"
        
    - alert: NodeDiskReadRateCountHigh
      expr: irate(node_disk_reads_completed_total{job="node"}[2m]) > 3000
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk iops 每秒读取速率过高"
        description: "Disk iops 每秒读取速率超过 3000 iops"
        value: "{{ $value }}"
 
    - alert: NodeDiskWriteRateCountHigh
      expr: irate(node_disk_writes_completed_total{job="node"}[2m]) > 3000
      for: 2m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk iops 每秒写入速率过高"
        description: "Disk iops 每秒写入速率超过 3000 iops"
        value: "{{ $value }}"
 
    - alert: NodeInodeRootUsedPercentHigh
      expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/ 分区) inode 使用率过高"
        description: "Disk (/ 分区) inode 使用率超过 80%"
        value: "{{ $value }}"
 
    - alert: NodeInodeBootUsedPercentHigh
      expr: (1 - node_filesystem_files_free{job="node",fstype=~"ext4|xfs",mountpoint="/boot"} / node_filesystem_files{job="node",fstype=~"ext4|xfs",mountpoint="/boot"}) * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} disk(/boot 分区) inode 使用率过高"
        description: "Disk (/boot 分区) inode 使用率超过 80%"
        value: "{{ $value }}"
        
    - alert: NodeFilefdAllocatedPercentHigh
      expr: node_filefd_allocated{job="node"} / node_filefd_maximum{job="node"} * 100 > 80
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} filefd 打开百分比过高"
        description: "Filefd 打开百分比 超过 80%"
        value: "{{ $value }}"
 
    - alert: NodeNetworkNetinBitRateHigh
      expr: avg by (instance) (irate(node_network_receive_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} network 接收比特数 速率过高"
        description: "Network 接收比特数 速率超过 20MB/s"
        value: "{{ $value }}"
 
    - alert: NodeNetworkNetoutBitRateHigh
      expr: avg by (instance) (irate(node_network_transmit_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m]) * 8) > 20 * (1024 ^ 2) * 8
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} network 发送比特数 速率过高"
        description: "Network 发送比特数 速率超过 20MB/s"
        value: "{{ $value }}"
        
    - alert: NodeNetworkNetinPacketErrorRateHigh
      expr: avg by (instance) (irate(node_network_receive_errs_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 接收错误包 速率过高"
        description: "Network 接收错误包 速率超过 15个/秒"
        value: "{{ $value }}"
 
    - alert: NodeNetworkNetoutPacketErrorRateHigh
      expr: avg by (instance) (irate(node_network_transmit_packets_total{device=~"eth0|eth1|ens33|ens37"}[1m])) > 15
      for: 3m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 发送错误包 速率过高"
        description: "Network 发送错误包 速率超过 15个/秒"
        value: "{{ $value }}"
 
    - alert: NodeProcessBlockedHigh
      expr: node_procs_blocked{job="node"} > 10
      for: 10m
      labels:
        severity: warning
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 当前被阻塞的任务的数量过多"
        description: "Process 当前被阻塞的任务的数量超过 10个"
        value: "{{ $value }}"
 
    - alert: NodeTimeOffsetHigh
      expr: abs(node_timex_offset_seconds{job="node"}) > 3 * 60
      for: 2m
      labels:
        severity: info
        instance: "{{ $labels.instance }}"
      annotations:
        summary: "instance: {{ $labels.instance }} 时间偏差过大"
        description: "Time 节点的时间偏差超过 3m"
        value: "{{ $value }}"

    - alert: WindowsServerCollectorError
      expr: windows_exporter_collector_success == 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Windows Server collector Error (instance {{ $labels.instance }})
        description: "Collector {{ $labels.collector }} was not successful\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
  
    - alert: WindowsServerServiceStatus
      expr: windows_service_status{status="ok"} != 1
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Windows Server service Status (instance {{ $labels.instance }})
        description: "Windows服务状态不正常\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
  
    - alert: WindowsServerCpuUsage
      expr: 100 - (avg by (instance) (rate(windows_cpu_time_total{mode="idle"}[2m])) * 100) > 80
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Windows Server CPU Usage (instance {{ $labels.instance }})
        description: "CPU使用率超过80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
  
    - alert: WindowsServerMemoryUsage
      expr: 100 - ((windows_os_physical_memory_free_bytes / windows_cs_physical_memory_bytes) * 100) > 90
      for: 2m
      labels:
        severity: warning
      annotations:
        summary: Windows Server memory Usage (instance {{ $labels.instance }})
        description: "内存使用率超过90%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
  
