linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jaegeuk Kim <jaegeuk@kernel.org>
To: Christoph Hellwig <hch@infradead.org>
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-f2fs-devel@lists.sourceforge.net
Subject: Re: [PATCH 5/6] f2fs: add a kernel thread to issue discard commands asynchronously
Date: Fri, 13 Jan 2017 11:12:11 -0800	[thread overview]
Message-ID: <20170113191211.GB1301@jaegeuk.local> (raw)
In-Reply-To: <20170113080159.GB31777@infradead.org>

On 01/13, Christoph Hellwig wrote:
> On Thu, Jan 12, 2017 at 02:44:06PM -0800, Jaegeuk Kim wrote:
> > This patch adds a kernel thread to issue discard commands.
> > It proposes three states, D_PREP, D_SUBMIT, and D_DONE to identify current
> > bio status.
> 
> Why?  Instead of creating the complexity of a thread you should look
> into issuing the discard bios asynchronously, which should help to
> simplify a lot of the discard logic in f2fs.

Previously, I've done to issue discard bios asynchronously. But the problem that
I've got is that was not enough. When testing nvme SSD with noop IO scheduler,
submit_bio() was blocked at every 8 async discard bios, resulting in very slow
checkpoint process which blocks most of other FS operations.

Thanks,

  reply	other threads:[~2017-01-13 19:12 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-12 22:44 [PATCH 1/6] f2fs: clean up flush/discard command namings Jaegeuk Kim
2017-01-12 22:44 ` [PATCH 2/6] f2fs: reorganize stat information Jaegeuk Kim
2017-02-22  9:40   ` [f2fs-dev] " Chao Yu
2017-01-12 22:44 ` [PATCH 3/6] f2fs: remove batched discard in f2fs_trim_fs Jaegeuk Kim
2017-02-22  9:40   ` Chao Yu
2017-02-22 21:55     ` [f2fs-dev] " Jaegeuk Kim
2017-02-23  2:19       ` Chao Yu
2017-02-23  4:25         ` Jaegeuk Kim
2017-01-12 22:44 ` [PATCH 4/6] f2fs: factor out discard command info into discard_cmd_control Jaegeuk Kim
2017-02-22  9:40   ` Chao Yu
2017-01-12 22:44 ` [PATCH 5/6] f2fs: add a kernel thread to issue discard commands asynchronously Jaegeuk Kim
2017-01-13  8:01   ` Christoph Hellwig
2017-01-13 19:12     ` Jaegeuk Kim [this message]
2017-01-16 17:32       ` Christoph Hellwig
2017-02-05  8:59         ` Christoph Hellwig
2017-02-07  3:44           ` Jaegeuk Kim
2017-02-08 16:02             ` Christoph Hellwig
2017-02-08 22:05               ` Jaegeuk Kim
2017-02-22  9:40   ` Chao Yu
2017-01-12 22:44 ` [PATCH 6/6] f2fs: show # of on-going flush and discard bios Jaegeuk Kim
2017-01-14  2:26   ` [f2fs-dev] " heyunlei
2017-01-14  7:27   ` heyunlei
2017-01-14 23:32   ` [PATCH 6/6 v2] " Jaegeuk Kim
2017-02-22  9:40   ` [f2fs-dev] [PATCH 6/6] " Chao Yu
2017-02-22  9:40 ` [f2fs-dev] [PATCH 1/6] f2fs: clean up flush/discard command namings Chao Yu

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=20170113191211.GB1301@jaegeuk.local \
    --to=jaegeuk@kernel.org \
    --cc=hch@infradead.org \
    --cc=linux-f2fs-devel@lists.sourceforge.net \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@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 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).