Bug 15523
Summary: | Receiving "BUG: soft lockup - CPU#(number) stuck for xxs!" appears to be disk IO related. system_call_fastpath | ||
---|---|---|---|
Product: | File System | Reporter: | xousnet |
Component: | VFS | Assignee: | fs_vfs |
Status: | RESOLVED CODE_FIX | ||
Severity: | normal | CC: | joe, josephtsalisbury |
Priority: | P1 | ||
Hardware: | All | ||
OS: | Linux | ||
Kernel Version: | 2.6.31.6 | Subsystem: | |
Regression: | No | Bisected commit-id: |
Description
xousnet
2010-03-12 15:32:24 UTC
Also received the following bug: 1391.162705] Assertion failed: *nmap >= 1, file: fs/xfs/xfs_bmap.c, line: 4846 [ 1391.162738] ------------[ cut here ]------------ [ 1391.162798] kernel BUG at fs/xfs/support/debug.c:109! [ 1391.162864] invalid opcode: 0000 [#1] SMP [ 1391.162930] last sysfs file: /sys/devices/virtual/block/dm-8/dev [ 1391.162995] CPU 3 [ 1391.163057] Modules linked in: snd_hda_codec_atihdmi snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_timer r8169 snd mii amd64_edac_mod soundcore snd_page_alloc i2c_piix4 sata_promise pata_atiixp [ 1391.163270] Pid: 12261, comm: rsync Not tainted 2.6.31.6-luffy #1 System Product Name [ 1391.163387] RIP: 0010:[<ffffffff81258869>] [<ffffffff81258869>] assfail+0x1a/0x1e [ 1391.163514] RSP: 0018:ffff880117d53bc8 EFLAGS: 00010292 [ 1391.163577] RAX: 0000000000000054 RBX: 0000000000000000 RCX: 0000000000013c9e [ 1391.163589] RDX: 0000000000006767 RSI: 0000000000000046 RDI: ffff880117d53a18 [ 1391.163589] RBP: ffff880117d53bc8 R08: 0000000000000002 R09: ffffffff8167fdad [ 1391.163589] R10: 0000000000000000 R11: 0000000000018600 R12: 0000000000000002 [ 1391.163589] R13: ffff88004ae99c00 R14: 0000000800000000 R15: 0000000000005000 [ 1391.163589] FS: 00007f50995a56f0(0000) GS:ffff880028073000(0000) knlGS:0000000000000000 [ 1391.163589] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1391.163589] CR2: 00007fa55af2f8a0 CR3: 0000000100f69000 CR4: 00000000000006e0 [ 1391.163589] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1391.163589] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 1391.163589] Process rsync (pid: 12261, threadinfo ffff880117d52000, task ffff88010f9f9e40) [ 1391.163589] Stack: [ 1391.163589] ffff880117d53da8 ffffffff8120e2ba ffff880117d53c18 0000000000000246 [ 1391.163589] <0> 0000001800000250 0000000000000000 0000000000000250 0000000000000000 [ 1391.163589] <0> 0000000000000064 ffff88011dc20400 ffff880117d53c58 ffffffff8124cdef [ 1391.163589] Call Trace: [ 1391.163589] [<ffffffff8120e2ba>] xfs_bmapi+0x62/0x15ac [ 1391.163589] [<ffffffff8124cdef>] ? kmem_zone_alloc+0x67/0xaf [ 1391.163589] [<ffffffff810cc205>] ? virt_to_head_page+0x9/0x2a [ 1391.163589] [<ffffffff81250643>] ? xfs_buf_free+0xc3/0xcc [ 1391.163589] [<ffffffff81250743>] ? xfs_buf_rele+0xf7/0x100 [ 1391.163589] [<ffffffff8124616e>] ? xfs_buf_relse+0x23/0x27 [ 1391.163589] [<ffffffff81246398>] ? xfs_trans_brelse+0x226/0x22f [ 1391.163589] [<ffffffff812188b7>] ? xfs_da_brelse+0xab/0xd0 [ 1391.163589] [<ffffffff810e0782>] ? filldir+0x6e/0xbd [ 1391.163589] [<ffffffff81221358>] xfs_dir2_leaf_getdents+0x23e/0x683 [ 1391.163589] [<ffffffff810d25d2>] ? nameidata_to_filp+0x41/0x52 [ 1391.163589] [<ffffffff810e0714>] ? filldir+0x0/0xbd [ 1391.163589] [<ffffffff810e0714>] ? filldir+0x0/0xbd [ 1391.163589] [<ffffffff8121c806>] xfs_readdir+0xdd/0xec [ 1391.163589] [<ffffffff810e8d4c>] ? mntput_no_expire+0x24/0xe8 [ 1391.163589] [<ffffffff810e0714>] ? filldir+0x0/0xbd [ 1391.163589] [<ffffffff81251683>] xfs_file_readdir+0x34/0x43 [ 1391.163589] [<ffffffff810e08fc>] vfs_readdir+0x79/0xaf [ 1391.163589] [<ffffffff810e0a70>] sys_getdents+0x7d/0xc9 [ 1391.163589] [<ffffffff8100baab>] system_call_fastpath+0x16/0x1b [ 1391.163589] Code: 6b 81 c7 44 24 08 01 00 00 00 e8 4c 2c 04 00 c9 c3 55 89 d1 31 c0 48 89 f2 48 89 fe 48 c7 c7 0b 49 6b 81 48 89 e5 e8 fe e1 2a 00 <0f> 0b eb fe 55 48 89 e5 41 57 41 56 49 89 d6 41 55 49 89 cd 41 [ 1391.163589] RIP [<ffffffff81258869>] assfail+0x1a/0x1e [ 1391.163589] RSP <ffff880117d53bc8> [ 1391.166797] ---[ end trace ac94affb5388788f ]--- After some googling and experimentation the issue may have been caused by having debug support for XFS enabled. http://oss.sgi.com/bugzilla/show_bug.cgi?id=850 Cloning the entire file system to see I'm able to get the same bug or lockup and will close if I don't. Did you end up finding a cause for this bug? I may be suffering from the same issue. Hi, Yes, I believe the problem was that I had CONFIG_XFS_DEBUG enabled and apparently this dev feature can cause these results. After recompiling the kernel the issues stopped for at least a month. I then ended up moving the services to new hardware anyway. |