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/attachments/20100106/55e012b3/attachment.html
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/attachments/20100106/5eac5eba/attachment.html
On 2010-01-06, at 01:42, Tung Dam wrote:> 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 wait took 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: 0This warning has been removed in the 1.8 release of Lustre. In particular, with FLK (flock) type locks, they can be held indefinitely, so there is no reason to print a message at all. Cheers, Andreas -- Andreas Dilger Sr. Staff Engineer, Lustre Group Sun Microsystems of Canada, Inc.
On 2010-01-06, at 03:49, Tung Dam wrote:> The bad news is that i''m using lustre 1.8, do you have any idea ? > Could you tell me that how it could affect to our system or it''s > just a harmless warning ?It is just a harmless warning. The message is gone in CVS, err Git, but I don''t know when that was done, so it might not appear until 1.8.2.> On Wed, Jan 6, 2010 at 5:22 PM, Andreas Dilger <adilger at sun.com> > wrote: >> On 2010-01-06, at 01:42, Tung Dam wrote: >> 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 wait took 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 >> >> >> This warning has been removed in the 1.8 release of Lustre. In >> particular, with FLK (flock) type locks, they can be held >> indefinitely, so there is no reason to print a message at all. >>Cheers, Andreas -- Andreas Dilger Sr. Staff Engineer, Lustre Group Sun Microsystems of Canada, Inc.