linux 定位IO过高进程

操作系统IO过高，可以通过基础工具 top/iostat 查看

  1. 通过 top 的 %cpu 的wa（wait）指标

    1
    #top

  1. iostat 的%util 指标

    1
    #iostat -dx 1

如何定位具体哪个进程/服务造成io过高呢？

  1. 最简单的可以通过 iotop 定位， 通过IO百分比定位进程

  2. 通过判断进程是 D状态 定位

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

    ps 进程状态

    1
    2
    3
    4
    5
    6
    7
    8
    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.

定位哪个文件造成IO过高，可以通过 lsof 或者 pt-ioprofile 跟踪进程pid来继续定位