[Gluster-users] glusterfsd/glusterfs process taking CPU load higher than usual

[ABHISHEK PALIWAL]

Please reply I am waiting for your response.
On Nov 30, 2016 2:21 PM, "ABHISHEK PALIWAL" <abhishpaliwal at gmail.com> wrote:

> could you please respond on this issue?
>
> On Tue, Nov 29, 2016 at 6:56 PM, ABHISHEK PALIWAL <abhishpaliwal at gmail.com
> > wrote:
>
>> Hi Team,
>>
>> I have two board setup and on which we have one volume with two brick on
>> each board.
>>
>> When I was checking the cpu load I found glusterfsd/glusterfs process
>> taking higher CPU load then usual like below:
>>
>> PID USER      PR  NI  VIRT  RES  SHR S %CPU %MEM    TIME+
>> COMMAND
>>  3117 root      20   0 1429m  48m 3636 R   98  0.2 212:12.35
>> fpipt_main_thre
>> 12299 root      20   0 1139m  52m 4192 R   73  0.2 120:41.69
>> glusterfsd
>>  4517 root      20   0 1139m  52m 4192 S   72  0.2 121:01.54
>> glusterfsd
>>  1915 root      20   0 1139m  52m 4192 R   62  0.2 121:16.22
>> glusterfsd
>> 14633 root      20   0 1139m  52m 4192 S   62  0.2 120:37.13
>> glusterfsd
>>  1992 root      20   0  634m 154m 4340 S   57  0.7  68:11.18
>> glusterfs
>> 17886 root      20   0 1139m  52m 4192 R   55  0.2 120:28.57
>> glusterfsd
>>  2664 root      20   0  783m  31m 4708 S   52  0.1 100:13.12
>> Scc_SctpHost_pr
>>  1914 root      20   0 1139m  52m 4192 S   50  0.2 121:20.19
>> glusterfsd
>> 12556 root      20   0 1139m  52m 4192 S   50  0.2 120:31.38
>> glusterfsd
>>  1583 root      20   0 1139m  52m 4192 R   48  0.2 121:16.83
>> glusterfsd
>> 12112 root      20   0 1139m  52m 4192 R   43  0.2 120:58.73
>> glusterfsd
>>
>> Is there any way to identify the way or to reduce this high load.
>>
>> I have also collected the volume profile logs but don't know how to
>> understand or analyze those logs.
>>
>> I am attaching those logs here.
>> --
>> Regards
>> Abhishek Paliwal
>>
>
>
>
> --
>
>
>
>
> Regards
> Abhishek Paliwal
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20161201/e064ff59/attachment.html>