From: "Eric D. Mudama" <edmudama@mail.bounceswoosh.org>
To: Jeff Garzik <jgarzik@pobox.com>
Cc: "Eric D. Mudama" <edmudama@mail.bounceswoosh.org>,
Jens Axboe <axboe@suse.de>,
linux-kernel@vger.kernel.org,
Bartlomiej Zolnierkiewicz <B.Zolnierkiewicz@elka.pw.edu.pl>,
Ed Tomlinson <edt@aei.ca>, Andrew Morton <akpm@osdl.org>
Subject: Re: flush cache range proposal (was Re: ide errors in 7-rc1-mm1 and later)
Date: Fri, 11 Jun 2004 10:52:24 -0600 [thread overview]
Message-ID: <20040611165224.GA11945@bounceswoosh.org> (raw)
In-Reply-To: <40C9DE7F.8040002@pobox.com>
On Fri, Jun 11 at 12:31, Jeff Garzik wrote:
>If queued-FUA is out of the question, this seems quite reasonable. It
>appears to achieve the commit-block semantics described for barrier
>operation, AFAICS.
Queued FUA shouldn't be out of the question.
However, Queued FUA requires waiting for the queue to drain before
sending more commands, since a pair of queued FUA commands doesn't
guarantee the ordering of those two commands, which may or may not be
acceptable semantics.
The barrier operation is basically a queueing-friendly flush+FUA,
which may be better... it lets the driver keep the queue in the drive
full, and also allows writes other than the commit block to not be
done as FUA operations, which is potentially faster. THe bigger the
ratio of data to commit block, the better the performance would be
with a barrier operation vs a purely queued FUA workload.
--eric
--
Eric D. Mudama
edmudama@mail.bounceswoosh.org
next prev parent reply other threads:[~2004-06-11 16:52 UTC|newest]
Thread overview: 66+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-05-27 20:24 [2.6.7-rc1-mm1] cant mount reiserfs using -o barrier=flush Günther Persoons
2004-05-27 23:28 ` Ed Tomlinson
2004-05-28 11:54 ` Gunther Persoons
2004-05-28 12:18 ` Jens Axboe
2004-05-28 21:39 ` Ed Tomlinson
2004-05-29 8:30 ` Jens Axboe
2004-06-04 2:07 ` ide errors in 7-rc1-mm1 and later Ed Tomlinson
2004-06-04 2:31 ` Andrew Morton
2004-06-04 9:42 ` Jens Axboe
2004-06-04 11:22 ` Ed Tomlinson
2004-06-04 11:32 ` Jens Axboe
2004-06-04 11:45 ` Jens Axboe
2004-06-04 11:57 ` Bartlomiej Zolnierkiewicz
2004-06-04 12:01 ` Jens Axboe
2004-06-04 12:38 ` Bartlomiej Zolnierkiewicz
2004-06-04 12:47 ` Jens Axboe
2004-06-04 13:34 ` Bartlomiej Zolnierkiewicz
2004-06-04 15:23 ` Jens Axboe
2004-06-04 16:14 ` Bartlomiej Zolnierkiewicz
2004-06-05 9:18 ` Jens Axboe
2004-06-09 21:52 ` Bartlomiej Zolnierkiewicz
2004-06-09 22:06 ` Andrew Morton
2004-06-09 23:38 ` Bartlomiej Zolnierkiewicz
2004-06-09 23:50 ` Andrew Morton
2004-06-10 0:20 ` Bartlomiej Zolnierkiewicz
2004-06-10 0:37 ` Andrew Morton
2004-06-10 1:02 ` Bartlomiej Zolnierkiewicz
2004-06-10 0:28 ` Chris Mason
2004-06-10 0:38 ` Andrew Morton
2004-06-10 0:45 ` Bartlomiej Zolnierkiewicz
2004-06-10 15:14 ` Chris Mason
2004-06-10 15:15 ` Jens Axboe
2004-06-10 1:05 ` Bartlomiej Zolnierkiewicz
2004-06-10 6:27 ` Jens Axboe
2004-06-10 6:26 ` Jens Axboe
2004-06-04 17:29 ` Jeff Garzik
2004-06-05 9:24 ` Jens Axboe
2004-06-06 16:18 ` Eric D. Mudama
2004-06-06 20:46 ` Jens Axboe
2004-06-10 0:38 ` Bartlomiej Zolnierkiewicz
2004-06-10 6:11 ` Jens Axboe
2004-06-10 16:41 ` Eric D. Mudama
2004-06-10 17:50 ` flush cache range proposal (was Re: ide errors in 7-rc1-mm1 and later) Jeff Garzik
2004-06-10 18:02 ` Jeff Garzik
2004-06-10 20:33 ` Eric D. Mudama
2004-06-11 16:22 ` Jeff Garzik
2004-06-11 7:55 ` Jens Axboe
2004-06-11 16:17 ` Eric D. Mudama
2004-06-11 16:31 ` Jeff Garzik
2004-06-11 16:52 ` Eric D. Mudama [this message]
2004-06-11 16:58 ` Jens Axboe
2004-06-11 16:54 ` Jens Axboe
2004-06-11 16:50 ` Jens Axboe
2004-06-11 16:24 ` Jeff Garzik
2004-06-11 6:10 ` Stuart Young
2004-06-26 8:31 ` ide errors in 7-rc1-mm1 and later Andre Hedrick
2004-06-26 8:58 ` Andre Hedrick
2004-06-28 18:18 ` Eric D. Mudama
2004-07-02 8:29 ` Jens Axboe
2004-07-07 5:40 ` Jeff Garzik
2004-06-04 11:48 ` Bartlomiej Zolnierkiewicz
2004-06-09 23:44 ` Ed Tomlinson
2004-06-09 23:52 ` Andrew Morton
2004-06-10 0:17 ` Ed Tomlinson
2004-06-10 6:29 ` Jens Axboe
2004-06-14 21:42 ` Ed Tomlinson
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=20040611165224.GA11945@bounceswoosh.org \
--to=edmudama@mail.bounceswoosh.org \
--cc=B.Zolnierkiewicz@elka.pw.edu.pl \
--cc=akpm@osdl.org \
--cc=axboe@suse.de \
--cc=edt@aei.ca \
--cc=jgarzik@pobox.com \
--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 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.