[LU-2531] osc_page.c:432:osc_page_delete()) ASSERTION( 0 ) failed running racer

• Type: Bug
• Resolution: Fixed
• Priority: Blocker
• Fix Version/s: Lustre 2.4.0
• Affects Version/s: Lustre 2.4.0
• Labels: MB
• Severity: 3
• Assignee: Jinshan Xiong (Inactive)
• Reporter: Oleg Drokin

Description

Hit this running racer on a single node

[56349.656614] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800805c6f08[3 ffff88000bf11f80:256 ^(null)_ffff880014be0f08 0 0 1 (null) (null) 0x0]
[56349.657354] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880014be0f08[2 ffff88002a8ecf98:256 ^ffff8800805c6f08_(null) 0 0 1 (null) (null) 0x0]
[56349.658145] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88006e65eb60(0:0:0) vm@ffffea00021b5a58 2000000000083c 2:0 ffff8800805c6f08 256 lru
[56349.658890] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff88002510ee00
[56349.659360] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff880062170f08: 1< 0x845fed 258 0 + - > 2< 1048576 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.660491] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff8800805c6f08
[56349.660996] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.661284] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880014be1f08[3 ffff88000bf11f80:257 ^(null)_ffff88001333ef08 0 0 1 (null) (null) 0x0]
[56349.662042] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff88001333ef08[2 ffff88002a8ecf98:257 ^ffff880014be1f08_(null) 0 0 1 (null) (null) 0x0]
[56349.662802] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88006e65ebc8(0:0:0) vm@ffffea0001cef2d0 2000000000083c 2:0 ffff880014be1f08 257 lru
[56349.663548] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff88002510e620
[56349.664016] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff88002b782f08: 1< 0x845fed 258 0 + - > 2< 1052672 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.665336] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff880014be1f08
[56349.665805] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.666679] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880093a26f08[3 ffff88000bf11f80:258 ^(null)_ffff88003c596f08 0 0 1 (null) (null) 0x0]
[56349.667419] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff88003c596f08[2 ffff88002a8ecf98:258 ^ffff880093a26f08_(null) 0 0 1 (null) (null) 0x0]
[56349.668166] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88006e65ec30(0:0:0) vm@ffffea0002285560 2000000000083c 2:0 ffff880093a26f08 258 lru
[56349.668917] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff88002510ece0
[56349.669389] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff88005bf32f08: 1< 0x845fed 258 0 + - > 2< 1056768 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.671402] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff880093a26f08
[56349.671883] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.672186] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800304a3f08[3 ffff88000bf11f80:259 ^(null)_ffff880032388f08 0 0 1 (null) (null) 0x0]
[56349.672953] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880032388f08[2 ffff88002a8ecf98:259 ^ffff8800304a3f08_(null) 0 0 1 (null) (null) 0x0]
[56349.673667] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88006e65ec98(0:0:0) vm@ffffea0001d40e80 2000000000083c 2:0 ffff8800304a3f08 259 lru
[56349.674403] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff8800740957d0
[56349.674898] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff8800922cff08: 1< 0x845fed 258 0 + - > 2< 1060864 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.676000] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff8800304a3f08
[56349.676500] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.676872] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800304a2f08[3 ffff88000bf11f80:260 ^(null)_ffff8800639baf08 0 0 1 (null) (null) 0x0]
[56349.677605] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800639baf08[2 ffff88002a8ecf98:260 ^ffff8800304a2f08_(null) 0 0 1 (null) (null) 0x0]
[56349.678374] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88006e65ed00(0:0:0) vm@ffffea0002114048 2000000000083c 2:0 ffff8800304a2f08 260 lru
