Re: 2.6.32.3 x86_64 - XFS hangs, all I/O to D-state bug (again)
From: Justin Piszcz
Date: Thu Feb 11 2010 - 09:35:35 EST
On Thu, 11 Feb 2010, Justin Piszcz wrote:
Hm..
# cd /raid5_mdadm
# touch a
.. hang ..
From echo t to sysrq-trigger:
[ 6906.296062] touch D ffff880222402680 0 705 599 0x00000000
[ 6906.296062] ffff880034de3360 0000000000000086 0000000000014000 ffffffff811c985b
[ 6906.296062] 000000000000c928 ffff88019c26bfd8 ffff880222402680 ffff8802224028f8
[ 6906.296062] 0000000300014000 ffffffff811f5277 ffff88023e52f000 ffff8802224028f8
[ 6906.296062] Call Trace:
[ 6906.296062] [<ffffffff811c985b>] ? xfs_buf_item_init+0xab/0x110
[ 6906.296062] [<ffffffff811f5277>] ? xfs_trans_read_buf+0x247/0x350
[ 6906.296062] [<ffffffff811feb3b>] ? xfs_buf_rele+0x3b/0x100
[ 6906.296122] [<ffffffff810b56e6>] ? cache_alloc_refill+0x96/0x590
[ 6906.296125] [<ffffffff8145dbc5>] ? schedule_timeout+0x195/0x1f0
[ 6906.296127] [<ffffffff8145ea81>] ? __down+0x61/0xa0
[ 6906.296131] [<ffffffff81072046>] ? down+0x46/0x50
[ 6906.296134] [<ffffffff811ef1b5>] ? xfs_getsb+0x15/0x40
[ 6906.296134] [<ffffffff811f53da>] ? xfs_trans_getsb+0x5a/0xc0
[ 6906.296134] [<ffffffff811f325f>] ? xfs_trans_apply_sb_deltas+0xf/0x300
[ 6906.296144] [<ffffffff811f39fb>] ? _xfs_trans_commit+0xeb/0x3a0
[ 6906.296144] [<ffffffff811dffd3>] ? xfs_ialloc+0x513/0x6d0
[ 6906.296144] [<ffffffff811ce72a>] ? xfs_dir_createname+0x17a/0x1d0
[ 6906.296144] [<ffffffff8105d60e>] ? current_fs_time+0x1e/0x30
[ 6906.296144] [<ffffffff811f86b1>] ? xfs_create+0x491/0x520
[ 6906.296165] [<ffffffff81202752>] ? xfs_vn_mknod+0x82/0x130
[ 6906.296167] [<ffffffff810c46c6>] ? vfs_create+0xa6/0xf0
[ 6906.296170] [<ffffffff810c806e>] ? do_filp_open+0x9fe/0xad0
[ 6906.296174] [<ffffffff810a2679>] ? handle_mm_fault+0x1b9/0x7d0
[ 6906.296177] [<ffffffff8145d2fc>] ? thread_return+0x3e/0x622
[ 6906.296177] [<ffffffff810b8ae7>] ? do_sys_open+0x97/0x150
[ 6906.296177] [<ffffffff8102eeeb>] ? system_call_fastpath+0x16/0x1b
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/