From: Christoph Hellwig <hch@lst.de>
To: Dave Chinner <david@fromorbit.com>
Cc: kernel test robot <ying.huang@linux.intel.com>,
LKML <linux-kernel@vger.kernel.org>,
xfs@oss.sgi.com, Dave Chinner <dchinner@redhat.com>,
lkp@01.org, Christoph Hellwig <hch@lst.de>
Subject: Re: [lkp] [xfs] fbcc025613: -5.6% fsmark.files_per_sec
Date: Mon, 22 Feb 2016 09:54:09 +0100 [thread overview]
Message-ID: <20160222085409.GA19493@lst.de> (raw)
In-Reply-To: <20160219064932.GX14668@dastard>
On Fri, Feb 19, 2016 at 05:49:32PM +1100, Dave Chinner wrote:
> That doesn't really seem right. The writeback should be done as a
> single ioend, with a single completion, with a single setsize
> transaction, adn then all the pages are marked clean sequentially.
> The above behaviour implies we are ending up doing something like:
>
> fsync proc io completion
> wait on page 0
> end page 0 writeback
> wake up page 0
> wait on page 1
> end page 1 writeback
> wake up page 1
> wait on page 2
> end page 2 writeback
> wake up page 2
>
> Though in slightly larger batches than a single page (10 wakeups a
> file, so batches of around 100 pages per wakeup?). i.e. the fsync
> IO wait appears to be racing with IO completion marking pages as
> done. I simply cannot see how the above change would cause that, as
> it was simply a change in the IO submission code that doesn't affect
> overall size or shape of the IOs being submitted.
Could this be the lack of blk plugs, which will cause us to complete
too early?
_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: lkp@lists.01.org
Subject: Re: [xfs] fbcc025613: -5.6% fsmark.files_per_sec
Date: Mon, 22 Feb 2016 09:54:09 +0100 [thread overview]
Message-ID: <20160222085409.GA19493@lst.de> (raw)
In-Reply-To: <20160219064932.GX14668@dastard>
[-- Attachment #1: Type: text/plain, Size: 1059 bytes --]
On Fri, Feb 19, 2016 at 05:49:32PM +1100, Dave Chinner wrote:
> That doesn't really seem right. The writeback should be done as a
> single ioend, with a single completion, with a single setsize
> transaction, adn then all the pages are marked clean sequentially.
> The above behaviour implies we are ending up doing something like:
>
> fsync proc io completion
> wait on page 0
> end page 0 writeback
> wake up page 0
> wait on page 1
> end page 1 writeback
> wake up page 1
> wait on page 2
> end page 2 writeback
> wake up page 2
>
> Though in slightly larger batches than a single page (10 wakeups a
> file, so batches of around 100 pages per wakeup?). i.e. the fsync
> IO wait appears to be racing with IO completion marking pages as
> done. I simply cannot see how the above change would cause that, as
> it was simply a change in the IO submission code that doesn't affect
> overall size or shape of the IOs being submitted.
Could this be the lack of blk plugs, which will cause us to complete
too early?
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Hellwig <hch@lst.de>
To: Dave Chinner <david@fromorbit.com>
Cc: kernel test robot <ying.huang@linux.intel.com>,
Dave Chinner <dchinner@redhat.com>,
lkp@01.org, LKML <linux-kernel@vger.kernel.org>,
Christoph Hellwig <hch@lst.de>,
xfs@oss.sgi.com
Subject: Re: [lkp] [xfs] fbcc025613: -5.6% fsmark.files_per_sec
Date: Mon, 22 Feb 2016 09:54:09 +0100 [thread overview]
Message-ID: <20160222085409.GA19493@lst.de> (raw)
In-Reply-To: <20160219064932.GX14668@dastard>
On Fri, Feb 19, 2016 at 05:49:32PM +1100, Dave Chinner wrote:
> That doesn't really seem right. The writeback should be done as a
> single ioend, with a single completion, with a single setsize
> transaction, adn then all the pages are marked clean sequentially.
> The above behaviour implies we are ending up doing something like:
>
> fsync proc io completion
> wait on page 0
> end page 0 writeback
> wake up page 0
> wait on page 1
> end page 1 writeback
> wake up page 1
> wait on page 2
> end page 2 writeback
> wake up page 2
>
> Though in slightly larger batches than a single page (10 wakeups a
> file, so batches of around 100 pages per wakeup?). i.e. the fsync
> IO wait appears to be racing with IO completion marking pages as
> done. I simply cannot see how the above change would cause that, as
> it was simply a change in the IO submission code that doesn't affect
> overall size or shape of the IOs being submitted.
Could this be the lack of blk plugs, which will cause us to complete
too early?
next prev parent reply other threads:[~2016-02-22 8:54 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-19 2:52 [xfs] fbcc025613: -5.6% fsmark.files_per_sec kernel test robot
2016-02-19 2:52 ` [lkp] " kernel test robot
2016-02-19 6:49 ` Dave Chinner
2016-02-19 6:49 ` Dave Chinner
2016-02-19 6:49 ` Dave Chinner
2016-02-22 8:54 ` Christoph Hellwig [this message]
2016-02-22 8:54 ` [lkp] " Christoph Hellwig
2016-02-22 8:54 ` Christoph Hellwig
2016-02-22 11:22 ` [lkp] " Dave Chinner
2016-02-22 11:22 ` Dave Chinner
2016-02-22 11:22 ` Dave Chinner
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=20160222085409.GA19493@lst.de \
--to=hch@lst.de \
--cc=david@fromorbit.com \
--cc=dchinner@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lkp@01.org \
--cc=xfs@oss.sgi.com \
--cc=ying.huang@linux.intel.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.