[56349.679110] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff880074095c98
[56349.679560] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff880081cf0f08: 1< 0x845fed 258 0 + - > 2< 1064960 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.680665] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff8800304a2f08
[56349.681134] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.681428] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800639bbf08[3 ffff88000bf11f80:261 ^(null)_ffff8800223a9f08 0 0 1 (null) (null) 0x0]
[56349.682160] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800223a9f08[2 ffff88002a8ecf98:261 ^ffff8800639bbf08_(null) 0 0 1 (null) (null) 0x0]
[56349.682893] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88006e65ed68(0:0:0) vm@ffffea000218f5a0 2000000000083c 2:0 ffff8800639bbf08 261 lru
[56349.683625] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff880074095ce0
[56349.684092] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff88001309df08: 1< 0x845fed 258 0 + - > 2< 1069056 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.685177] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff8800639bbf08
[56349.685623] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.685921] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800223a8f08[3 ffff88000bf11f80:262 ^(null)_ffff8800248a3f08 0 0 1 (null) (null) 0x0]
[56349.686682] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800248a3f08[2 ffff88002a8ecf98:262 ^ffff8800223a8f08_(null) 0 0 1 (null) (null) 0x0]
[56349.687427] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88002d0ee0d0(0:0:0) vm@ffffea0001f0b178 2000000000083c 2:0 ffff8800223a8f08 262 lru
[56349.688184] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff880074095ae8
[56349.688665] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff88008e200f08: 1< 0x845fed 258 0 + - > 2< 1073152 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.689748] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff8800223a8f08
[56349.690214] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.690501] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880075c2ef08[3 ffff88000bf11f80:263 ^(null)_ffff880033ee2f08 0 0 1 (null) (null) 0x0]
[56349.691237] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880033ee2f08[2 ffff88002a8ecf98:263 ^ffff880075c2ef08_(null) 0 0 1 (null) (null) 0x0]
[56349.691967] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88002d0ee4e0(0:0:0) vm@ffffea00020fec90 2000000000083c 2:0 ffff880075c2ef08 263 lru
[56349.692706] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff880074095aa0
[56349.693172] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff880093ce0f08: 1< 0x845fed 258 0 + - > 2< 1077248 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.694248] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff880075c2ef08
[56349.694717] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.695010] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880033ee3f08[3 ffff88000bf11f80:264 ^(null)_ffff880061765f08 0 0 1 (null) (null) 0x0]
[56349.696293] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff880061765f08[2 ffff88002a8ecf98:264 ^ffff880033ee3f08_(null) 0 0 1 (null) (null) 0x0]
[56349.697945] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88002d0eea90(0:0:0) vm@ffffea0001f481f8 2000000000083c 2:0 ffff880033ee3f08 264 lru
[56349.698697] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff880074095740
[56349.699176] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff8800794ccf08: 1< 0x845fed 258 0 + - > 2< 1081344 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.700246] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff880033ee3f08
[56349.700732] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.701026] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff8800393f6f08[3 ffff88000bf11f80:265 ^(null)_ffff88008b6e9f08 0 0 1 (null) (null) 0x0]
[56349.701758] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) page@ffff88008b6e9f08[2 ffff88002a8ecf98:265 ^ffff8800393f6f08_(null) 0 0 1 (null) (null) 0x0]
[56349.702492] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff88002d0eec30(0:0:0) vm@ffffea000277cc78 2000000000083c 2:0 ffff8800393f6f08 265 lru
[56349.703850] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff880074095110
[56349.704321] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff88006b098f08: 1< 0x845fed 258 0 + - > 2< 1085440 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 1 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.705396] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) end page@ffff8800393f6f08
[56349.706003] LustreError: 20323:0:(osc_io.c:364:trunc_check_cb()) exists 0/cp.
[56349.758028] LustreError: 20323:0:(osc_cache.c:2370:osc_teardown_async_page()) extent ffff88006e1f1f38@{[256 -> 506/511], [2|0|-|cache|wi|ffff880078590eb0], [1028096|251|+|-|ffff88002b60ced8|256|(null)]} trunc at 256.
[56349.759172] LustreError: 20323:0:(osc_page.c:431:osc_page_delete()) page@ffff8800805c6f08[2 ffff88000bf11f80:256 ^(null)_ffff880014be0f08 4 0 1 (null) (null) 0x0]
[56349.759981] LustreError: 20323:0:(osc_page.c:431:osc_page_delete()) page@ffff880014be0f08[2 ffff88002a8ecf98:256 ^ffff8800805c6f08_(null) 4 0 1 (null) (null) 0x0]
[56349.760931] LustreError: 20323:0:(osc_page.c:431:osc_page_delete()) vvp-page@ffff88006e65eb60(0:0:0) vm@ffffea00021b5a58 20000000000035 3:0 0 256 lru
[56349.761537] LustreError: 20323:0:(osc_page.c:431:osc_page_delete()) lov-page@ffff88002510ee00
[56349.762131] LustreError: 20323:0:(osc_page.c:431:osc_page_delete()) osc-page@ffff880062170f08: 1< 0x845fed 258 0 + - > 2< 1048576 0 4096 0x0 0x520 | (null) ffff88007d410cf0 ffff880078590eb0 > 3< + ffff88006fc50140 0 0 0 > 4< 0 0 8 20480 - | - - + - > 5< - - + - | 0 - | 251 - ->
[56349.763222] LustreError: 20323:0:(osc_page.c:431:osc_page_delete()) end page@ffff8800805c6f08
[56349.763780] LustreError: 20323:0:(osc_page.c:431:osc_page_delete()) Trying to teardown failed: -16
[56349.764587] LustreError: 20323:0:(osc_page.c:432:osc_page_delete()) ASSERTION( 0 ) failed: 
[56349.765113] LustreError: 20323:0:(osc_page.c:432:osc_page_delete()) LBUG
[56349.765406] Pid: 20323, comm: cp
[56349.765648] 
[56349.765648] Call Trace:
[56349.766258]  [<ffffffffa0405915>] libcfs_debug_dumpstack+0x55/0x80 [libcfs]
[56349.766719]  [<ffffffffa0405f27>] lbug_with_loc+0x47/0xb0 [libcfs]
[56349.767070]  [<ffffffffa09bd5dd>] osc_page_delete+0x32d/0x330 [osc]
[56349.767381]  [<ffffffffa05d6b15>] cl_page_delete0+0xc5/0x510 [obdclass]
[56349.767713]  [<ffffffffa05d6fa2>] cl_page_delete+0x42/0x120 [obdclass]
[56349.768192]  [<ffffffffa0e4025d>] ll_invalidatepage+0x8d/0x180 [lustre]
[56349.768623]  [<ffffffff81129ee8>] do_invalidatepage+0x28/0x30
[56349.768950]  [<ffffffff8112a102>] truncate_inode_page+0xa2/0xc0
[56349.769216]  [<ffffffff8112a42a>] truncate_inode_pages_range+0x15a/0x460
[56349.769515]  [<ffffffff8112a745>] truncate_inode_pages+0x15/0x20
[56349.769877]  [<ffffffff8112a797>] truncate_pagecache+0x47/0x70
[56349.770297]  [<ffffffff8112a7d9>] truncate_setsize+0x19/0x20
[56349.770657]  [<ffffffff8112a81e>] vmtruncate+0x3e/0x70
[56349.771010]  [<ffffffffa0e53a53>] vvp_io_setattr_end+0x63/0x80 [lustre]
[56349.771349]  [<ffffffffa05dec60>] cl_io_end+0x60/0x150 [obdclass]
[56349.771769]  [<ffffffffa05e3d82>] cl_io_loop+0xc2/0x1b0 [obdclass]
[56349.772084]  [<ffffffffa0e4c448>] cl_setattr_ost+0x208/0x2d0 [lustre]
[56349.772389]  [<ffffffffa0e1c122>] ll_setattr_raw+0x792/0xfb0 [lustre]
[56349.772706]  [<ffffffffa0e1c99b>] ll_setattr+0x5b/0xf0 [lustre]
[56349.772987]  [<ffffffff81197688>] notify_change+0x168/0x340
[56349.773252]  [<ffffffff81179af4>] do_truncate+0x64/0xa0
[56349.773530]  [<ffffffff8118c309>] do_filp_open+0x829/0xd90
[56349.773854]  [<ffffffff8118827b>] ? getname+0x3b/0x250
[56349.774277]  [<ffffffff81044f4e>] ? kernel_map_pages+0xfe/0x110
[56349.774708]  [<ffffffff8119861b>] ? alloc_fd+0xab/0x160
[56349.775166]  [<ffffffff81178839>] do_sys_open+0x69/0x140
[56349.775569]  [<ffffffff81178950>] sys_open+0x20/0x30
[56349.775968]  [<ffffffff8100b0f2>] system_call_fastpath+0x16/0x1b
[56349.776371] 
[56349.777741] Kernel panic - not syncing: LBUG

vmcore and modules are in /exports/crashdumps/192.168.10.218-2012-12-23-08:15:29

Issue Links

• is related to: LU-3448 osc_page_delete()) ASSERTION(0) failed running racer

Comments

[Jinshan Xiong (Inactive)]

This should be a duplication of LU-3448.

[Sarah Liu]

Hit this issue again on build lustre-master #1532

https://maloo.whamcloud.com/test_sets/480b1f6e-d993-11e2-8ecf-52540035b04c

Lustre: DEBUG MARKER: == racer test 1: racer on clients: client-16vm1,client-16vm2.lab.whamcloud.com DURATION=900 == 07:11:36 (1371651096)
07:11:38:Lustre: DEBUG MARKER: DURATION=900 MDSCOUNT=1 				   /usr/lib64/lustre/tests/racer/racer.sh /mnt/lustre/racer 
07:11:38:Lustre: DEBUG MARKER: DURATION=900 MDSCOUNT=1 				   /usr/lib64/lustre/tests/racer/racer.sh /mnt/lustre2/racer 
07:14:02:LustreError: 11841:0:(osc_cache.c:2381:osc_teardown_async_page()) extent ffff88007b768e58@{[1418 -> 1422/1535], [2|0|-|cache|wi|ffff88005a321180], [20480|5|+|-|ffff8800583e6ed0|256|(null)]} trunc at 1418.
07:14:02:LustreError: 11841:0:(osc_page.c:430:osc_page_delete()) page@ffff8800530bde00[2 ffff880057212808:1418 ^(null)_ffff8800530bc200 4 0 1 (null) (null) 0x0]
07:14:02:LustreError: 11841:0:(osc_page.c:430:osc_page_delete()) page@ffff8800530bc200[2 ffff88005b73db08:1418 ^ffff8800530bde00_(null) 4 0 1 (null) (null) 0x0]
07:14:05:LustreError: 11841:0:(osc_page.c:430:osc_page_delete()) vvp-page@ffff8800530bdeb0(0:0:0) vm@ffffea0000ddc238 20000000000015 4:0 0 1418 lru
07:14:05:LustreError: 11841:0:(osc_page.c:430:osc_page_delete()) lov-page@ffff8800530bdf00
07:14:05:LustreError: 11841:0:(osc_page.c:430:osc_page_delete()) osc-page@ffff8800530bc2d8: 1< 0x845fed 258 0 + - > 2< 5808128 0 4096 0x0 0x520 | (null) ffff8800693187c0 ffff88005a321180 > 3< + ffff88005809eaa0 0 0 0 > 4< 0 0 8 39362560 - | - - + - > 5< - - + - | 0 - | 5 - ->
07:14:06:LustreError: 11841:0:(osc_page.c:430:osc_page_delete()) end page@ffff8800530bde00
07:14:06:LustreError: 11841:0:(osc_page.c:430:osc_page_delete()) Trying to teardown failed: -16
07:14:06:LustreError: 11841:0:(osc_page.c:431:osc_page_delete()) ASSERTION( 0 ) failed: 
07:14:06:LustreError: 11841:0:(osc_page.c:431:osc_page_delete()) LBUG
07:14:06:Pid: 11841, comm: cp
07:14:06:
07:14:06:Call Trace:
07:14:06: [<ffffffffa058e895>] libcfs_debug_dumpstack+0x55/0x80 [libcfs]
07:14:06: [<ffffffffa058ee97>] lbug_with_loc+0x47/0xb0 [libcfs]
07:14:06: [<ffffffffa0a3b701>] osc_page_delete+0x311/0x320 [osc]
07:14:06: [<ffffffffa06f5125>] cl_page_delete0+0xc5/0x4e0 [obdclass]
07:14:06: [<ffffffffa06f5582>] cl_page_delete+0x42/0x120 [obdclass]
07:14:06: [<ffffffffa0b7c7ad>] ll_invalidatepage+0x8d/0x160 [lustre]
07:14:06: [<ffffffff811304e5>] do_invalidatepage+0x25/0x30
07:14:06: [<ffffffff81130802>] truncate_inode_page+0xa2/0xc0
07:14:06: [<ffffffff81130baf>] truncate_inode_pages_range+0x16f/0x500
07:14:06: [<ffffffff81142562>] ? unmap_mapping_range+0x72/0x140
07:14:06: [<ffffffff81130fd5>] truncate_inode_pages+0x15/0x20
07:14:06: [<ffffffff8113102f>] truncate_pagecache+0x4f/0x70
07:14:06: [<ffffffff811a918a>] simple_setsize+0x3a/0x50
07:14:06: [<ffffffff811a91e0>] simple_setattr+0x40/0x70
07:14:06: [<ffffffffa0b56556>] ll_setattr_raw+0x2a6/0x1090 [lustre]
07:14:06: [<ffffffffa0b5739b>] ll_setattr+0x5b/0xf0 [lustre]
07:14:06: [<ffffffff8119e708>] notify_change+0x168/0x340
07:14:06: [<ffffffff8117f1e4>] do_truncate+0x64/0xa0
07:14:06: [<ffffffff8121cd9f>] ? security_inode_permission+0x1f/0x30
07:14:06: [<ffffffff81193084>] do_filp_open+0x844/0xdd0
07:14:06: [<ffffffff8104757c>] ? __do_page_fault+0x1ec/0x480
07:14:06: [<ffffffff8119f5e2>] ? alloc_fd+0x92/0x160
07:14:06: [<ffffffff8117df59>] do_sys_open+0x69/0x140
07:14:06: [<ffffffff8117e070>] sys_open+0x20/0x30
07:14:06: [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b
07:14:06:
07:14:06:Kernel panic - not syncing: LBUG

