[LU-2260] 2.1.3 Client LBUG

• Status: Resolved
• Project: Lustre
• Affects Version/s: Lustre 2.1.3
• Type: Bug
• Priority: Major
• Reporter: Roland Fehrenbacher
• Assignee: WC Triage
• Resolution: Duplicate

Environment

Vanilla kernel 2.6.32.59 + kernel patches from 2.1.3 (sles11 series)

• Severity: 3

Description

I just ran into the following kernel panic on 2.1.3:

[122107.084072] LustreError: 3698:0:(socklnd_cb.c:2518:ksocknal_check_peer_timeouts()) Total 1 stale ZC_REQs for peer 192.168.62.201@tcp detected; the oldest(ffff88002b888000) timed out 1 secs ago, resid: 0, wmem: 3902680
[122107.086329] LustreError: 3698:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff88003187c000
[122107.090814] LustreError: 3693:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff88000850a000
[122107.091945] LustreError: 3698:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff880007afc000
[122107.093077] LustreError: 3693:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff88003e19e000
[122107.095582] LustreError: 3698:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff8800370a8000
[122107.097038] LustreError: 3693:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff88003997a000
[122107.098707] LustreError: 3698:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff880028006000
[122107.100127] LustreError: 3693:0:(events.c:194:client_bulk_callback()) event type 0, status -5, desc ffff8800313b2000
[122113.426533] LustreError: 3778:0:(client.c:1702:ptlrpc_check_set()) @@@ bulk transfer failed req@ffff880007b98c00 x1417357565721132/t60129987996(60129987996) o4->l-OST0000-osc-ffff880031303000@192.168.62.201@tcp:6/4 lens 456/416 e 1 to 0 dl 1351819648 ref 3 fl Bulk:R/4/0 rc 0/0
[122113.431918] LustreError: 3778:0:(client.c:1703:ptlrpc_check_set()) LBUG
[122113.441554] Kernel panic - not syncing: LBUG

Issue Links

• duplicates: LU-1039 data corruption in check_set
• duplicates: LU-901 LustreError: 25196:0:(client.c:1696:p...

Comments

[Ned Bass]

I believe this LBUG is fixed by this patch:

http://review.whamcloud.com/#change,4499

[Peter Jones]

Seems likely a duplicate of LU-1039