    - alert: WindowsServerDiskSpaceUsage
      expr: 100.0 - 100 * ((windows_logical_disk_free_bytes / 1024 / 1024 ) / (windows_logical_disk_size_bytes / 1024 / 1024)) > 80
      for: 2m
      labels:
        severity: critical
      annotations:
        summary: Windows Server disk Space Usage (instance {{ $labels.instance }})
        description: "磁盘使用率超过80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

参考官网告警规则https://awesome-prometheus-alerts.grep.to/rules#windows-server 2.配置Prometheus与Alertmanager通信

vim /mnt/storage/prom/prometheus/prometheus.yml
global:
  scrape_interval:     15s
  evaluation_interval: 15s
 
alerting:
  alertmanagers:
  - static_configs:
    - targets:
      - alertmanager:9093
 
rule_files:
  - "*rules.yml"
  
scrape_configs:
  - job_name: 'prometheus'
    static_configs:
    - targets: ['prometheus:9090']
 
  - job_name: 'node'
    static_configs:
    - targets: ['node-exporter:9100']
 
  - job_name: 'alertmanager'
    static_configs:
    - targets: ['alertmanager:9093']

3.热加载prometheus配置

curl -X POST http://localhost:9090/-/reload

确认加载完成done

Alertmanager

上面配置了prometheus与alertmanager的通信，接下来我们配下alertmanager来实现发送告警信息给我们 这里我们主要以钉钉告警为例子

  1. 钉钉上添加一个钉钉机器人, 设置好名字，群组，选择加签，确定。
  2. 修改prometheus-webook配置文件绑定申请的机器人
vim /mnt/storage/prom/alertmanager/config.yml
templates:
  /etc/alertmanager/dingding.tmpl
targets: webhook: url: https://oapi.dingtalk.com/robot/send?access_token=xxxx #修改为钉钉机器人的webhook secret: xxxx # 配置加签（申请的时候那串数字）
message: title: ‘{{ template “ops.title” . }}’ # 给这个webhook应用上 模板标题 （ops.title是我们模板文件中的title 可在下面给出的模板文件中看到） text: ‘{{ template “ops.content” . }}’ mention: all: true
vim /mnt/storage/prom/alertmanager/alertmanager.yml
global:
  resolve_timeout: 5m
  smtp_smarthost: 'smtp.qiye.163.com:465'             #邮箱smtp服务器代理，启用SSL发信, 端口一般是465
  smtp_from: 'user@163.com'              #发送邮箱名称
  smtp_auth_username: 'user@163.com'              #邮箱名称
  smtp_auth_password: 'password'                #邮箱密码或授权码
  smtp_require_tls: false

templates:
  - '/etc/alertmanager/*.tmpl'  #告警模板位置

route:
  receiver: 'default'  # 根据告警规则组名进行分组
  group_wait: 10s # 分组内第一个告警等待时间，10s内如有第二个告警会合并一个告警
  group_interval: 1m # 发送新告警间隔时间
  repeat_interval: 1h #重复告警间隔发送时间，如果没处理过多久再次发送一次
  group_by: ['alertname'] 
 
inhibit_rules:
- source_match:
    severity: 'critical'
  target_match:
    severity: 'warning'
  equal: ['alertname', 'instance']
  
receivers:
- name: 'default'
  email_configs:
  - to: 'receiver@163.com'
    send_resolved: true
    headers: { Subject: " 【监控告警】 {{ .CommonLabels.alertname }} " } #标题
    html: '{{ template "alertsList.html" . }}' #模板
    
  webhook_configs:
  - url: 'http://dingtalk:8060/dingtalk/webhook/send'
    send_resolved: true  # 在恢复后是否发送恢复消息给接收人

  wechat_configs:
  - send_resolved: true
    message: '{{ template "wechat.default.message" . }}'
    to_party: '2'         # 企业微信中创建的接收告警的部门【告警机器人】的部门ID
    agent_id: '100022222'     # 企业微信中创建的应用的ID
    message_type: markdown #改变格式
    api_secret: 'awgJcJPA'      # 企业微信中，应用的Secret

3.告警模板

vim ./dingding.tmpl ##钉钉
{{ define "__subject" }}
[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}]
{{ end }}
 
 
{{ define "__alert_list" }}{{ range . }}
---
    **告警类型**: {{ .Labels.alertname }} 
    **告警级别**: {{ .Labels.severity }}
    **故障主机**: {{ .Labels.instance }} 
    **告警信息**: {{ .Annotations.description }}
    **触发时间**: {{ (.StartsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}  
{{ end }}{{ end }}
 