[Jodi Levi (Inactive)]

Patch landed. Please reopen if more work is needed.

[Jinshan Xiong (Inactive)]

patch is at: http://review.whamcloud.com/4896, please give it a try

[Jinshan Xiong (Inactive)]

I found the root cause of this problem. It turns out that the one write RPC was failed with -28 so that truncate process stopped to evicting OSC extents and caused dirty pages still in cache. This problem is easy to fix but it seems like the grant algorithm is broken.

[Oleg Drokin]

Just hit it again

[37032.954552] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) page@ffff880010eaef08[3 ffff880022de2f80:256 ^(null)_ffff880010eaff08 2 0 1 (null) ffff880014409458 0x0]
[37032.956370] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) page@ffff880010eaff08[2 ffff880084a92f98:256 ^ffff880010eaef08_(null) 0 0 1 (null) (null) 0x0]
[37032.957249] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff880010ea54e0(0:0:0) vm@ffffea00022004f0 2000000000082e 2:0 ffff880010eaef08 256 lru
[37032.958143] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff88005a0487d0
[37032.958671] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff8800571e0f08: 1< 0x845fed 258 0 - - > 2< 1048576 0 4096 0x0 0x520 | (null) ffff88003723caf0 ffff88008a4deeb0 > 3< + (null) 0 0 0 > 4< 0 0 8 4997120 - | - - + - > 5< - - + - | 0 - | 1 - ->
[37032.959823] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) end page@ffff880010eaef08
[37032.960336] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) exists 0/dd.
[37032.960749] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) page@ffff880071bdef08[3 ffff880022de2f80:512 ^(null)_ffff880071bdff08 0 0 1 (null) (null) 0x0]
[37032.961551] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) page@ffff880071bdff08[2 ffff880084a92f98:512 ^ffff880071bdef08_(null) 0 0 1 (null) (null) 0x0]
[37032.962441] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) vvp-page@ffff8800824c4a90(0:0:0) vm@ffffea0001ce55f8 2000000000081c 3:0 ffff880071bdef08 512 lru
[37032.969323] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) lov-page@ffff88005390e5d8
[37032.969898] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) osc-page@ffff880071bc8f08: 1< 0x845fed 258 0 + - > 2< 2097152 0 4096 0x0 0x520 | (null) ffff88003723caf0 ffff88008a4deeb0 > 3< + ffff88006d186400 1 0 0 > 4< 0 0 8 4997120 - | - - + - > 5< - - + - | 0 - | 1 - ->
[37032.971071] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) end page@ffff880071bdef08
[37032.971577] LustreError: 25132:0:(osc_io.c:364:trunc_check_cb()) exists 0/dd.
[37032.983825] LustreError: 25132:0:(osc_cache.c:2370:osc_teardown_async_page()) extent ffff88004b3eaf38@{[512 -> 512/767], [2|0|-|cache|wi|ffff88008a4deeb0], [4096|1|+|-|ffff880051415ed8|256|(null)]} trunc at 512.
[37032.984734] LustreError: 25132:0:(osc_page.c:431:osc_page_delete()) page@ffff880071bdef08[2 ffff880022de2f80:512 ^(null)_ffff880071bdff08 4 0 1 (null) (null) 0x0]
[37032.985539] LustreError: 25132:0:(osc_page.c:431:osc_page_delete()) page@ffff880071bdff08[2 ffff880084a92f98:512 ^ffff880071bdef08_(null) 4 0 1 (null) (null) 0x0]
