云服务器解决io过高导致的命令卡顿

查看操作系统负载

[root@node-master1Ewao ~]# cat /proc/cpuinfo | grep "process"
processor	: 0
processor	: 1
processor	: 2
processor	: 3

[root@node-master1Ewao ~]# w
 15:42:05 up 72 days, 22:09,  1 user,  load average: 24.43, 20.18, 18.37
USER     TTY        LOGIN@   IDLE   JCPU   PCPU WHAT
root     pts/0     15:41    5.00s  0.03s  0.00s w

发现load average的值很高

[root@node-master1Ewao ~]# free -g
              total        used        free      shared  buff/cache   available
Mem:             15          10           0           1           4           3
Swap:             9           0           9

top命令查看

top - 15:46:48 up 72 days, 22:14,  1 user,  load average: 13.20, 16.25, 17.14
Tasks: 327 total,   1 running, 326 sleeping,   0 stopped,   0 zombie
%Cpu(s):  4.7 us,  5.4 sy,  0.0 ni,  9.3 id, 80.6 wa,  0.0 hi,  0.0 si,  0.0 st
KiB Mem : 16250032 total,   724568 free, 10980624 used,  4544840 buff/cache
KiB Swap: 10239996 total, 10180860 free,    59136 used.  3046656 avail Mem 

wa值比较高，说明I/O Wait比较高

iostat -x 2 5查看具体的io状态，发现iowait基本在90%

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           1.01    0.00    2.02   96.97    0.00    0.00

Device:         rrqm/s   wrqm/s     r/s     w/s    rkB/s    wkB/s avgrq-sz avgqu-sz   await r_await w_await  svctm  %util
vda               0.00     0.00    0.00   10.50     0.00   648.00   123.43   228.19 6493.48    0.00 6493.48  95.24 100.00
vdb               0.00   112.00    0.00    9.00     0.00   826.00   183.56    24.68 6654.28    0.00 6654.28 111.11 100.00

使用iotop或者ps查找导致高I/O的进程，**pidstat -d 1**命令

最终通过清理buff-cache解决问题:通过清理buff-cache解决问题

参考：io过高问题