From: Bart Van Assche <bvanassche@acm.org>
To: Mike Christie <michaelc@cs.wisc.edu>
Cc: linux-kernel <linux-kernel@vger.kernel.org>,
Tejun Heo <tj@kernel.org>, Jens Axboe <axboe@kernel.dk>
Subject: Re: Kernel hangs in truncate_inode_pages()
Date: Fri, 24 Aug 2012 17:47:56 +0000 [thread overview]
Message-ID: <5037BE4C.80609@acm.org> (raw)
In-Reply-To: <5037B8C1.8050903@cs.wisc.edu>
On 08/24/12 17:24, Mike Christie wrote:
> On 08/24/2012 08:13 AM, Bart Van Assche wrote:
>> If I log in with the open-iscsi initiator to an iSCSI target an power
>> down the target the initiator hangs in truncate_inode_pages(). This
>> happens systematically with kernel 3.6-rc3 and it's something I've
>> never seen with kernel 3.4 or before. Has anyone else already run into
>> this issue ?
>
> I have not seen this issue before and have not seen it reported.
>
> Are you doing IO the disk at the time of power down, or are you doing a
> iscsiadm -m node ... --logout command?
There was no I/O load test running at the time of the target power down.
The call stack I posted is what I see before logout. And this is what I
get after iscsi logout:
BUG: soft lockup - CPU#3 stuck for 23s! [iscsid:8589]
Modules linked in: ... [last unloaded: crc32c]
irq event stamp: 918076162
hardirqs last enabled at (918076161): [<ffffffff8140d98f>] _raw_spin_unlock_irqrestore+0x3f/0x70
hardirqs last disabled at (918076162): [<ffffffff814167d7>] apic_timer_interrupt+0x67/0x80
softirqs last enabled at (917955754): [<ffffffff81044162>] __do_softirq+0x142/0x2a0
softirqs last disabled at (917955749): [<ffffffff81416f5c>] call_softirq+0x1c/0x30
CPU 3
Pid: 8589, comm: iscsid Not tainted 3.6.0-rc3+ #1 Gigabyte Technology Co., Ltd. Z68X-UD3H-B3/Z68X-UD3H-B3
RIP: 0010:[<ffffffff8140d991>] [<ffffffff8140d991>] _raw_spin_unlock_irqrestore+0x41/0x70
RSP: 0018:ffff8800ae7e5928 EFLAGS: 00000286
RAX: ffff880106002eb0 RBX: ffffffff810956a2 RCX: 0000000000000006
RDX: 0000000000000040 RSI: ffff880106003498 RDI: ffff880106002eb0
RBP: ffff8800ae7e5938 R08: 0000000000000000 R09: 0000000000000001
R10: 0000000000000002 R11: 0000000000000000 R12: 0000000000000006
R13: 0000000000000007 R14: ffff880106002eb0 R15: ffff880106003498
FS: 00007fa8cfc22700(0000) GS:ffff88012fac0000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00007fa8cf26617c CR3: 00000000bc87c000 CR4: 00000000000407e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process iscsid (pid: 8589, threadinfo ffff8800ae7e4000, task ffff880106002eb0)
Stack:
ffff88011af0c000 ffff88001ea0fff0 ffff8800ae7e5988 ffffffffa00aaafc
0000000000000286 ffff88001ea10000 ffff8800ae7e5968 ffff88008ae44a28
ffff88008ae44800 ffff88008ae44818 0000000000000000 0000000000000001
Call Trace:
[<ffffffffa00aaafc>] scsi_remove_target+0x1bc/0x1f0 [scsi_mod]
[<ffffffffa06af6c6>] __iscsi_unbind_session+0xc6/0x1a0 [scsi_transport_iscsi]
[<ffffffffa06af8a5>] iscsi_remove_session+0x105/0x1e0 [scsi_transport_iscsi]
[<ffffffffa06af996>] iscsi_destroy_session+0x16/0x60 [scsi_transport_iscsi]
[<ffffffffa07bc549>] iscsi_session_teardown+0xa9/0xd0 [libiscsi]
[<ffffffffa07c91a0>] iscsi_sw_tcp_session_destroy+0x50/0x70 [iscsi_tcp]
[<ffffffffa06aeef8>] iscsi_if_rx+0xab8/0xf60 [scsi_transport_iscsi]
[<ffffffff81350cad>] netlink_unicast+0x1ad/0x230
[<ffffffff8135102b>] netlink_sendmsg+0x2fb/0x350
[<ffffffff8131c458>] ? sock_update_classid+0xc8/0x140
[<ffffffff813162d2>] sock_sendmsg+0xa2/0xe0
[<ffffffff8111c9ac>] ? might_fault+0x9c/0xb0
[<ffffffff8111c963>] ? might_fault+0x53/0xb0
[<ffffffff81325356>] ? verify_iovec+0x56/0xd0
[<ffffffff81317ac2>] __sys_sendmsg+0x382/0x390
[<ffffffff8111c9ac>] ? might_fault+0x9c/0xb0
[<ffffffff8111c963>] ? might_fault+0x53/0xb0
[<ffffffff81069c63>] ? lg_local_unlock+0x23/0x50
[<ffffffff811501f6>] ? cp_new_stat+0x116/0x130
[<ffffffff813198f9>] sys_sendmsg+0x49/0x90
[<ffffffff81415d52>] system_call_fastpath+0x16/0x1b
Bart.
prev parent reply other threads:[~2012-08-24 17:48 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-24 13:13 Kernel hangs in truncate_inode_pages() Bart Van Assche
2012-08-24 17:24 ` Mike Christie
2012-08-24 17:47 ` Bart Van Assche [this message]
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=5037BE4C.80609@acm.org \
--to=bvanassche@acm.org \
--cc=axboe@kernel.dk \
--cc=linux-kernel@vger.kernel.org \
--cc=michaelc@cs.wisc.edu \
--cc=tj@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox