# 1. 告警阈值配置
警告级别 CPU 内存 磁盘 处理时间
警告 80% 80% 80% 24小时内
严重 90% 90% 90% 4小时内
紧急 95% 95% 95% 立即处理

# 2. CPU告警脚本
# cat > /tmp/cpu_alert.sh << 'EOF' #!/bin/bash WARNING_THRESHOLD=80 CRITICAL_THRESHOLD=90 EMERGENCY_THRESHOLD=95 cpu_usage=$(top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1) if [ $(echo "$cpu_usage >= $EMERGENCY_THRESHOLD” | bc) -eq 1 ]; then
echo “EMERGENCY: CPU usage is ${cpu_usage}%”
# 发送紧急告警
elif [ $(echo “$cpu_usage >= $CRITICAL_THRESHOLD” | bc) -eq 1 ]; then
echo “CRITICAL: CPU usage is ${cpu_usage}%”
# 发送严重告警
elif [ $(echo “$cpu_usage >= $WARNING_THRESHOLD” | bc) -eq 1 ]; then
echo “WARNING: CPU usage is ${cpu_usage}%”
# 发送警告告警
fi
EOF

# 3. 内存告警脚本
# cat > /tmp/memory_alert.sh << 'EOF' #!/bin/bash WARNING_THRESHOLD=80 CRITICAL_THRESHOLD=90 EMERGENCY_THRESHOLD=95 mem_total=$(free | grep Mem | awk '{print $2}') mem_used=$(free | grep Mem | awk '{print $3}') mem_percent=$((mem_used * 100 / mem_total)) if [ $mem_percent -ge $EMERGENCY_THRESHOLD ]; then echo "EMERGENCY: Memory usage is ${mem_percent}%" # 发送紧急告警 elif [ $mem_percent -ge $CRITICAL_THRESHOLD ]; then echo "CRITICAL: Memory usage is ${mem_percent}%" # 发送严重告警 elif [ $mem_percent -ge $WARNING_THRESHOLD ]; then echo "WARNING: Memory usage is ${mem_percent}%" # 发送警告告警 fi EOF # 4. 定时任务配置 # crontab -e */30 * * * * /tmp/cpu_alert.sh */30 * * * * /tmp/memory_alert.sh # 5. 告警通知配置 # 邮件通知 # 钉钉通知 # 企业微信通知 # 短信通知 # 6. 告警历史记录 # 记录告警时间、指标值、处理结果

# 1. 创建监控审计脚本
# cat > /tmp/monitoring_audit.sh << 'EOF' #!/bin/bash REPORT="/tmp/monitoring_audit_report.txt" echo "========================================" > $REPORT
echo “Monitoring Audit Report – $(date)” >> $REPORT
echo “========================================” >> $REPORT
echo “” >> $REPORT

# 1. CPU使用情况
echo “1. CPU Usage” >> $REPORT
echo “———–” >> $REPORT
top -bn1 | grep “Cpu(s)” >> $REPORT
echo “” >> $REPORT

# 2. 内存使用情况
echo “2. Memory Usage” >> $REPORT
echo “————–” >> $REPORT
free -h >> $REPORT
echo “” >> $REPORT

# 3. 磁盘使用情况
echo “3. Disk Usage” >> $REPORT
echo “————” >> $REPORT
df -h >> $REPORT
echo “” >> $REPORT

# 4. 磁盘IO情况
echo “4. Disk I/O” >> $REPORT
echo “———–” >> $REPORT
iostat -x 1 3 >> $REPORT
echo “” >> $REPORT

# 5. 网络IO情况
echo “5. Network I/O” >> $REPORT
echo “————–” >> $REPORT
sar -n DEV 1 3 >> $REPORT
echo “” >> $REPORT

# 6. 进程状态
echo “6. Top Processes” >> $REPORT
echo “—————” >> $REPORT
ps aux –sort=-%cpu | head -n 10 >> $REPORT
echo “” >> $REPORT

# 7. 系统负载
echo “7. System Load” >> $REPORT
echo “————–” >> $REPORT
uptime >> $REPORT
echo “” >> $REPORT

echo “Audit completed. Report saved to $REPORT”
EOF

# 2. 执行审计脚本
# chmod +x /tmp/monitoring_audit.sh
# /tmp/monitoring_audit.sh
Audit completed. Report saved to /tmp/monitoring_audit_report.txt

# 3. 查看审计报告
# cat /tmp/monitoring_audit_report.txt

# 1. 启动top命令
# top
top – 10:00:00 up 1:23, 2 users, load average: 0.50, 0.60, 0.70
Tasks: 123 total, 1 running, 122 sleeping, 0 stopped, 0 zombie
%Cpu(s): 5.0 us, 2.0 sy, 0.0 ni, 92.0 id, 0.0 wa, 0.0 hi, 0.0 si, 1.0 st
MiB Mem: 1822.0 total, 446.0 free, 1200.0 used, 176.0 buff/cache
MiB Swap: 2047.0 total, 2047.0 free, 0.0 used. 1600.0 avail Mem

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
1234 root 20 0 123456 98765 12345 S 5.0 5.2 0:05.00 /usr/bin/python3 /usr/bin/app
5678 root 20 0 56789 54321 5678 S 2.0 3.1 0:01.00 /usr/sbin/nginx
9012 root 20 0 45678 43210 4321 S 1.0 2.5 0:00.30 /usr/sbin/mysqld

# 2. 以批处理模式运行
# top -bn1
top – 10:00:00 up 1:23, 2 users, load average: 0.50, 0.60, 0.70
Tasks: 123 total, 1 running, 122 sleeping, 0 stopped, 0 zombie
%Cpu(s): 5.0 us, 2.0 sy, 0.0 ni, 92.0 id, 0.0 wa, 0.0 hi, 0.0 si, 1.0 st
MiB Mem: 1822.0 total, 446.0 free, 1200.0 used, 176.0 buff/cache
MiB Swap: 2047.0 total, 2047.0 free, 0.0 used. 1600.0 avail Mem

# 3. 指定刷新间隔
# top -d 2
（每2秒刷新一次）

# 4. 指定刷新次数
# top -n 5
（刷新5次后退出）

# 5. 查看指定用户进程
# top -u fgedu
（只显示fgedu用户的进程）

# 6. 查看指定PID
# top -p 1234
（只显示PID为1234的进程）

# 7. 查看指定PID列表
# top -p 1234,5678,9012
（只显示指定PID的进程）

# 8. 显示完整命令行
# top -c
（显示完整的命令行）

# 9. 显示线程信息
# top -H
（显示线程信息）

# 10. 显示CPU信息
# top -1
（显示所有CPU信息）

# 11. 显示内存单位为KB
# top -k
（内存单位为KB）

# 12. 显示内存单位为MB
# top -m
（内存单位为MB）

# 13. 显示内存单位为GB
# top -g
（内存单位为GB）

# 14. 显示指定字段
# top -o %CPU,%MEM,TIME+,COMMAND
（只显示指定字段）

# 15. 保存配置文件
# top -b -n 1 > /tmp/top_output.txt
（将输出保存到文件）

# 1. 启动htop命令
# htop
（显示图形化界面）

# 2. 指定刷新间隔
# htop -d 2
（每2秒刷新一次）

# 3. 查看指定用户进程
# htop -u fgedu
（只显示fgedu用户的进程）

# 4. 查看指定PID
# htop -p 1234
（只显示PID为1234的进程）

# 5. 查看指定PID列表
# htop -p 1234,5678,9012
（只显示指定PID的进程）

# 6. 显示线程信息
# htop -H
（显示线程信息）

# 7. 显示CPU信息
# htop -1
（显示所有CPU信息）

# 8. 显示指定CPU
# htop -1 -p 0
（只显示CPU 0）

# 9. 显示指定CPU列表
# htop -1 -p 0,1,2,3
（只显示指定CPU）

# 10. 显示指定字段
# htop -o PID,USER,%,CPU,%,MEM,TIME,COMMAND
（只显示指定字段）

# 11. 保存配置文件
# htop -s /tmp/htop_config
（使用指定配置文件）

# 12. 不显示颜色
# htop –no-color
（不显示彩色输出）

# 13. 显示帮助信息
# htop –help
（显示帮助信息）

# 14. 显示版本信息
# htop –version
（显示版本信息）

# 15. htop交互式操作
# F1: 显示帮助
# F2: 配置界面
# F3: 搜索进程
# F4: 过滤进程
# F5: 树形显示
# F6: 排序
# F7: 降低优先级
# F8: 提高优先级
# F9: 杀死进程
# F10: 退出
# q: 退出
# k: 杀死进程
# /: 搜索进程

# 1. 查找CPU使用最多的进程
# ps aux –sort=-%cpu | head -n 10
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1234 50.0 5.2 123456 98765 ? R 10:00 5:00 /usr/bin/python3 /usr/bin/app
root 5678 2.0 3.1 56789 54321 ? S 10:00 0:01 /usr/sbin/nginx

# 2. 查找内存使用最多的进程
# ps aux –sort=-%mem | head -n 10
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1234 5.0 85.2 1234567 1567890 ? S 10:00 0:05 /usr/bin/python3 /usr/bin/app
root 5678 2.0 3.1 56789 54321 ? S 10:00 0:01 /usr/sbin/nginx

# 3. 查找僵尸进程
# ps aux | grep defunct
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 9999 0.0 0.0 0 0 ? Z 10:00 0:00 [defunct]

# 4. 查找长时间运行的进程
# ps aux | awk ‘$10 > 3600 {print}’
（运行时间超过1小时的进程）

# 5. 监控系统负载
# cat > /tmp/load_monitor.sh << 'EOF' #!/bin/bash while true; do load=$(uptime | awk -F'load average:' '{print $2}' | awk '{print $1}') echo "$(date): Load average: $load" sleep 60 done EOF # 6. 监控CPU使用率 # cat > /tmp/cpu_monitor.sh << 'EOF' #!/bin/bash while true; do cpu_usage=$(top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1) echo "$(date): CPU usage: ${cpu_usage}%" sleep 60 done EOF # 7. 监控内存使用率 # cat > /tmp/memory_monitor.sh << 'EOF' #!/bin/bash while true; do mem_total=$(free | grep Mem | awk '{print $2}') mem_used=$(free | grep Mem | awk '{print $3}') mem_percent=$((mem_used * 100 / mem_total)) echo "$(date): Memory usage: ${mem_percent}%" sleep 60 done EOF # 8. 监控磁盘IO # iostat -x 1 5 Linux 4.18.0-477.el8.x86_64 (localhost) 04/02/2026 _x86_64_ (2 CPU) avg-cpu: %user %nice %system %iowait %steal %idle 0.50 0.00 0.50 0.00 0.00 99.00 Device r/s w/s rkB/s wkB/s rrqm/s wrqm/s %rrqm %wrqm r_await w_await aqu-sz rareq-sz wareq-sz svctm %util sda 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 dm-0 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 # 9. 监控网络IO # sar -n DEV 1 5 Linux 4.18.0-477.el8.x86_64 (localhost) 04/02/2026 _x86_64_ (2 CPU) 10:00:01 IFACE rxpck/s txpck/s rxkB/s txkB/s rxcmp/s txcmp/s rxmcst/s txmcst/s 10:00:02 eth0 123.45 67.89 12.34 6.78 0.00 0.00 0.00 0.00 10:00:02 eth1 45.67 23.45 4.56 2.34 0.00 0.00 0.00 0.00 # 10. 监控进程状态 # cat > /tmp/process_monitor.sh << 'EOF' #!/bin/bash while true; do echo "$(date): Process status" ps aux --sort=-%cpu | head -n 5 echo "" ps aux --sort=-%mem | head -n 5 echo "----------------------------------------" sleep 60 done EOF # 11. 监控系统资源 # cat > /tmp/system_monitor.sh << 'EOF' #!/bin/bash while true; do echo "========================================" echo "System Monitor - $(date)" echo "========================================" # CPU使用率 cpu_usage=$(top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1) echo "CPU usage: ${cpu_usage}%" # 内存使用率 mem_total=$(free | grep Mem | awk '{print $2}') mem_used=$(free | grep Mem | awk '{print $3}') mem_percent=$((mem_used * 100 / mem_total)) echo "Memory usage: ${mem_percent}%" # 磁盘使用率 disk_usage=$(df -h / | tail -n 1 | awk '{print $5}' | cut -d'%' -f1) echo "Disk usage: ${disk_usage}%" # 系统负载 load=$(uptime | awk -F'load average:' '{print $2}' | awk '{print $1}') echo "Load average: $load" echo "========================================" echo "" sleep 60 done EOF # 12. 监控进程资源使用 # cat > /tmp/process_resource_monitor.sh << 'EOF' #!/bin/bash PID=$1 if [ -z "$PID" ]; then echo "Usage: $0 ”
exit 1
fi

while true; do
if [ -d “/proc/$PID” ]; then
echo “$(date): Process $PID”
ps -p $PID -o pid,ppid,%cpu,%mem,vsz,rss,stat,etime,cmd
echo “”
else
echo “Process $PID not found”
break
fi

sleep 10
done
EOF

# 13. 监控系统日志
# cat > /tmp/log_monitor.sh << 'EOF' #!/bin/bash tail -f /var/log/messages | while read line; do echo "$(date): $line" done EOF # 14. 监控应用日志 # cat > /tmp/app_log_monitor.sh << 'EOF' #!/bin/bash tail -f /var/log/app/app.log | grep --line-buffered -E "ERROR|WARN" | while read line; do echo "$(date): $line" # 发送告警 done EOF # 15. 综合监控脚本 # cat > /tmp/comprehensive_monitor.sh << 'EOF' #!/bin/bash while true; do # CPU监控 cpu_usage=$(top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1) if [ $(echo "$cpu_usage > 80″ | bc) -eq 1 ]; then
echo “WARNING: CPU usage is ${cpu_usage}%”
fi

# 内存监控
mem_total=$(free | grep Mem | awk ‘{print $2}’)
mem_used=$(free | grep Mem | awk ‘{print $3}’)
mem_percent=$((mem_used * 100 / mem_total))
if [ $mem_percent -gt 80 ]; then
echo “WARNING: Memory usage is ${mem_percent}%”
fi

# 磁盘监控
disk_usage=$(df -h / | tail -n 1 | awk ‘{print $5}’ | cut -d’%’ -f1)
if [ $disk_usage -gt 80 ]; then
echo “WARNING: Disk usage is ${disk_usage}%”
fi

# 系统负载监控
load=$(uptime | awk -F’load average:’ ‘{print $2}’ | awk ‘{print $1}’)
if [ $(echo “$load > 2.0” | bc) -eq 1 ]; then
echo “WARNING: Load average is $load”
fi

sleep 60
done
EOF

# 1. Web服务器监控
# cat > /tmp/web_monitor.sh << 'EOF' #!/bin/bash echo "Web Server Monitor - $(date)" # CPU监控 echo "CPU Usage:" top -bn1 | grep "Cpu(s)" # 内存监控 echo "" echo "Memory Usage:" free -h # 磁盘监控 echo "" echo "Disk Usage:" df -h | grep -E '/$|/var|/data' # 进程监控 echo "" echo "Web Processes:" ps aux | grep -E "nginx|apache|httpd" | grep -v grep # 网络监控 echo "" echo "Network Connections:" netstat -an | grep -E ":80|:443" | wc -l EOF # 2. 数据库服务器监控 # cat > /tmp/db_monitor.sh << 'EOF' #!/bin/bash echo "Database Server Monitor - $(date)" # CPU监控 echo "CPU Usage:" top -bn1 | grep "Cpu(s)" # 内存监控 echo "" echo "Memory Usage:" free -h # 磁盘监控 echo "" echo "Disk Usage:" df -h | grep -E '/$|/data|/var' # 进程监控 echo "" echo "Database Processes:" ps aux | grep -E "mysql|postgres|redis" | grep -v grep # 连接数监控 echo "" echo "Database Connections:" netstat -an | grep -E ":3306|:5432|:6379" | wc -l EOF # 3. 应用服务器监控 # cat > /tmp/app_monitor.sh << 'EOF' #!/bin/bash echo "Application Server Monitor - $(date)" # CPU监控 echo "CPU Usage:" top -bn1 | grep "Cpu(s)" # 内存监控 echo "" echo "Memory Usage:" free -h # 磁盘监控 echo "" echo "Disk Usage:" df -h | grep -E '/$|/opt|/data|/var' # 进程监控 echo "" echo "Application Processes:" ps aux | grep -E "java|python|node" | grep -v grep # 日志监控 echo "" echo "Recent Application Errors:" tail -n 20 /var/log/app/app.log | grep -i error EOF # 4. 容器服务器监控 # cat > /tmp/container_monitor.sh << 'EOF' #!/bin/bash echo "Container Server Monitor - $(date)" # CPU监控 echo "CPU Usage:" top -bn1 | grep "Cpu(s)" # 内存监控 echo "" echo "Memory Usage:" free -h # 磁盘监控 echo "" echo "Disk Usage:" df -h | grep -E '/$|/var' # 容器监控 echo "" echo "Container Status:" docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Ports}}" # 容器资源监控 echo "" echo "Container Resources:" docker stats --no-stream --format "table {{.Name}}\t{{.CPUPerc}}\t{{.MemUsage}}\t{{.MemPerc}}" EOF # 5. 综合监控 # cat > /tmp/comprehensive_monitor.sh << 'EOF' #!/bin/bash echo "Comprehensive System Monitor - $(date)" # 1. 系统信息 echo "1. System Information:" echo "-------------------" uname -a uptime echo "" # 2. CPU监控 echo "2. CPU Usage:" echo "-------------" top -bn1 | grep "Cpu(s)" echo "" # 3. 内存监控 echo "3. Memory Usage:" echo "----------------" free -h echo "" # 4. 磁盘监控 echo "4. Disk Usage:" echo "-------------" df -h echo "" # 5. 磁盘IO监控 echo "5. Disk I/O:" echo "------------" iostat -x 1 3 echo "" # 6. 网络IO监控 echo "6. Network I/O:" echo "---------------" sar -n DEV 1 3 echo "" # 7. 进程监控 echo "7. Top Processes:" echo "----------------" ps aux --sort=-%cpu | head -n 10 echo "" # 8. 系统负载 echo "8. System Load:" echo "---------------" uptime EOF

