Lustre devel - Jan 2007 - [Bug 11546] LBUG POISONED open 0000010163af1a00!

Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
https://bugzilla.lustre.org/show_bug.cgi?id=11546



Created an attachment (id=9335)
Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
 --> (https://bugzilla.lustre.org/attachment.cgi?id=9335&action=view)
Console log

Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
https://bugzilla.lustre.org/show_bug.cgi?id=11546



Lustre: lustre-1.4.7.2-pre-12llnl
Kernel: 56chaos

Observed on 5 peleton nodes last night.


2007-01-13 00:14:20 LustreError: 6829:0:(client.c:576:ptlrpc_check_status()) @@@
type == PTL_RPC_MSG_ERR, err == -107 req@0000010163aeb000 x63351/t0
o101->mds_p_lscratchb_UUID@pigs-mds1_UUID:12 lens 512/2960 ref 1 fl
Rpc:RP/0/0
rc 0/-107
2007-01-13 00:14:20 LustreError:
MDC_pigs-mds1_mds_p_lscratchb_MNT_lscratchb_client-00000103053cb800: Connection
to service mds_p_lscratchb via nid 172.16.60.200@tcp was lost; in progress
operations using this service will wait for recovery to complete.
2007-01-13 00:15:16 LustreError: This client was evicted by mds_p_lscratchb; in
progress operations using this service will fail.
2007-01-13 00:15:16 LustreError: Skipped 33 previous similar messages
2007-01-13 00:15:16 LustreError:
6841:0:(ldlm_resource.c:365:ldlm_namespace_cleanup()) Namespace
MDC_pigs-mds1_mds_p_lscratchb_MNT_lscratchb_client-00000103053cb800 resource
refcount 1 after lock cleanup; forcing cleanup.
2007-01-13 00:15:16 Lustre:
MDC_pigs-mds1_mds_p_lscratchb_MNT_lscratchb_client-00000103053cb800: Connection
restored to service mds_p_lscratchb using nid 172.16.60.200@tcp.
2007-01-13 00:15:16 LustreError: 6829:0:(mdc_locks.c:417:mdc_enqueue())
ldlm_cli_enqueue: -5
2007-01-13 00:15:18 LustreError: 6827:0:(mdc_request.c:649:mdc_close()) LBUG
POISONED open 0000010163af1a00!
2007-01-13 00:15:18 general protection fault: 0000 [1] SMP
2007-01-13 00:15:18 CPU 5
2007-01-13 00:15:18 Modules linked in: osc(U) llite(U) lov(U) lquota(U) mdc(U)
ko2iblnd(U) ptlrpc(U) lnet(U) obdclass(U) lvfs(U) libcfs(U) sg(U) perfctr(U)
netdump(U) job(U) i2c_dev(U) i2c_core(U) ib_ipoib(U) rdma_ucm(U) rdma_cm(U)
ib_addr(U) ib_mthca(U) ib_umad(U) ib_ucm(U) ib_uverbs(U) ib_cm(U) ib_sa(U)
ib_mad(U) ib_core(U) dm_mod(U) sd_mod(U) usb_storage(U) joydev(U) rtc(U) md(U)
ohci_hcd(U) k8_edac(U) edac_mc(U) floppy(U) sata_nv(U) libata(U) scsi_mod(U)
unionfs(U) nfs(U) lockd(U) sunrpc(U) e1000(U)
2007-01-13 00:15:18 Pid: 6827, comm: umt2k_DD Tainted: GF     2.6.9-56chaos
2007-01-13 00:15:18 RIP: 0010:[<ffffffffa03e0f0a>]
<ffffffffa03e0f0a>{:mdc:mdc_close+2563}
2007-01-13 00:15:18 RSP: 0018:00000100bc3adb68  EFLAGS: 00010206
2007-01-13 00:15:18 RAX: 5a5a5a5a5a5a5a5a RBX: 0000010163af1a00 RCX:
0000010000019000
2007-01-13 00:15:18 RDX: 0000000000000201 RSI: 000000000000005a RDI:
000001005c090000
2007-01-13 00:15:18 RBP: 0000010176016ba0 R08: 0000000000000000 R09:
ffffffff803ba8c8
2007-01-13 00:15:18 R10: 0000000100000000 R11: ffffffffa03ea16f R12:
000001005c090000
2007-01-13 00:15:18 R13: 00000000fffffffb R14: 00000100c3fa2270 R15:
00000102fbe56c80
2007-01-13 00:15:18 FS:  0000002a96864ce0(0000) GS:ffffffff804e3280(0000)
knlGS:0000000000000000
2007-01-13 00:15:18 CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
2007-01-13 00:15:18 CR2: 0000002a959c2469 CR3: 00000001fff26000 CR4:
00000000000006e0
2007-01-13 00:15:18 Process umt2k_DD (pid: 6827, threadinfo 00000100bc3ac000,
task 000001CPU#0 is frozen.
2007-01-13 00:15:21 CPU#1 is frozen.
2007-01-13 00:15:21 CPU#2 is frozen.
2007-01-13 00:15:21 CPU#3 is frozen.
2007-01-13 00:15:21 CPU#4 is frozen.
2007-01-13 00:15:21 CPU#5 is executing netdump.
2007-01-13 00:15:21 CPU#6 is frozen.
2007-01-13 00:15:21 CPU#7 is frozen.
2007-01-13 00:15:21 < netdump activated - performing handshake with the
server. >
2007-01-13 00:15:21 NETDUMP START!

Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
https://bugzilla.lustre.org/show_bug.cgi?id=11546



Created an attachment (id=9336)
Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
 --> (https://bugzilla.lustre.org/attachment.cgi?id=9336&action=view)
Back traces from crash dump

Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
https://bugzilla.lustre.org/show_bug.cgi?id=11546



Whoops, it looks like Terry already filed this as bug 11545 last night.

Please don''t reply to lustre-devel. Instead, comment in Bugzilla by
using the following link:
https://bugzilla.lustre.org/show_bug.cgi?id=11546

           What    |Removed                     |Added
----------------------------------------------------------------------------
OtherBugsDependingO|                            |11545
              nThis|                            |
                 CC|                            |th@llnl.gov


*** Bug 11545 has been marked as a duplicate of this bug. ***