From: Andrea Arcangeli <andrea@suse.de>
To: Linus Torvalds <torvalds@transmeta.com>
Cc: Roman Zippel <zippel@fh-brandenburg.de>,
"Eric W. Biederman" <ebiederman@uswest.net>,
Alexander Viro <viro@math.psu.edu>,
Daniel Phillips <phillips@innominate.de>,
linux-kernel@vger.kernel.org
Subject: Re: [RFC] Generic deferred file writing
Date: Sun, 31 Dec 2000 17:50:04 +0100 [thread overview]
Message-ID: <20001231175004.A8027@athlon.random> (raw)
In-Reply-To: <20001231153849.B17728@athlon.random> <Pine.LNX.4.10.10012310812500.3084-100000@penguin.transmeta.com>
In-Reply-To: <Pine.LNX.4.10.10012310812500.3084-100000@penguin.transmeta.com>; from torvalds@transmeta.com on Sun, Dec 31, 2000 at 08:33:01AM -0800
On Sun, Dec 31, 2000 at 08:33:01AM -0800, Linus Torvalds wrote:
> By doing a better job of caching stuff.
Caching can happen after we are been slow and we waited for I/O synchronously
the first time (bread).
How can we optimize the first time (when the indirect blocks are out of buffer
cache) without changing the on-disk format? We can't as far I can see.
It's of course fine to optimize the address_space->physical_block resolver
algorithm, because it has to run anyways if we want to write such data to disk
eventually (despite it's asynchronous with allocate on flush, or synchronous
like now). Probably it's a more sensible optimization than the allocate
on flush thing. But still being able to run the resolver in an asynchronous
manner, in parallel, only at the time we need to flush the page to disk, looks
nicer behaviour to me.
Andrea
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
next prev parent reply other threads:[~2000-12-31 17:21 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2000-12-30 0:25 test13-pre6 Linus Torvalds
2000-12-30 0:49 ` test13-pre6 Alexander Viro
2000-12-30 1:03 ` test13-pre6 Linus Torvalds
2000-12-30 18:09 ` test13-pre6 Alexander Viro
2000-12-30 2:25 ` test13-pre6 Daniel Phillips
2000-12-30 3:16 ` test13-pre6 Linus Torvalds
2000-12-30 18:58 ` [RFC] Generic deferred file writing Daniel Phillips
2000-12-30 20:05 ` Linus Torvalds
2000-12-30 20:06 ` Alexander Viro
2000-12-30 20:21 ` Linus Torvalds
2000-12-30 21:10 ` Andreas Dilger
2000-12-30 21:46 ` Alexander Viro
2000-12-30 23:12 ` Daniel Phillips
2000-12-30 22:00 ` Eric W. Biederman
2000-12-30 22:44 ` Linus Torvalds
2000-12-31 0:26 ` Eric W. Biederman
2000-12-31 1:02 ` Andrea Arcangeli
2000-12-31 1:13 ` Chris Wedgwood
2000-12-31 1:50 ` Alexander Viro
2000-12-31 2:34 ` Andrea Arcangeli
2000-12-31 2:09 ` Roman Zippel
2000-12-31 2:28 ` Linus Torvalds
2000-12-31 12:58 ` Roman Zippel
2001-04-21 20:06 ` Races in affs_unlink(), affs_rmdir() and affs_rename() Alexander Viro
2001-04-21 22:16 ` Roman Zippel
2001-04-22 5:53 ` Alexander Viro
2001-04-22 12:57 ` Roman Zippel
2001-04-22 13:15 ` Alexander Viro
2000-12-31 14:38 ` [RFC] Generic deferred file writing Andrea Arcangeli
2000-12-31 16:33 ` Linus Torvalds
2000-12-31 16:50 ` Andrea Arcangeli [this message]
2000-12-31 16:51 ` Alexander Viro
2000-12-31 17:12 ` Linus Torvalds
2000-12-31 18:30 ` Daniel Phillips
2000-12-31 18:44 ` Linus Torvalds
2000-12-31 19:10 ` Daniel Phillips
2000-12-31 19:31 ` Linus Torvalds
2000-12-31 21:03 ` Roman Zippel
2000-12-31 21:32 ` Linus Torvalds
2001-01-02 18:27 ` Chris Mason
2000-12-30 3:08 ` test13-pre6 (Fork Bug with Athlons? Temporary Fix) Byron Stanoszek
2000-12-30 3:36 ` Linus Torvalds
2000-12-30 5:55 ` Andi Kleen
2000-12-30 5:13 ` Linus Torvalds
2000-12-30 8:13 ` Graham Murray
2000-12-30 4:21 ` test13-pre6 Dan Aloni
2001-01-04 20:23 ` test13-pre6 Stephen C. Tweedie
2001-01-04 22:15 ` test13-pre6 stewart
[not found] <Pine.LNX.4.10.10012311726230.1671-100000@penguin.transmeta.com>
2001-01-01 2:50 ` [RFC] Generic deferred file writing Roman Zippel
2001-01-01 3:47 ` Alexander Viro
2001-01-01 12:44 ` Roman Zippel
2001-01-01 15:16 ` Alexander Viro
2001-01-02 3:00 ` Roman Zippel
2001-01-02 5:00 ` Alexander Viro
2001-01-02 16:53 ` Roman Zippel
2001-01-01 20:00 ` Daniel Phillips
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=20001231175004.A8027@athlon.random \
--to=andrea@suse.de \
--cc=ebiederman@uswest.net \
--cc=linux-kernel@vger.kernel.org \
--cc=phillips@innominate.de \
--cc=torvalds@transmeta.com \
--cc=viro@math.psu.edu \
--cc=zippel@fh-brandenburg.de \
/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