# 案例1：CPU使用率过高
# 症状：系统响应缓慢，CPU使用率超过90%

# 排查步骤：
# 1. 检查CPU使用情况
# top -bn1
%Cpu(s): 95.0 us, 2.0 sy, 0.0 ni, 2.0 id, 0.0 wa, 0.0 hi, 0.0 si, 1.0 st

# 2. 检查CPU使用最多的进程
# ps aux –sort=-%cpu | head -n 10
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1234 90.0 5.2 123456 98765 ? R 10:00 5:00 /usr/bin/app

# 3. 检查进程线程
# ps -Lp 1234 -o pid,tid,psr,%cpu,%mem,cmd
PID TID PSR %CPU %MEM CMD
1234 1234 0 90.0 5.2 /usr/bin/app
1234 1235 1 5.0 0.1 /usr/bin/app

# 解决：优化应用或增加CPU资源

# 案例2：内存使用率过高
# 症状：系统响应缓慢，内存使用率超过90%

# 排查步骤：
# 1. 检查内存使用情况
# free -h
total used free shared buff/cache available
Mem: 1.8G 1.7G 100M 12M 50M 100M

# 2. 检查内存使用最多的进程
# ps aux –sort=-%mem | head -n 10
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1234 5.0 85.2 1234567 1567890 ? S 10:00 0:05 /usr/bin/app

# 3. 检查交换使用情况
# free -h | grep Swap
Swap: 2.0G 1.5G 500M

# 解决：优化应用或增加内存

# 案例3：磁盘IO过高
# 症状：系统响应缓慢，磁盘IO使用率高

# 排查步骤：
# 1. 检查磁盘IO
# iostat -x 1 5
Device r/s w/s rkB/s wkB/s rrqm/s wrqm/s %rrqm %wrqm r_await w_await aqu-sz rareq-sz wareq-sz svctm %util
sda 1000.00 500.00 8000.00 4000.00 0.00 0.00 0.00 0.00 50.00 50.00 75.00 8.00 8.00 0.67 100.00

# 2. 检查磁盘使用最多的进程
# iotop -o -b -n 1
Total DISK READ: 10.00 M/s | Total DISK WRITE: 5.00 M/s
PID PRIO USER DISK READ DISK WRITE SWAPIN IO> COMMAND
1234 be/4 root 8.00 M/s 4.00 M/s 0.00 % 10.00 % /usr/bin/app

# 3. 检查磁盘使用情况
# df -h
Filesystem Size Used Avail Use% Mounted on
/dev/mapper/rhel-root 50G 45G 5G 90% /

# 解决：优化磁盘IO或升级硬件

# 案例4：系统负载过高
# 症状：系统响应缓慢，系统负载超过2.0

# 排查步骤：
# 1. 检查系统负载
# uptime
10:00:00 up 1:23, 2 users, load average: 3.50, 3.60, 3.70

# 2. 检查运行队列
# vmstat 1 5
procs ———–memory———- —swap– —–io—- -system– ——cpu—–
r b swpd free buff cache si so bi bo in cs us sy id wa st
3 0 0 123456 12345 456789 0 0 100 50 100 200 10 5 80 5 0

