From: Roland Stigge <stigge@debian.org>
To: linux-scsi@vger.kernel.org
Cc: aacraid@adaptec.com, JBottomley@parallels.com
Subject: Kernel hang w/ aacraid on supermicro X8SIE
Date: Sun, 22 Jan 2012 13:05:42 +0100 [thread overview]
Message-ID: <4F1BFB96.3090905@debian.org> (raw)
Hi,
I'm experiencing serious temporary kernel hangs on a Supermicro X8SIE
machine with an aacraid controller. I'm suspecting the latter one since
the issue looks similar to:
=========================================================================
commit cf16123c9c8e346ed1dd171295a678d77648d7f8
Author: Vasily Averin <vvs@parallels.com>
Date: Fri Nov 11 13:42:16 2011 +0400
[SCSI] aacraid: controller hangs if kernel uses non-default ASPM policy
=========================================================================
The problem is triggered by regular nightly backup rsyncs and is
reproducible: The below kernel traces happen _once_ around the first
nightly rsync after booting. During following days, no further traces
are written, but the machine feels generally slow. I/O during the rsync
runs leading to load values >30.
Both the AAC RAID and the Supermicro board have already been replaced
(with same models) but the problem is still there.
=========================================================================
[29040.293627] INFO: task flush-8:0:1074 blocked for more than 120 seconds.
[29040.293676] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs"
disables this message.
[29040.293727] flush-8:0 D ffff880131ffcfc0 0 1074 2
0x00000000
[29040.293730] ffff880131ffcfc0 0000000000000046 ffff880100000000
ffff880134f480c0
[29040.293733] 0000000000013440 ffff8801319f9fd8 ffff8801319f9fd8
0000000000013440
[29040.293735] ffff880131ffcfc0 ffff8801319f8010 ffff8801319f9810
00000001319f9810
[29040.293738] Call Trace:
[29040.293746] [<ffffffff8134b6dc>] ? io_schedule+0x84/0xc3
[29040.293750] [<ffffffff811a16f1>] ? get_request_wait+0x104/0x199
[29040.293753] [<ffffffff81061b25>] ? wake_up_bit+0x20/0x20
[29040.293756] [<ffffffff811a1bc8>] ? blk_queue_bio+0x17a/0x2ce
[29040.293759] [<ffffffff81129076>] ? T.1020+0x17/0x17
[29040.293761] [<ffffffff811a106e>] ? generic_make_request+0x8e/0xcd
[29040.293763] [<ffffffff811a1186>] ? submit_bio+0xd9/0xf7
[29040.293765] [<ffffffff81129076>] ? T.1020+0x17/0x17
[29040.293767] [<ffffffff8112be2d>] ? bio_alloc_bioset+0x44/0xb3
[29040.293770] [<ffffffff81127cd1>] ? submit_bh+0xe5/0x105
[29040.293772] [<ffffffff8112a360>] ? __block_write_full_page+0x1dd/0x2b5
[29040.293774] [<ffffffff8112c354>] ? I_BDEV+0x8/0x8
[29040.293778] [<ffffffff810c31e2>] ? __writepage+0xa/0x21
[29040.293781] [<ffffffff810c42d5>] ? write_cache_pages+0x226/0x31e
[29040.293783] [<ffffffff810c31d8>] ? set_page_dirty+0x61/0x61
[29040.293785] [<ffffffff810c440b>] ? generic_writepages+0x3e/0x55
[29040.293790] [<ffffffff81122b15>] ? writeback_single_inode+0x178/0x35e
[29040.293792] [<ffffffff81123015>] ? writeback_sb_inodes+0x169/0x1ff
[29040.293794] [<ffffffff81123118>] ? __writeback_inodes_wb+0x6d/0xab
[29040.293796] [<ffffffff8112333f>] ? wb_writeback+0x128/0x222
[29040.293798] [<ffffffff8134b36d>] ? __schedule+0x5a0/0x5cd
[29040.293800] [<ffffffff811235b2>] ? wb_do_writeback+0x179/0x1de
[29040.293805] [<ffffffff81053dcb>] ? del_timer_sync+0x34/0x3e
[29040.293807] [<ffffffff811236da>] ? bdi_writeback_thread+0xc3/0x1fe
[29040.293809] [<ffffffff81123617>] ? wb_do_writeback+0x1de/0x1de
[29040.293811] [<ffffffff81123617>] ? wb_do_writeback+0x1de/0x1de
[29040.293813] [<ffffffff810616e9>] ? kthread+0x7a/0x82
[29040.293816] [<ffffffff81354eb4>] ? kernel_thread_helper+0x4/0x10
[29040.293818] [<ffffffff8106166f>] ? kthread_worker_fn+0x147/0x147
[29040.293820] [<ffffffff81354eb0>] ? gs_change+0x13/0x13
=========================================================================
See also full kernel log at
http://antcom.de/linux-aacraid-supermicro-X8SIE.dmesg
Please redirect me if you suspect the problem elsewhere.
Thanks in advance,
Roland
reply other threads:[~2012-01-22 12:11 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4F1BFB96.3090905@debian.org \
--to=stigge@debian.org \
--cc=JBottomley@parallels.com \
--cc=aacraid@adaptec.com \
--cc=linux-scsi@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.