[Lustre-discuss] ost write operation fail with -5 error

[Dilip Sathaye]

Hi !

We have a lustre 2.3 setup on centos 6.3 . We are seeing error messages of
following type in the logs on client side.


Mar 16 04:51:38 node1 kernel: LustreError:
3227:0:(osc_request.c:1689:osc_brw_redo_request()) @@@ redo for recoverable
error -5  req at ffff8808087d7400 x1461623509830439/t0(0)
o4->lustre-OST0006-osc-ffff880828f4a800 at 192.168.1.45@o2ib:6/4 lens 488/416
e 0 to 0 dl 1394925742 ref 2 fl Interpret:R/0/0 rc -5/-5
Mar 16 04:51:38 node1 kernel: LustreError:
3227:0:(osc_request.c:1689:osc_brw_redo_request()) Skipped 7 previous
similar messages
Mar 16 04:51:46 node1 kernel: LustreError: 11-0: an error occurred while
communicating with 192.168.1.45 at o2ib. The ost_write operation failed with -5

The oss side logs have
Mar 16 13:07:55 oss1 kernel: Lustre: Skipped 1 previous similar message
Mar 16 13:07:55 oss1 kernel: Lustre: lustre-OST0000: haven't heard from
client fd08d07d-6476-6565-3ef5-7e6be1363eea (at 192.168.1.6 at o2ib) in 215
seconds. I think it's dead, and I am evicting it. exp ffff88090b46bc00, cur
1394955475 expire 1394955325 last 1394955260
Mar 16 13:07:55 oss1 kernel: Lustre: Skipped 1 previous similar message
Mar 16 13:44:29 oss1 lrmd: [2966]: info: rsc:ost0:11: monitor
Mar 17 12:47:19 oss1 kernel: LustreError:
2895:0:(quota_context.c:837:dqacq_interpret()) quota for user has been
enabled by master, but disabled by slave.
Mar 17 12:47:19 oss1 kernel: LustreError:
2895:0:(quota_context.c:699:dqacq_completion()) acquire qunit got error!
(rc:-3)
Mar 17 12:47:19 oss1 kernel: LustreError:
9837:0:(quota_interface.c:502:quota_chk_acq_common()) mismatched quota
configuration, stop try.

Any idea what this could be ?

Thanks and Regards
Dilip
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20140317/d29471fa/attachment.htm>