groups:
– name: server_alerts
rules:
– alert: HighCPUUsage
expr: (100 – (avg by(instance) (irate(node_cpu_seconds_total{mode=”idle”}[5m])) * 100) > 80
for: 5m
labels:
severity: warning
annotations:
summary: “High CPU Usage on {{ $labels.instance }}”
description: “CPU usage is above 80% for 5 minutes”

– alert: HighMemoryUsage
expr: (1 – (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
for: 5m
labels:
severity: warning
annotations:
summary: “High Memory Usage on {{ $labels.instance }}”
description: “Memory usage is above 85% for 5 minutes”

– alert: HighDiskUsage
expr: (1 – (node_filesystem_avail_bytes{mountpoint=”/”} / node_filesystem_size_bytes{mountpoint=”/”})) * 100 > 90
for: 5m
labels:
severity: warning
annotations:
summary: “High Disk Usage on {{ $labels.instance }}”
description: “Disk usage is above 90% for 5 minutes”

# 在prometheus.yml中引用告警规则
$ vim /path/to/prometheus/prometheus.yml

rule_files:
– “rules/server_alerts.yml”

# 重启Prometheus
$ sudo systemctl restart prometheus

# 在Grafana中配置告警通知
1. 点击左侧菜单的”Alerting” -> “Notification channels”
2. 点击”Add channel”
3. 配置通知方式（邮件、Slack等）
4. 点击”Save”

# 查看cAdvisor状态
$ docker ps | grep cadvisor

CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
xxxxxxxxxxxx gcr.io/cadvisor/cadvisor:v0.47.0 “/usr/bin/cadvisor -logtostderr” 2 minutes ago Up 2 minutes 0.0.0.0:8080->8080/tcp cadvisor

# 访问cAdvisor web界面
# 浏览器打开 http://localhost:8080

scrape_configs:
– job_name: ‘cadvisor’
static_configs:
– targets: [‘localhost:8080’]

# 重启Prometheus
$ sudo systemctl restart prometheus

# 导入容器监控面板
1. 点击左侧菜单的”Dashboards” -> “Import”
2. 输入面板ID：14282（cAdvisor Exporter）
3. 选择Prometheus数据源
4. 点击”Import”
5. 查看容器监控面板，包含：
– 容器CPU使用率
– 容器内存使用情况
– 容器网络流量
– 容器磁盘I/O

# 安装Elasticsearch
$ sudo dnf install elasticsearch -y
$ sudo systemctl start elasticsearch
$ sudo systemctl enable elasticsearch

# 安装Logstash
$ sudo dnf install logstash -y
$ sudo systemctl start logstash
$ sudo systemctl enable logstash

# 安装Kibana
$ sudo dnf install kibana -y
$ sudo systemctl start kibana
$ sudo systemctl enable kibana

# 配置Logstash接收rsyslog日志
$ sudo vim /etc/logstash/conf.d/rsyslog.conf

input {
syslog {
port => 514
type => syslog
}
}

filter {
if [type] == “syslog” {
grok {
match => { “message” => “%{SYSLOGTIMESTAMP:syslog_timestamp} %{SYSLOGHOST:syslog_hostname} %{DATA:syslog_program}(?:\[%{POSINT:syslog_pid}\])?: %{GREEDYDATA:syslog_message}” }
add_field => [ “received_at”, “%{@timestamp}” ]
add_field => [ “received_from”, “%{host}” ]
}
date {
match => [ “syslog_timestamp”, “MMM d HH:mm:ss”, “MMM dd HH:mm:ss” ]
}
}
}

output {
elasticsearch {
hosts => [“localhost:9200”]
index => “syslog-%{+YYYY.MM.dd}”
}
}

# 重启Logstash
$ sudo systemctl restart logstash

# 配置rsyslog发送日志到Logstash
$ sudo vim /etc/rsyslog.conf

*.* @192.168.1.100:514

# 重启rsyslog
$ sudo systemctl restart rsyslog

# 访问Kibana
# 浏览器打开 http://localhost:5601
# 创建索引模式：syslog-*
# 查看日志数据

# 1. 通过Prometheus查看CPU使用率
# 访问Prometheus web界面，查询：
100 – (avg by(instance) (irate(node_cpu_seconds_total{mode=”idle”}[5m])) * 100

# 2. 通过Grafana查看详细CPU使用情况
# 打开服务器监控面板，查看CPU使用率图表

# 3. 登录服务器查看进程
$ top

top – 10:30:00 up 1 day, 2:30, 2 users, load average: 4.50, 3.80, 3.20
Tasks: 150 total, 1 running, 149 sleeping, 0 stopped, 0 zombie
%Cpu(s): 85.0 us, 10.0 sy, 0.0 ni, 5.0 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
KiB Mem : 8192000 total, 1024000 free, 5120000 used, 2048000 buff/cache
KiB Swap: 4096000 total, 3072000 free, 1024000 used. 1536000 avail Mem

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
12345 fgedu 20 0 2097152 1048576 16384 R 80.0 12.8 0:30.00 java

# 4. 查看进程详情
$ ps aux | grep java

fgedu 12345 80.0 12.8 2097152 1048576 ? R 10:29 0:30 java -jar application.jar

# 5. 查看应用日志
$ tail -f /var/log/application.log

2026-04-05 10:29:00 INFO Application started
2026-04-05 10:29:30 ERROR OutOfMemoryError: Java heap space
2026-04-05 10:30:00 ERROR GC overhead limit exceeded

# 6. 分析问题原因：Java应用内存不足，导致频繁GC，CPU使用率升高

# 7. 解决方案：增加Java堆内存
$ java -Xmx2g -Xms1g -jar application.jar

# 8. 验证解决方案
$ top

top – 10:35:00 up 1 day, 2:35, 2 users, load average: 1.20, 2.50, 3.00
Tasks: 150 total, 1 running, 149 sleeping, 0 stopped, 0 zombie
%Cpu(s): 10.0 us, 5.0 sy, 0.0 ni, 85.0 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
KiB Mem : 8192000 total, 512000 free, 5632000 used, 2048000 buff/cache
KiB Swap: 4096000 total, 3072000 free, 1024000 used. 1024000 avail Mem

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
12345 fgedu 20 0 2097152 1048576 16384 S 10.0 12.8 0:35.00 java