smonk@sandia.gov
2006-Dec-18  15:45 UTC
[Lustre-devel] [Bug 11416] received cancel for unknown lock cookie
Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
https://bugzilla.lustre.org/show_bug.cgi?id=11416
           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|ASSIGNED                    |NEW
Below are some more sample messages..I''ll keep digging, but I do not
see the
"### lock callback timer expired".  The nodes mount 2 lustre file
systems one of
which had issues last week (errors are not coming from the problem fs). 
I''m
considering stopping/starting lustre (umount,lconf -d and mount) to see what
happens.
server:
Dec 18 15:22:59 ca894 kernel: LustreError:
7428:0:(ldlm_lockd.c:1043:ldlm_handle_cancel()) received cancel for unknown lock
cookie 0xe39bddcbdac8c2db from client c05a5639-d38f-0400-cfbf-834a787a5e1e id
12345-0xdd7f73db@gm
Dec 18 15:22:59 ca894 kernel: LustreError:
7428:0:(ldlm_lockd.c:1043:ldlm_handle_cancel()) Skipped 9 previous similar
messages
Dec 18 15:25:49 ca894 kernel: LustreError:
7446:0:(ldlm_lockd.c:1043:ldlm_handle_cancel()) received cancel for unknown lock
cookie 0xe39bddcbdac8c22c from client c05a5639-d38f-0400-cfbf-834a787a5e1e id
12345-0xdd7f73db@gm
Dec 18 15:25:49 ca894 kernel: LustreError:
7446:0:(ldlm_lockd.c:1043:ldlm_handle_cancel()) Skipped 1 previous similar
message
client:
Dec 18 15:22:59 eu352 kernel: LustreError:
24052:0:(file.c:747:ll_extent_lock_callback()) Skipped 3 previous similar
messages
Dec 18 15:23:05 eu352 kernel: LustreError:
24071:0:(ldlm_request.c:746:ldlm_cli_cancel()) client/server (nid
10.196.132.84@o2ib) out of sync -- not fatal, flags 1056912
Dec 18 15:23:05 eu352 kernel: LustreError:
24071:0:(ldlm_request.c:746:ldlm_cli_cancel()) Skipped 3 previous similar
messages
Dec 18 15:23:05 eu352 kernel: LustreError:
24071:0:(file.c:747:ll_extent_lock_callback()) ldlm_cli_cancel failed: 116
Dec 18 15:23:05 eu352 kernel: LustreError:
24071:0:(file.c:747:ll_extent_lock_callback()) Skipped 3 previous similar
messages
Dec 18 15:23:12 eu352 kernel: LustreError:
24069:0:(ldlm_request.c:746:ldlm_cli_cancel()) client/server (nid
10.196.132.85@o2ib) out of sync -- not fatal, flags 1056912