[37032.986366] LustreError: 25132:0:(osc_page.c:431:osc_page_delete()) vvp-page@ffff8800824c4a90(0:0:0) vm@ffffea0001ce55f8 20000000000035 3:0 0 512 lru
[37032.986978] LustreError: 25132:0:(osc_page.c:431:osc_page_delete()) lov-page@ffff88005390e5d8
[37032.987521] LustreError: 25132:0:(osc_page.c:431:osc_page_delete()) osc-page@ffff880071bc8f08: 1< 0x845fed 258 0 + - > 2< 2097152 0 4096 0x0 0x520 | (null) ffff88003723caf0 ffff88008a4deeb0 > 3< + ffff88006d186400 0 0 0 > 4< 0 0 8 4997120 - | - - + - > 5< - - + - | 0 - | 1 - ->
[37032.988857] LustreError: 25132:0:(osc_page.c:431:osc_page_delete()) end page@ffff880071bdef08
[37032.989387] LustreError: 25132:0:(osc_page.c:431:osc_page_delete()) Trying to teardown failed: -16
[37032.989919] LustreError: 25132:0:(osc_page.c:432:osc_page_delete()) ASSERTION( 0 ) failed: 
[37032.990433] LustreError: 25132:0:(osc_page.c:432:osc_page_delete()) LBUG
[37032.990736] Pid: 25132, comm: dd
[37032.990974] 
[37032.990975] Call Trace:
[37032.991411]  [<ffffffffa0c09915>] libcfs_debug_dumpstack+0x55/0x80 [libcfs]
[37032.991739]  [<ffffffffa0c09f27>] lbug_with_loc+0x47/0xb0 [libcfs]
[37032.992094]  [<ffffffffa049a5dd>] osc_page_delete+0x32d/0x330 [osc]
[37032.992466]  [<ffffffffa0edcb15>] cl_page_delete0+0xc5/0x510 [obdclass]
[37032.992808]  [<ffffffffa0edcfa2>] cl_page_delete+0x42/0x120 [obdclass]
[37032.993141]  [<ffffffffa0a5025d>] ll_invalidatepage+0x8d/0x180 [lustre]
[37032.993469]  [<ffffffff81129ee8>] do_invalidatepage+0x28/0x30
[37032.993889]  [<ffffffff8112a102>] truncate_inode_page+0xa2/0xc0
[37032.994200]  [<ffffffff8112a42a>] truncate_inode_pages_range+0x15a/0x460
[37032.994517]  [<ffffffff8112a745>] truncate_inode_pages+0x15/0x20
[37032.994857]  [<ffffffff8112a797>] truncate_pagecache+0x47/0x70
[37032.995175]  [<ffffffff8112a7d9>] truncate_setsize+0x19/0x20
[37032.995461]  [<ffffffff8112a81e>] vmtruncate+0x3e/0x70
[37032.995750]  [<ffffffffa0a63a53>] vvp_io_setattr_end+0x63/0x80 [lustre]
[37032.996091]  [<ffffffffa0ee4c60>] cl_io_end+0x60/0x150 [obdclass]
[37032.996417]  [<ffffffffa0ee9d82>] cl_io_loop+0xc2/0x1b0 [obdclass]
[37032.996726]  [<ffffffffa0a5c448>] cl_setattr_ost+0x208/0x2d0 [lustre]
[37032.997040]  [<ffffffffa0a2c122>] ll_setattr_raw+0x792/0xfb0 [lustre]
[37032.997384]  [<ffffffffa0a2c99b>] ll_setattr+0x5b/0xf0 [lustre]
[37032.997676]  [<ffffffff81197688>] notify_change+0x168/0x340
[37032.998008]  [<ffffffff81179af4>] do_truncate+0x64/0xa0
[37032.998286]  [<ffffffff8118c309>] do_filp_open+0x829/0xd90
[37032.998563]  [<ffffffff8119861b>] ? alloc_fd+0xab/0x160
[37032.998839]  [<ffffffff81178839>] do_sys_open+0x69/0x140
[37032.999168]  [<ffffffff8117b666>] ? sys_lseek+0x66/0x80
[37032.999446]  [<ffffffff81178950>] sys_open+0x20/0x30
[37032.999719]  [<ffffffff8100b0f2>] system_call_fastpath+0x16/0x1b
[37033.000016] 
[37033.014558] Kernel panic - not syncing: LBUG

Dump and modules in /exports/crashdumps/192.168.10.210-2012-12-27-10:28:56