public inbox for linux-block@vger.kernel.org
 help / color / mirror / Atom feed
From: Joseph Qi <jiangqi903@gmail.com>
To: Shaohua Li <shli@kernel.org>
Cc: linux-block <linux-block@vger.kernel.org>,
	Jens Axboe <axboe@kernel.dk>, Shaohua Li <shli@fb.com>,
	boyu.mt@taobao.com, wenqing.lz@taobao.com,
	qijiang.qj@alibaba-inc.com
Subject: Re: [PATCH] blk-throttle: fix possible io stall when doing upgrade
Date: Tue, 26 Sep 2017 09:06:57 +0800	[thread overview]
Message-ID: <5216fe6f-deb2-8db3-a241-46f95c999a7e@gmail.com> (raw)
In-Reply-To: <20170925172228.n2soitn5vj53ln36@kernel.org>

Hi Shaohua,

On 17/9/26 01:22, Shaohua Li wrote:
> On Mon, Sep 25, 2017 at 06:46:42PM +0800, Joseph Qi wrote:
>> From: Joseph Qi <qijiang.qj@alibaba-inc.com>
>>
>> Currently it will try to dispatch bio in throtl_upgrade_state. This may
>> lead to io stall in the following case.
>> Say the hierarchy is like:
>> /-test1
>>   |-subtest1
>> and subtest1 has 32 queued bios now.
>>
>> throtl_pending_timer_fn            throtl_upgrade_state
>> ------------------------------------------------------------------------
>>                                    upgrade to max
>>                                    throtl_select_dispatch
>>                                    throtl_schedule_next_dispatch
>> throtl_select_dispatch
>> throtl_schedule_next_dispatch
>>
>> Since throtl_select_dispatch will move queued bios from subtest1 to
>> test1 in throtl_upgrade_state, it will then just do nothing in
>> throtl_pending_timer_fn. As a result, queued bios won't be dispatched
>> any more if no proper timer scheduled.
> 
> Sorry, didn't get it. If throtl_pending_timer_fn does nothing (because
> throtl_upgrade_state already moves bios to parent), there is no pending
> blkcg/bio, not rearming the timer wouldn't lose anything. Am I missing
> anything? could you please describe the failure in details?
> 
> Thanks,
> Shaohua
>In normal case, throtl_pending_timer_fn tries to move bios from
subtest1 to test1, and finally do the real issueing work when reach
the top-level.
But int the case above, throtl_select_dispatch in
throtl_pending_timer_fn returns 0, because the work is done by
throtl_upgrade_state. Then throtl_pending_timer_fn *thinks* there is
nothing to do, but the queued bios are still in service queue of
test1.
Since both throtl_pending_timer_fn and throtl_upgrade_state won't
handle the queued bios, io stall happens.

Thanks,
Joseph

  reply	other threads:[~2017-09-26  1:06 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-25 10:46 [PATCH] blk-throttle: fix possible io stall when doing upgrade Joseph Qi
2017-09-25 17:22 ` Shaohua Li
2017-09-26  1:06   ` Joseph Qi [this message]
2017-09-26  2:48     ` Shaohua Li
2017-09-26  3:16       ` Joseph Qi
2017-09-27 21:38         ` Shaohua Li
2017-09-28  3:48           ` Joseph Qi
2017-09-28 11:19             ` Joseph Qi
2017-09-28 21:18               ` Shaohua Li

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=5216fe6f-deb2-8db3-a241-46f95c999a7e@gmail.com \
    --to=jiangqi903@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=boyu.mt@taobao.com \
    --cc=linux-block@vger.kernel.org \
    --cc=qijiang.qj@alibaba-inc.com \
    --cc=shli@fb.com \
    --cc=shli@kernel.org \
    --cc=wenqing.lz@taobao.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