From: Daniel Phillips <phillips@bonn-fries.net>
To: Alexander Viro <viro@math.psu.edu>,
Richard Gooch <rgooch@ras.ucalgary.ca>
Cc: Linus Torvalds <torvalds@transmeta.com>,
Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: Getting FS access events
Date: Tue, 15 May 2001 12:33:35 +0200 [thread overview]
Message-ID: <01051512333507.24410@starship> (raw)
In-Reply-To: <Pine.GSO.4.21.0105150252171.19333-100000@weyl.math.psu.edu>
In-Reply-To: <Pine.GSO.4.21.0105150252171.19333-100000@weyl.math.psu.edu>
On Tuesday 15 May 2001 08:57, Alexander Viro wrote:
> On Tue, 15 May 2001, Richard Gooch wrote:
> > > What happens if you create a buffer cache entry? Does that
> > > invalidate the page cache one? Or do you just allow invalidates
> > > one way, and not the other? And why=
> >
> > I just figured on one way invalidates, because that seems cheap and
> > easy and has some benefits. Invalidating the other way is costly,
> > so don't bother, even if there were some benefits.
>
> Cute.
> * create an instance in pagecache
> * start reading into buffer cache (doesn't invalidate, right?)
> * start writing using pagecache
> * lose the page
> * try to read it (via pagecache)
> Woops - just found a copy in buffer cache, let's pick data from it.
> Pity that said data is obsolete...
That's because you left out his invalidate:
* create an instance in pagecache
* start reading into buffer cache (doesn't invalidate, right?)
* start writing using pagecache (invalidate buffer copy)
* lose the page
* try to read it (via pagecache)
Everthing ok. As an optimization, instead of 'lose the page', do 'move
page blocks to buffer cache'.
--
Daniel
next prev parent reply other threads:[~2001-05-15 10:34 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <200105140117.f4E1HqN07362@vindaloo.ras.ucalgary.ca>
2001-05-14 1:32 ` Getting FS access events Linus Torvalds
2001-05-14 1:45 ` Larry McVoy
2001-05-14 2:39 ` Richard Gooch
2001-05-14 3:09 ` Rik van Riel
2001-05-14 4:27 ` Richard Gooch
2001-05-15 4:37 ` Chris Wedgwood
2001-05-23 11:37 ` Stephen C. Tweedie
2001-05-14 2:24 ` Richard Gooch
2001-05-14 4:46 ` Linus Torvalds
2001-05-14 5:15 ` Richard Gooch
2001-05-14 13:04 ` Daniel Phillips
2001-05-14 18:00 ` Andreas Dilger
2001-05-14 20:16 ` Linus Torvalds
2001-05-14 23:19 ` Richard Gooch
2001-05-15 0:42 ` Daniel Phillips
2001-05-15 4:00 ` Linus Torvalds
2001-05-15 4:35 ` Larry McVoy
2001-05-15 4:57 ` David S. Miller
2001-05-15 5:12 ` Alexander Viro
2001-05-15 9:10 ` Alan Cox
2001-05-15 9:48 ` Lars Brinkhoff
2001-05-15 9:54 ` Alexander Viro
2001-05-15 20:17 ` Kai Henningsen
2001-05-15 20:58 ` Alexander Viro
2001-05-15 21:08 ` Alexander Viro
2001-05-15 4:59 ` Alexander Viro
2001-05-15 17:01 ` Pavel Machek
2001-05-15 4:43 ` Linus Torvalds
2001-05-15 5:04 ` Alexander Viro
2001-05-15 6:20 ` Richard Gooch
2001-05-15 6:28 ` Linus Torvalds
2001-05-15 6:49 ` Richard Gooch
2001-05-15 6:57 ` Alexander Viro
2001-05-15 10:33 ` Daniel Phillips [this message]
2001-05-15 10:44 ` Alexander Viro
2001-05-15 14:42 ` Daniel Phillips
2001-05-15 7:13 ` Linus Torvalds
2001-05-15 7:56 ` Chris Wedgwood
2001-05-15 8:06 ` Linus Torvalds
2001-05-15 8:33 ` Alexander Viro
2001-05-15 10:27 ` David Woodhouse
2001-05-15 16:00 ` Chris Mason
2001-05-15 19:26 ` H. Peter Anvin
2001-05-15 20:03 ` Alexander Viro
2001-05-15 20:07 ` H. Peter Anvin
2001-05-15 20:15 ` Alexander Viro
2001-05-15 20:17 ` H. Peter Anvin
2001-05-15 20:22 ` Alexander Viro
2001-05-15 20:26 ` H. Peter Anvin
2001-05-15 20:31 ` Alexander Viro
2001-05-15 21:12 ` Linus Torvalds
2001-05-15 21:22 ` H. Peter Anvin
2001-05-15 21:02 ` Linus Torvalds
2001-05-15 21:53 ` Jan Harkes
2001-05-19 5:26 ` Chris Wedgwood
2001-05-15 10:04 ` Anton Altaparmakov
2001-05-15 19:28 ` H. Peter Anvin
2001-05-15 22:31 ` Albert D. Cahalan
2001-05-15 22:35 ` H. Peter Anvin
2001-05-16 1:17 ` Anton Altaparmakov
2001-05-16 1:30 ` H. Peter Anvin
2001-05-16 8:34 ` Anton Altaparmakov
2001-05-16 16:27 ` H. Peter Anvin
2001-05-15 16:26 ` Pavel Machek
2001-05-15 18:02 ` Craig Milo Rogers
2001-05-15 16:17 ` Pavel Machek
2001-05-19 19:39 ` Linus Torvalds
2001-05-19 19:44 ` Pavel Machek
2001-05-19 19:47 ` Linus Torvalds
2001-05-23 11:29 ` Stephen C. Tweedie
2001-05-20 4:30 ` Chris Wedgwood
2001-05-20 19:47 ` Alan Cox
2001-05-18 7:55 ` Rogier Wolff
2001-05-23 11:36 ` Stephen C. Tweedie
2001-05-15 6:13 ` Richard Gooch
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=01051512333507.24410@starship \
--to=phillips@bonn-fries.net \
--cc=linux-kernel@vger.kernel.org \
--cc=rgooch@ras.ucalgary.ca \
--cc=torvalds@transmeta.com \
--cc=viro@math.psu.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox