From: Avi Kivity <avi@redhat.com>
To: "Ted Ts'o" <tytso@mit.edu>, Christoph Hellwig <hch@infradead.org>,
Ric Wheeler <rwheeler@redhat.com>, Mingming Cao <cmm@us.ibm.com>,
djwong@us.ibm.com, linux-ext4 <linux-ext4@vger.ker
Subject: Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages.
Date: Thu, 05 Aug 2010 05:20:12 +0300 [thread overview]
Message-ID: <4C5A1FDC.3010700@redhat.com> (raw)
In-Reply-To: <20100804233206.GA2901@thunk.org>
On 08/05/2010 02:32 AM, Ted Ts'o wrote:
> On Tue, Aug 03, 2010 at 04:24:49PM +0300, Avi Kivity wrote:
>> On 06/30/2010 03:48 PM, tytso@mit.edu wrote:
>>> I wonder if it's worthwhile to think about a new system call which
>>> allows users to provide an array of fd's which are collectively should
>>> be fsync'ed out at the same time. Otherwise, we end up issuing
>>> multiple barrier operations in cases where the application needs to
>>> do:
>>>
>>> fsync(control_fd);
>>> fsync(data_fd);
>>>
>> The system call exists, it's called io_submit().
> Um, not the same thing at all.
Why not? To be clear, I'm talking about an io_submit() with multiple
IO_CMD_FSYNC requests, with a kernel implementation that is able to
batch these requests.
--
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.
WARNING: multiple messages have this Message-ID (diff)
From: Avi Kivity <avi@redhat.com>
To: "Ted Ts'o" <tytso@mit.edu>, Christoph Hellwig <hch@infradead.org>,
Ric Wheeler <rwheeler@redhat.com>, Mingming Cao <cmm@us.ibm.com>,
djwong@us.ibm.com, linux-ext4 <linux-ext4@vger.kernel.org>,
linux-kernel <linux-kernel@vger.kernel.org>,
Keith Mannthey <kmannth@us.ibm.com>,
Mingming Cao <mcao@us.ibm.com>
Subject: Re: [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages.
Date: Thu, 05 Aug 2010 05:20:12 +0300 [thread overview]
Message-ID: <4C5A1FDC.3010700@redhat.com> (raw)
In-Reply-To: <20100804233206.GA2901@thunk.org>
On 08/05/2010 02:32 AM, Ted Ts'o wrote:
> On Tue, Aug 03, 2010 at 04:24:49PM +0300, Avi Kivity wrote:
>> On 06/30/2010 03:48 PM, tytso@mit.edu wrote:
>>> I wonder if it's worthwhile to think about a new system call which
>>> allows users to provide an array of fd's which are collectively should
>>> be fsync'ed out at the same time. Otherwise, we end up issuing
>>> multiple barrier operations in cases where the application needs to
>>> do:
>>>
>>> fsync(control_fd);
>>> fsync(data_fd);
>>>
>> The system call exists, it's called io_submit().
> Um, not the same thing at all.
Why not? To be clear, I'm talking about an io_submit() with multiple
IO_CMD_FSYNC requests, with a kernel implementation that is able to
batch these requests.
--
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.
next prev parent reply other threads:[~2010-08-05 2:20 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-29 23:51 [RFC] ext4: Don't send extra barrier during fsync if there are no dirty pages Darrick J. Wong
2010-05-04 0:57 ` Mingming Cao
2010-05-04 14:16 ` Ric Wheeler
2010-05-04 15:45 ` Christoph Hellwig
2010-06-30 12:48 ` tytso
2010-06-30 13:21 ` Ric Wheeler
2010-06-30 13:21 ` Ric Wheeler
2010-06-30 13:44 ` tytso
2010-06-30 13:54 ` Ric Wheeler
2010-06-30 13:54 ` Ric Wheeler
2010-06-30 19:05 ` Andreas Dilger
2010-07-21 17:16 ` Jan Kara
2010-07-21 17:16 ` Jan Kara
2010-08-03 0:09 ` Darrick J. Wong
2010-08-03 9:01 ` Christoph Hellwig
2010-08-04 18:16 ` Darrick J. Wong
2010-08-03 13:21 ` Jan Kara
2010-08-03 13:24 ` Avi Kivity
2010-08-03 13:24 ` Avi Kivity
2010-08-04 23:32 ` Ted Ts'o
2010-08-05 2:20 ` Avi Kivity [this message]
2010-08-05 2:20 ` Avi Kivity
2010-08-05 16:17 ` Ted Ts'o
2010-08-05 19:13 ` Jeff Moyer
2010-08-05 20:39 ` Ted Ts'o
2010-08-05 20:44 ` Jeff Moyer
2010-05-04 19:49 ` Mingming Cao
2010-06-29 20:51 ` [RFC v2] " Darrick J. Wong
2010-08-05 16:40 ` Ted Ts'o
2010-08-05 16:45 ` Ted Ts'o
2010-08-05 16:45 ` Ted Ts'o
2010-08-06 7:04 ` Darrick J. Wong
2010-08-06 7:04 ` Darrick J. Wong
2010-08-06 10:17 ` Ric Wheeler
2010-08-09 19:53 ` [RFC v3] ext4: Combine barrier requests coming from fsync Darrick J. Wong
2010-08-09 19:53 ` Darrick J. Wong
2010-08-09 21:07 ` Christoph Hellwig
2010-08-16 16:14 ` Darrick J. Wong
2010-08-19 2:07 ` Darrick J. Wong
2010-08-19 8:53 ` Christoph Hellwig
2010-08-19 9:17 ` Tejun Heo
2010-08-19 15:48 ` Tejun Heo
2010-08-09 21:19 ` Andreas Dilger
2010-08-09 23:38 ` Darrick J. Wong
2010-08-19 2:14 ` [RFC v4] ext4: Coordinate fsync requests Darrick J. Wong
2010-08-23 18:31 ` Performance testing of various barrier reduction patches [was: Re: [RFC v4] ext4: Coordinate fsync requests] Darrick J. Wong
2010-09-23 23:25 ` Darrick J. Wong
2010-09-24 6:24 ` Andreas Dilger
2010-09-24 11:44 ` Ric Wheeler
2010-09-27 23:01 ` Darrick J. Wong
2010-10-08 21:26 ` Darrick J. Wong
2010-10-08 21:56 ` Ric Wheeler
2010-10-11 20:20 ` Darrick J. Wong
2010-10-12 14:14 ` Christoph Hellwig
2010-10-15 23:39 ` Darrick J. Wong
2010-10-15 23:40 ` Christoph Hellwig
2010-10-16 0:02 ` Darrick J. Wong
2010-10-11 14:33 ` Ted Ts'o
2010-10-18 22:49 ` Darrick J. Wong
2010-10-19 18:28 ` Christoph Hellwig
2010-08-06 7:13 ` [RFC v2] ext4: Don't send extra barrier during fsync if there are no dirty pages Darrick J. Wong
2010-08-06 7:13 ` Darrick J. Wong
2010-08-06 18:04 ` Ted Ts'o
2010-08-09 19:36 ` Darrick J. Wong
2010-08-09 19:36 ` Darrick J. Wong
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=4C5A1FDC.3010700@redhat.com \
--to=avi@redhat.com \
--cc=cmm@us.ibm.com \
--cc=djwong@us.ibm.com \
--cc=hch@infradead.org \
--cc=linux-ext4@vger.ker \
--cc=rwheeler@redhat.com \
--cc=tytso@mit.edu \
/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.