# 3. 检查CPU使用情况
# top -bn1 | grep “Cpu(s)”
%Cpu(s): 10.0 us, 5.0 sy, 0.0 ni, 80.0 id, 5.0 wa, 0.0 hi, 0.0 si, 0.0 st

# 解决：优化应用或增加CPU资源

# 案例5：网络连接过多
# 症状：系统响应缓慢，网络连接数过多

# 排查步骤：
# 1. 检查网络连接数
# netstat -an | wc -l
10000

# 2. 检查各端口连接数
# netstat -an | grep -E “:80|:443” | wc -l
8000

# 3. 检查连接状态
# netstat -an | awk ‘{print $6}’ | sort | uniq -c | sort -nr
5000 ESTABLISHED
3000 TIME_WAIT
2000 CLOSE_WAIT

# 解决：优化应用或调整系统参数

# 案例6：进程僵尸
# 症状：系统中存在僵尸进程

# 排查步骤：
# 1. 检查僵尸进程
# ps aux | grep defunct
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 9999 0.0 0.0 0 0 ? Z 10:00 0:00 [defunct]

# 2. 检查僵尸进程的父进程
# ps -ef | grep 9999
root 9998 0.0 0.0 12345 5678 ? S 10:00 0:00 /usr/bin/app

# 3. 检查父进程状态
# ps -p 9998 -o pid,stat,cmd
PID STAT CMD
9998 S /usr/bin/app

# 解决：重启父进程或杀死父进程

# 案例7：进程卡死
# 症状：进程无响应

# 排查步骤：
# 1. 检查进程状态
# ps -p 1234 -o pid,stat,wchan,cmd
PID STAT WCHAN CMD
1234 D wait_for_disk /usr/bin/app

# 2. 检查进程堆栈
# cat /proc/1234/wchan
wait_for_disk

# 3. 检查进程文件描述符
# ls -l /proc/1234/fd/
total 0
lrwx——. 1 root root 64 Apr 2 10:00 0 -> /dev/null
lrwx——. 1 root root 64 Apr 2 10:00 1 -> socket:[12345]

# 解决：重启进程或修复磁盘问题

# 案例8：内存泄漏
# 症状：进程内存使用持续增长

# 排查步骤：
# 1. 监控进程内存使用
# watch -n 1 “ps -p 1234 -o pid,%mem,vsz,rss”

# 2. 检查进程内存详情
# cat /proc/1234/status | grep -E “VmSize|VmRSS|VmPeak|VmHWM”
VmSize: 1234567 kB
VmRSS: 1567890 kB
VmPeak: 2000000 kB
VmHWM: 1600000 kB

# 3. 使用内存分析工具
# valgrind –leak-check=full /usr/bin/app

# 解决：修复应用内存泄漏

# 案例9：CPU负载不均衡
# 症状：某些CPU使用率高，其他CPU空闲

# 排查步骤：
# 1. 检查各CPU使用情况
# top -1
%Cpu0 : 90.0 us, 5.0 sy, 0.0 ni, 5.0 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
%Cpu1 : 10.0 us, 5.0 sy, 0.0 ni, 85.0 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st

# 2. 检查进程CPU绑定
# taskset -pc 1234
pid 1234’s current affinity list: 0

# 3. 检查NUMA配置
# numactl –hardware
available: 2 nodes (0-1)
node 0 cpus: 0 1 2 3 4 5 6 7
node 0 size: 1024 MB
node 0 free: 512 MB
node 1 cpus: 8 9 10 11 12 13 14 15
node 1 size: 1024 MB
node 1 free: 1000 MB

# 解决：调整进程CPU绑定或优化应用

# 案例10：系统响应缓慢
# 症状：系统整体响应缓慢

# 排查步骤：
# 1. 检查系统负载
# uptime
10:00:00 up 1:23, 2 users, load average: 3.50, 3.60, 3.70

# 2. 检查CPU使用情况
# top -bn1 | grep “Cpu(s)”
%Cpu(s): 10.0 us, 5.0 sy, 0.0 ni, 80.0 id, 5.0 wa, 0.0 hi, 0.0 si, 0.0 st

# 3. 检查内存使用情况
# free -h
total used free shared buff/cache available
Mem: 1.8G 1.2G 100M 12M 50M 500M

# 4. 检查磁盘IO
# iostat -x 1 5
Device r/s w/s rkB/s wkB/s rrqm/s wrqm/s %rrqm %wrqm r_await w_await aqu-sz rareq-sz wareq-sz svctm %util
sda 100.00 50.00 800.00 400.00 0.00 0.00 0.00 0.00 50.00 50.00 75.00 8.00 8.00 0.67 100.00

