java面试题：服务器IO延时如何定位

1. 首先是top查看一下系统状况

发现两个参数异常，一是平均负载高，一是cpu %wa一直在50%以上。

查了一下%wa参数的意义：就是等待IO的时间

wa -- iowait
 Amount of time the CPU has been waiting for I/O to complete.

2. 查看磁盘使用情况

> PROCESS STATE CODES  
> D uninterruptible sleep (usually IO) 
>  R running or runnable (on run queue) 
>  S interruptible sleep (waiting for an event to complete)  
> T stopped, either by a job control signal or
> because it is being traced.  
> W paging (not valid since the 2.6.xx kernel)  
> X dead (should never be seen)  
> Z defunct ("zombie") process, terminated but not reaped by its parent.

3. 查看到进程中状态D（disk sleep）的进程

for x in `seq 1 1 10`; do ps -eo state,pid,cmd | grep "^D"; echo "----"; sleep 5; done

4. 查看进程相关状态信息

cat /proc/487/io

 rchar: 48752567
 wchar: 549961789
 syscr: 5967
 syscw: 67138
 read_bytes: 49020928
 write_bytes: 549961728
 cancelled_write_bytes: 0

查看都往哪写东西了

 lsof -p 487

就是查看引起进程该状态的原因