{{ define "__resolved_list" }}{{ range . }}
---
    **告警类型**: {{ .Labels.alertname }} 
    **告警级别**: {{ .Labels.severity }}
    **故障主机**: {{ .Labels.instance }} 
    **触发时间**: {{ (.StartsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}  
    **恢复时间**: {{ (.EndsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}
{{ end }}{{ end }}
 
 
{{ define "ops.title" }}
{{ template "__subject" . }}
{{ end }}
 
{{ define "ops.content" }}
{{ if gt (len .Alerts.Firing) 0 }}
**====侦测到{{ .Alerts.Firing | len  }}个故障====**
{{ template "__alert_list" .Alerts.Firing }}
---
{{ end }}
 
{{ if gt (len .Alerts.Resolved) 0 }}
**====恢复{{ .Alerts.Resolved | len  }}个故障====**
{{ template "__resolved_list" .Alerts.Resolved }}
{{ end }}
{{ end }}
 
{{ define "ops.link.title" }}{{ template "ops.title" . }}{{ end }}
{{ define "ops.link.content" }}{{ template "ops.content" . }}{{ end }}
{{ template "ops.title" . }}
{{ template "ops.content" . }}
vim ./email.tmpl ##邮件
{{ define "email.html" }}
{{- if gt (len .Alerts.Firing) 0 -}}
<h2>告警</h2>
<table border="5">
    <tr><td>报警项</td>
        <td>实例</td>
        <td>报警详情</td>
        <td>报警级别</td>
        <td>开始时间</td>
    </tr>
    {{ range $i, $alert := .Alerts }}
        <tr><td>{{ index $alert.Labels "alertname" }}</td>
            <td style="color:#32CD32" >{{ index $alert.Labels "instance" }}</td>
            <td>{{ index $alert.Annotations "description" }}</td>
            <td>{{ $alert.Labels.severity }}</td>
            <td style="color:#FF7F50">{{ $alert.StartsAt.Local.Format "2006-01-02 15:04:05" }}</td>
        </tr>
    {{ end }}
</table>
{{ end }}
{{- if gt (len .Alerts.Resolved) 0 -}}
<h2>已经恢复</h2>
<table border="5">
    <tr><td>报警项</td>
        <td>实例</td>
        <td>报警详情</td>
        <td>报警级别</td>
        <td>开始时间</td>
        <td>恢复时间</td>
    </tr>
    {{ range $i, $alert := .Alerts }}
        <tr><td>{{ index $alert.Labels "alertname" }}</td>
            <td style="color:#32CD32">{{ index $alert.Labels "instance" }}</td>
            <td>{{ index $alert.Annotations "description" }}</td>
            <td>{{ $alert.Labels.severity }}</td>
            <td style="color:#FF7F50">{{ $alert.StartsAt.Local.Format "2006-01-02 15:04:05" }}</td>
            <td style="color:#FF7F50">{{ $alert.EndsAt.Local.Format "2006-01-02 15:04:05" }}</td>
        </tr>
    {{ end }}
</table>
{{ end }}{{- end }}

vim ./wechat.tmpl ##企业微信
{{ define "wechat.message" }}
{{- if gt (len .Alerts.Firing) 0 -}}
{{- range $index, $alert := .Alerts -}}
{{- if eq $index 0 -}}
# 报警项: {{ $alert.Labels.alertname }}
{{- end }}
> `**===告警详情===**` 
> 告警级别: {{ $alert.Labels.severity }}
> 告警详情: <font color="comment">{{ index $alert.Annotations "description" }}{{ $alert.Annotations.message }}</font>
> 故障时间: <font color="warning">{{ $alert.StartsAt.Local.Format "2006-01-02 15:04:05" }}</font>
> 故障实例: <font color="info">{{ $alert.Labels.instance }}</font>
{{- end }}
{{- end }}
{{- if gt (len .Alerts.Resolved) 0 -}}
{{- range $index, $alert := .Alerts -}}
{{- if eq $index 0 -}}
# 恢复项: {{ $alert.Labels.alertname }}
{{- end }}
> `**===恢复详情===**` 
> 告警级别: {{ $alert.Labels.severity }}
> 告警详情: <font color="comment">{{ index $alert.Annotations "description" }}{{ $alert.Annotations.message }}</font>
> 故障时间: <font color="warning">{{ $alert.StartsAt.Local.Format "2006-01-02 15:04:05" }}</font>
> 恢复时间: <font color="warning">{{ $alert.EndsAt.Local.Format "2006-01-02 15:04:05" }}</font>
> 故障实例: <font color="info">{{ $alert.Labels.instance }}</font>
{{- end }}
{{- end }}
{{- end }}