# 解决：优化磁盘IO或升级硬件

# 1. 优化CPU调度
# cat > /tmp/optimize_cpu.sh << 'EOF' #!/bin/bash echo "Optimizing CPU scheduling..." # 检查当前调度器 echo "Current scheduler:" cat /sys/block/sda/queue/scheduler noop [deadline] cfq # 设置调度器为deadline echo deadline > /sys/block/sda/queue/scheduler

# 永久配置
if ! grep -q “echo deadline” /etc/rc.local; then
echo “echo deadline > /sys/block/sda/queue/scheduler” >> /etc/rc.local
fi

echo “CPU scheduling optimized”
EOF

# 2. 优化内存使用
# cat > /tmp/optimize_memory.sh << 'EOF' #!/bin/bash echo "Optimizing memory usage..." # 降低交换倾向 echo 10 > /proc/sys/vm/swappiness

# 提高缓存回收倾向
echo 50 > /proc/sys/vm/vfs_cache_pressure

# 降低脏页比例
echo 5 > /proc/sys/vm/dirty_ratio

# 永久配置
if ! grep -q “vm.swappiness” /etc/sysctl.conf; then
echo “vm.swappiness=10” >> /etc/sysctl.conf
echo “vm.vfs_cache_pressure=50” >> /etc/sysctl.conf
echo “vm.dirty_ratio=5” >> /etc/sysctl.conf
fi

# 应用配置
sysctl -p

echo “Memory usage optimized”
EOF

# 3. 优化磁盘IO
# cat > /tmp/optimize_disk.sh << 'EOF' #!/bin/bash echo "Optimizing disk I/O..." # 设置读取预取 echo 256 > /sys/block/sda/queue/read_ahead_kb

# 设置队列长度
echo 128 > /sys/block/sda/queue/nr_requests

# 永久配置
if ! grep -q “read_ahead_kb” /etc/rc.local; then
echo “echo 256 > /sys/block/sda/queue/read_ahead_kb” >> /etc/rc.local
echo “echo 128 > /sys/block/sda/queue/nr_requests” >> /etc/rc.local
fi

echo “Disk I/O optimized”
EOF

# 4. 优化网络性能
# cat > /tmp/optimize_network.sh << 'EOF' #!/bin/bash echo "Optimizing network performance..." # 增加TCP缓冲区 echo "net.core.rmem_max = 16777216" >> /etc/sysctl.conf
echo “net.core.wmem_max = 16777216” >> /etc/sysctl.conf
echo “net.ipv4.tcp_rmem = 4096 87380 16777216” >> /etc/sysctl.conf
echo “net.ipv4.tcp_wmem = 4096 65536 16777216” >> /etc/sysctl.conf

# 应用配置
sysctl -p

echo “Network performance optimized”
EOF

# 5. 优化进程优先级
# cat > /tmp/optimize_process.sh << 'EOF' #!/bin/bash echo "Optimizing process priority..." # 提高关键进程优先级 renice -10 1234 # 降低非关键进程优先级 renice +10 5678 echo "Process priority optimized" EOF # 6. 优化文件描述符 # cat > /tmp/optimize_fd.sh << 'EOF' #!/bin/bash echo "Optimizing file descriptors..." # 增加文件描述符限制 echo "* soft nofile 65536" >> /etc/security/limits.conf
echo “* hard nofile 65536” >> /etc/security/limits.conf

# 增加系统文件描述符
echo “fs.file-max = 1000000” >> /etc/sysctl.conf

# 应用配置
sysctl -p

echo “File descriptors optimized”
EOF

# 7. 完整性能优化
# cat > /tmp/full_performance_optimization.sh << 'EOF' #!/bin/bash echo "Starting full performance optimization..." # 1. 优化CPU调度 ./optimize_cpu.sh # 2. 优化内存使用 ./optimize_memory.sh # 3. 优化磁盘IO ./optimize_disk.sh # 4. 优化网络性能 ./optimize_network.sh # 5. 优化进程优先级 ./optimize_process.sh # 6. 优化文件描述符 ./optimize_fd.sh echo "Full performance optimization completed" EOF # chmod +x /tmp/full_performance_optimization.sh # /tmp/full_performance_optimization.sh