[Lustre-discuss] Enqueue wait from MDS log

[Tung Dam]

On Wed, Jan 6, 2010 at 3:35 PM, Tung Dam <lexluthor87 at gmail.com> wrote:

> Hi list
>
> I have an issue with lustre log from our MDS, like this:
> *
> Jan  6 14:00:49 MDS1 kernel: Lustre:
> 19141:0:(ldlm_lockd.c:808:ldlm_server_completion_ast()) ### enqueue waittook 164s from 1262761084 ns: mds-lustre-MDT0000_UUID lock:
> ffff8101b6265a00/0x874ddc3670da987c lrc: 3/0,0 mode: PW/PW res:
> 28739811/1154690434 rrc: 3 type: FLK pid: 2393 [0->9223372036854775807]
> flags: 0x0 remote: 0x49437cb8a7f893b2 expref: 7527 pid: 19134 timeout: 0
> Jan  6 14:03:17 MDS1 kernel: Lustre:
> 19151:0:(ldlm_lockd.c:808:ldlm_server_completion_ast()) ### enqueue waittook 165s from 1262761232 ns: mds-lustre-MDT0000_UUID lock:
> ffff81000ce85000/0x874ddc3670df7804 lrc: 3/0,0 mode: PW/PW res:
> 28764612/1154727429 rrc: 3 type: FLK pid: 5802 [0->9223372036854775807]
> flags: 0x0 remote: 0x49437cb8a7fc23d4 expref: 7618 pid: 19141 timeout: 0
> Jan  6 14:56:09 MDS1 kernel: Lustre:
> 19146:0:(ldlm_lockd.c:808:ldlm_server_completion_ast()) ### enqueue waittook 2292s from 1262762277 ns: mds-lustre-MDT0000_UUID lock:
> ffff81001353c400/0x874ddc367109bb09 lrc: 3/0,0 mode: PW/PW res:
> 50663149/1154741605 rrc: 8 type: FLK pid: 14506 [0->9223372036854775807]
> flags: 0x0 remote: 0x49437cb8a815133a expref: 13601 pid: 19127 timeout: 0
> Jan  6 14:56:09 MDS1 kernel: Lustre:
> 19125:0:(ldlm_lockd.c:808:ldlm_server_completion_ast()) ### enqueue waittook 2267s from 1262762302 ns: mds-lustre-MDT0000_UUID lock:
> ffff81000a217200/0x874ddc36710b5802 lrc: 3/0,0 mode: PW/PW res:
> 50663149/1154741605 rrc: 3 type: FLK pid: 4363 [0->9223372036854775807]
> flags: 0x0 remote: 0x49437cb8a815f26f expref: 13594 pid: 19129 timeout: 0
> Jan  6 14:56:09 MDS1 kernel: Lustre:
> 19125:0:(ldlm_lockd.c:808:ldlm_server_completion_ast()) Skipped 4 previous
> similar messages*
>
> I repeated many times in many days. Maybe it's not really a problem because
> our system is working ( just there's nothing goes down, but it seems like a
> reduction in speed somewhere  ) and so, could anyone tell me what's the
> meaning of these log messeages and how i could affect to our whole lustre
> file system ?
>
> Any help would be highly appreciated :)
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20100106/5eac5eba/attachment.htm>