三.创建docker-compose.yaml

vim /mnt/storage/prom/docker-compose.yml
version: '3.7'
 
services:
  node-exporter:
    image: prom/node-exporter:latest
    ports:
      - "9100:9100"
    networks:
      - prom
 
  dingtalk:
    image: timonwong/prometheus-webhook-dingtalk:latest
    volumes:
      - type: bind
        source: ./alertmanager/config.yml
        target: /etc/prometheus-webhook-dingtalk/config.yml
        read_only: true
      - type: bind
        source: ./alertmanager/dingding.tmpl
        target: /etc/alertmanager/dingding.tmpl
        read_only: true
    ports:
      - "8060:8060"
    networks:
      - prom
 
  alertmanager:
    depends_on:
      - dingtalk
    image: prom/alertmanager:latest
    volumes:
      - type: bind
        source: ./alertmanager/alertmanager.yml
        target: /etc/alertmanager/alertmanager.yml
        read_only: true
      - type: bind
        source: ./alertmanager/dingding.tmpl
        target: /etc/alertmanager/dingding.tmpl
        read_only: true
      - type: bind
        source: ./alertmanager/email.tmpl
        target: /etc/alertmanager/email.tmpl
        read_only: true
      - type: bind
        source: ./alertmanager/wechat.tmpl
        target: /etc/alertmanager/wechat.tmpl
        read_only: true
    ports:
      - "9093:9093"
      - "9094:9094"
    networks:
      - prom
 
  prometheus:
    depends_on:
      - alertmanager
    image: prom/prometheus:latest
    volumes:
      - type: bind
        source: ./prometheus/prometheus.yml
        target: /etc/prometheus/prometheus.yml
        read_only: true
      - type: bind
        source: ./prometheus/alert-rules.yml
        target: /etc/prometheus/alert-rules.yml
        read_only: true
      - type: volume
        source: prometheus
        target: /prometheus
    ports:
      - "9090:9090"
    networks:
      - prom
 
  grafana:
    depends_on:
      - prometheus
    image: grafana/grafana:latest
    volumes:
      - type: volume
        source: grafana
        target: /var/lib/grafana
    ports:
      - "3000:3000"
    networks:
      - prom
 
volumes:
  prometheus:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /Users/sk/Desktop/k3s/prometheus/prom/prometheus/data
  grafana:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /Users/sk/Desktop/k3s/prometheus/prom/grafana
      
networks:
  prom:
    driver: bridge

启动配置granafa 模板8919 16098 https://grafana.com/grafana/dashboards/16098-1-node-exporter-for-prometheus-dashboard-cn-0417-job/

四.服务端

1.安装软件

tar -xf node_exporter-1.0.0-rc.0.linux-amd64.tar.gz
ls
mv node_exporter-1.0.0-rc.0.linux-amd64 /usr/local/node_exporter
ls /usr/local/node_exporter

2.编写服务service文件

vim /usr/lib/systemd/system/node_exporter.service
[Unit]
Description=node_exporter
After=network.target
[Service]
Type=simple
ExecStart=/usr/local/node_exporter/node_exporter
[Install]
WantedBy=multi-user.target

systemctl  enable node_exporter –now

--------------------------------------------------------
#配置开机自启
vim /etc/rc.local

/usr/wubin/node_exporter1.1/node_exporter &

3.设置防火墙、SELinux

firewall-cmd --set-default-zone=trusted
setenforce 0
sed -i '/SELINUX/s/enforcing/permissive/' /etc/selinux/config

五.测试

1.我们可以通过故意调整阈值 或者 停掉告警检测中主机上的node_exporter探针来测试一下

systemctl stop node_exporter.service

2.prometheus上可以看到已经触发了告警规则阈值done3.此时钉钉群和邮箱里收到了告警邮件donedonedonedone4.其他测试 CPU

stress --cpu 4
# 4个CPU核心设置满载状态

内存

# 表示运行3个进程，每个进程分配500M内存
stress --vm 3 --vm-bytes 500M --vm-keep

内存

# github地址
https://github.com/woodcutter-wg/agp
GrafanaPrometheus告警
添加新评论