From: Tejun Heo <tj@kernel.org>
To: Mike Snitzer <snitzer@redhat.com>
Cc: jaxboe@fusionio.com, k-ueda@ct.jp.nec.com,
j-nomura@ce.jp.nec.com, jamie@shareable.org,
linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-raid@vger.kernel.org, hch@lst.de, dm-devel@redhat.com
Subject: Re: [PATCH 4/5] dm: implement REQ_FLUSH/FUA support for request-based dm
Date: Tue, 31 Aug 2010 12:29:59 +0200 [thread overview]
Message-ID: <4C7CD9A7.4030901@kernel.org> (raw)
In-Reply-To: <20100830212819.GA12522@redhat.com>
On 08/30/2010 11:28 PM, Mike Snitzer wrote:
> On Mon, Aug 30 2010 at 3:08pm -0400,
> Mike Snitzer <snitzer@redhat.com> wrote:
>
>> On Mon, Aug 30 2010 at 11:07am -0400,
>> Tejun Heo <tj@kernel.org> wrote:
>>
>>> On 08/30/2010 03:59 PM, Tejun Heo wrote:
>>>> Ah... that's probably from "if (!elv_queue_empty(q))" check below,
>>>> flushes are on a separate queue but I forgot to update
>>>> elv_queue_empty() to check the flush queue. elv_queue_empty() can
>>>> return %true spuriously in which case the queue won't be plugged and
>>>> restarted later leading to queue hang. I'll fix elv_queue_empty().
>>>
>>> I think I was too quick to blame elv_queue_empty(). Can you please
>>> test whether the following patch fixes the hang?
>>
>> It does, thanks!
>
> Hmm, but unfortunately I was too quick to say the patch fixed the hang.
>
> It is much more rare, but I can still get a hang. I just got the
> following running vgcreate against an DM mpath (rq-based) device:
Can you please try this one instead?
Thanks.
---
block/blk-flush.c | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
Index: block/block/blk-flush.c
===================================================================
--- block.orig/block/blk-flush.c
+++ block/block/blk-flush.c
@@ -56,22 +56,38 @@ static struct request *blk_flush_complet
return next_rq;
}
+static void blk_flush_complete_seq_end_io(struct request_queue *q,
+ unsigned seq, int error)
+{
+ bool was_empty = elv_queue_empty(q);
+ struct request *next_rq;
+
+ next_rq = blk_flush_complete_seq(q, seq, error);
+
+ /*
+ * Moving a request silently to empty queue_head may stall the
+ * queue. Kick the queue in those cases.
+ */
+ if (next_rq && was_empty)
+ __blk_run_queue(q);
+}
+
static void pre_flush_end_io(struct request *rq, int error)
{
elv_completed_request(rq->q, rq);
- blk_flush_complete_seq(rq->q, QUEUE_FSEQ_PREFLUSH, error);
+ blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_PREFLUSH, error);
}
static void flush_data_end_io(struct request *rq, int error)
{
elv_completed_request(rq->q, rq);
- blk_flush_complete_seq(rq->q, QUEUE_FSEQ_DATA, error);
+ blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_DATA, error);
}
static void post_flush_end_io(struct request *rq, int error)
{
elv_completed_request(rq->q, rq);
- blk_flush_complete_seq(rq->q, QUEUE_FSEQ_POSTFLUSH, error);
+ blk_flush_complete_seq_end_io(rq->q, QUEUE_FSEQ_POSTFLUSH, error);
}
static void init_flush_request(struct request *rq, struct gendisk *disk)
--
tejun
next prev parent reply other threads:[~2010-08-31 10:29 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-30 9:58 [PATCHSET 2.6.36-rc2] block, dm: finish REQ_FLUSH/FUA conversion, take#2 Tejun Heo
2010-08-30 9:58 ` [PATCH 1/5] block: make __blk_rq_prep_clone() copy most command flags Tejun Heo
2010-09-01 15:30 ` Christoph Hellwig
2010-08-30 9:58 ` [PATCH 2/5] dm: implement REQ_FLUSH/FUA support for bio-based dm Tejun Heo
2010-09-01 13:43 ` Mike Snitzer
2010-09-01 13:50 ` Tejun Heo
2010-09-01 13:54 ` Mike Snitzer
2010-09-01 13:56 ` Tejun Heo
2010-08-30 9:58 ` [PATCH 3/5] dm: relax ordering of bio-based flush implementation Tejun Heo
2010-09-01 13:51 ` Mike Snitzer
2010-09-01 13:56 ` Tejun Heo
2010-09-03 6:04 ` Kiyoshi Ueda
2010-09-03 9:42 ` Tejun Heo
2010-08-30 9:58 ` [PATCH 4/5] dm: implement REQ_FLUSH/FUA support for request-based dm Tejun Heo
2010-08-30 13:28 ` Mike Snitzer
2010-08-30 13:59 ` Tejun Heo
2010-08-30 15:07 ` Tejun Heo
2010-08-30 19:08 ` Mike Snitzer
2010-08-30 21:28 ` Mike Snitzer
2010-08-31 10:29 ` Tejun Heo [this message]
2010-08-31 13:02 ` Mike Snitzer
2010-08-31 13:14 ` Tejun Heo
2010-08-30 15:42 ` [PATCH] block: initialize flush request with WRITE_FLUSH instead of REQ_FLUSH Tejun Heo
2010-08-30 15:45 ` [PATCH UPDATED 4/5] dm: implement REQ_FLUSH/FUA support for request-based dm Tejun Heo
2010-08-30 19:18 ` Mike Snitzer
2010-09-01 7:15 ` Kiyoshi Ueda
2010-09-01 12:25 ` Mike Snitzer
2010-09-02 13:22 ` Tejun Heo
2010-09-02 13:32 ` Tejun Heo
2010-09-03 5:46 ` Kiyoshi Ueda
2010-09-02 17:43 ` [PATCH] block: make sure FSEQ_DATA request has the same rq_disk as the original Tejun Heo
2010-09-03 5:47 ` Kiyoshi Ueda
2010-09-03 9:33 ` Tejun Heo
2010-09-03 10:28 ` Kiyoshi Ueda
2010-09-03 11:42 ` Tejun Heo
2010-09-03 11:51 ` Kiyoshi Ueda
2010-08-30 9:58 ` [PATCH 5/5] block: remove the WRITE_BARRIER flag Tejun Heo
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=4C7CD9A7.4030901@kernel.org \
--to=tj@kernel.org \
--cc=dm-devel@redhat.com \
--cc=hch@lst.de \
--cc=j-nomura@ce.jp.nec.com \
--cc=jamie@shareable.org \
--cc=jaxboe@fusionio.com \
--cc=k-ueda@ct.jp.nec.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=snitzer@redhat.com \
/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;
as well as URLs for NNTP newsgroup(s).