All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: Ming Lei <tom.leiming@gmail.com>
Cc: Jiale Li <aaronlee0817@163.com>, Jens Axboe <axboe@kernel.dk>,
	Ming Lin <mlin@kernel.org>, Shaohua Li <shli@kernel.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
	cgroup@vger.kernel.org, jiale0817.li@samsung.com,
	yanzi.zhang@samsung.com, zhen1.zhang@samsung.com,
	linux-block <linux-block@vger.kernel.org>
Subject: Re: cgroup: Fix split bio been throttled more than once
Date: Wed, 6 Jul 2016 10:09:19 -0400	[thread overview]
Message-ID: <20160706140919.GH3262@mtj.duckdns.org> (raw)
In-Reply-To: <CACVXFVPO-7EEK02SUH16NtnwpE807KuYQHybBYYqVbXGZSzX2A@mail.gmail.com>

Hello, Ming.

On Wed, Jul 06, 2016 at 09:10:00AM +0800, Ming Lei wrote:
> > Then we did some research and find that in kernel version 4.3 brought in
> > blk_queue_split() function to split the big size bio into several parts,
> > and some of them are calling the generic_make_request() again, this result
> > the bio been throttled more than once. so the actual bio sent to device is
> > less than we expected.
> 
> Except for blk_queue_split(), there are other(stacked) drivers which call
> generic_make_request() too, such as drbd, dm, md and bcache.

So, blk-throtl already uses REQ_THROTTLED to avoid throttling the same
bio multiple times.  The problem seems that the flag isn't maintained
through clone.

> >
> > We have checked the newest kernel of 4.7-rc5, this problem is still exist.
> >
> > Based on this kind of situation, we propose a fix solution to add a flag bit
> > in bio to let the splited bio bypass the blk_queue_split(). Below is the patch
> > we used to fix this problem.
> 
> The splitted bio is just a fast-cloned bio(except for discard bio) and not very
> special compared with other fast-cloned bio, which is quite common used.
> 
> So I guess what you need is to bypass BIO_CLONED bio for this purpose
> since all fast-cloned bio shares the same bvec table of the source bio.

Depending on how a device handles a bio, that could allow bios to
bypass throttling entirely, no?  Wouldn't adding REQ_THROTTLED to
REQ_CLONE_MASK work?

Thanks.

-- 
tejun

  reply	other threads:[~2016-07-06 14:09 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-07-04 14:46 cgroup: Fix split bio been throttled more than once Jiale Li
2016-07-05 22:26 ` Tejun Heo
2016-07-06  1:14   ` Ming Lei
2016-07-06 14:58   ` aaronlee0817
2016-07-06 15:06     ` Tejun Heo
2016-07-06 15:17       ` aaronlee0817
2016-07-06 15:39       ` Ming Lei
2016-07-06 15:39         ` Ming Lei
2016-07-06  1:10 ` Ming Lei
2016-07-06 14:09   ` Tejun Heo [this message]
2016-07-06 14:53     ` Ming Lei
2016-07-07 13:48     ` aaronlee0817
2016-07-08 10:35       ` Ming Lei
2016-07-08 10:35         ` Ming Lei
2016-07-09 14:53         ` Tejun Heo
2016-07-10  8:58           ` Ming Lei
2016-07-06 14:57   ` aaronlee0817

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=20160706140919.GH3262@mtj.duckdns.org \
    --to=tj@kernel.org \
    --cc=aaronlee0817@163.com \
    --cc=axboe@kernel.dk \
    --cc=cgroup@vger.kernel.org \
    --cc=jiale0817.li@samsung.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mlin@kernel.org \
    --cc=shli@kernel.org \
    --cc=tom.leiming@gmail.com \
    --cc=yanzi.zhang@samsung.com \
    --cc=zhen1.zhang@samsung.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 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.