IO wait is 95 % , how to contorl

[senthil_kumar_1]

Hi

We are running Suse 9 linux on VM ware.

Suddenly we found that CPU has been utilized 100%.

Then i have issued the command "top", in output of TOP i have found that CPU idle is 0% and wa (IO wait) is almost 95%.

Example:

top - 11:59:44 up 19 days, 9:14, 4 users, load average: 1.00, 1.03, 1.01
Tasks: 113 total, 2 running, 111 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0% us, 2.3% sy, 0.0% ni, 0.0% id, 95.7% wa, 0.0% hi, 2.0% si
Mem: 1024912k total, 1016244k used, 8668k free, 48832k buffers
Swap: 2104472k total, 4k used, 2104468k free, 90648k cached

PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
16773 root 19 1 17436 9728 376 D 2.0 0.9 1:06.37 find
5001 root 15 0 67932 14m 11m S 0.3 1.4 0:18.23 kdesktop_lock
1 root 16 0 640 260 216 S 0.0 0.0 0:04.57 init
2 root 34 19 0 0 0 S 0.0 0.0 0:00.01 ksoftirqd/0
3 root 5 -10 0 0 0 S 0.0 0.0 0:01.38 events/0
4 root 7 -10 0 0 0 S 0.0 0.0 0:00.01 khelper



Then i have issued below command to find total CPU utilization of all process.

1101-dev01:~ # ps -eo user,pid,pcpu,comm | awk '{x += $3} END {print x}'
2.7



So how to solve the IO wait issue.

[Ivan Ferreira · Accepted solution]

You could try the iotop phyton program to detect which process is generating most I/O.

In case of a virtual machine, this could be also be a problem related to poor storage performance.

[senthil_kumar_1]

How to install "iotop python program"?

How to find if it is because of poor storage performance and how solve?

[Ivan Ferreira]

Check the requirements in the downloaded package. There should be a README or INSTALL file.

Check the output of the iostat -x 5 command, identify the storage service time (svctm).

What kind of storage are you using?

[Steven E. Protter]

Shalom,

rpm -qa | grep sysstat

This includes sar and other popular toys.

You probably need them to track down this problem. Install if not installed.

uname -a

SEP