From: Daniel Phillips <phillips@bonn-fries.net>
To: Rik van Riel <riel@conectiva.com.br>,
Marcelo Tosatti <marcelo@conectiva.com.br>
Cc: Linus Torvalds <torvalds@transmeta.com>,
Ben LaHaise <bcrl@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH] Unlazy activate (was: re "ongoing vm suckage")
Date: Sun, 5 Aug 2001 01:28:35 +0200 [thread overview]
Message-ID: <01080501283500.00315@starship> (raw)
In-Reply-To: <Pine.LNX.4.33L.0108040411220.2526-100000@imladris.rielhome.conectiva>
On Saturday 04 August 2001 09:13, Rik van Riel wrote:
> Oh, and we definately need to un-lazy the queue movement
> from the inactive_clean list. Having all of the pages you
> counted on as being reclaimable referenced is a very bad
> surprise ...
This patch does immediate activate for used-twice pages, so that
pages already known to be referenced don't stay sitting on the
inactive queue until page_launder finds them.
This improves dbench a little, as well as my make+grep load, so
it seems like a good thing. I can't think of any reason why it
makes sense to leave those pages sitting on the inactive queue
when we already know they're going to be activated eventually.
Well, *maybe* there would be less CPU spent acquiring the
pagemap_lru_lock, but that's it.
--- ../2.4.8-pre4/mm/filemap.c Sat Aug 4 14:27:16 2001
+++ ./mm/filemap.c Sat Aug 4 23:41:00 2001
@@ -979,9 +979,13 @@
static inline void check_used_once (struct page *page)
{
- if (!page->age) {
- page->age = PAGE_AGE_START;
- ClearPageReferenced(page);
+ if (!PageActive(page)) {
+ if (page->age)
+ activate_page(page);
+ else {
+ page->age = PAGE_AGE_START;
+ ClearPageReferenced(page);
+ }
}
}
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/
next prev parent reply other threads:[~2001-08-04 23:28 UTC|newest]
Thread overview: 94+ messages / expand[flat|nested] mbox.gz Atom feed top
2001-08-03 23:44 [RFC][DATA] re "ongoing vm suckage" Ben LaHaise
2001-08-03 23:44 ` Ben LaHaise
2001-08-04 1:29 ` Rik van Riel
2001-08-04 1:29 ` Rik van Riel
2001-08-04 3:06 ` Daniel Phillips
2001-08-04 3:06 ` Daniel Phillips
2001-08-04 3:13 ` Linus Torvalds
2001-08-04 3:13 ` Linus Torvalds
2001-08-04 3:23 ` Rik van Riel
2001-08-04 3:23 ` Rik van Riel
2001-08-04 3:35 ` Linus Torvalds
2001-08-04 3:35 ` Linus Torvalds
2001-08-04 3:26 ` Ben LaHaise
2001-08-04 3:26 ` Ben LaHaise
2001-08-04 3:34 ` Rik van Riel
2001-08-04 3:34 ` Rik van Riel
2001-08-04 3:38 ` Linus Torvalds
2001-08-04 3:38 ` Linus Torvalds
2001-08-04 3:48 ` Linus Torvalds
2001-08-04 3:48 ` Linus Torvalds
2001-08-04 4:14 ` Ben LaHaise
2001-08-04 4:14 ` Ben LaHaise
2001-08-04 4:20 ` Linus Torvalds
2001-08-04 4:20 ` Linus Torvalds
2001-08-04 4:39 ` Ben LaHaise
2001-08-04 4:39 ` Ben LaHaise
2001-08-04 4:47 ` Linus Torvalds
2001-08-04 4:47 ` Linus Torvalds
2001-08-04 5:13 ` Ben LaHaise
2001-08-04 5:13 ` Ben LaHaise
2001-08-04 5:28 ` Linus Torvalds
2001-08-04 5:28 ` Linus Torvalds
2001-08-04 6:37 ` Linus Torvalds
2001-08-04 6:37 ` Linus Torvalds
2001-08-04 5:38 ` Marcelo Tosatti
2001-08-04 5:38 ` Marcelo Tosatti
2001-08-04 7:13 ` Rik van Riel
2001-08-04 7:13 ` Rik van Riel
2001-08-04 23:28 ` Daniel Phillips [this message]
2001-08-04 14:22 ` Mike Black
2001-08-04 14:22 ` Mike Black
2001-08-04 17:08 ` Linus Torvalds
2001-08-04 17:08 ` Linus Torvalds
2001-08-04 20:54 ` Jonathan Morton
2001-08-05 4:19 ` Michael Rothwell
2001-08-05 4:19 ` Michael Rothwell
2001-08-05 18:40 ` Marcelo Tosatti
2001-08-05 18:40 ` Marcelo Tosatti
2001-08-05 20:20 ` Linus Torvalds
2001-08-05 20:20 ` Linus Torvalds
2001-08-05 20:45 ` arjan
2001-08-06 20:32 ` Rob Landley
2001-08-06 20:32 ` Rob Landley
2001-08-05 15:24 ` Mike Black
2001-08-05 15:24 ` Mike Black
2001-08-05 20:04 ` Linus Torvalds
2001-08-05 20:04 ` Linus Torvalds
2001-08-05 20:23 ` Alan Cox
2001-08-05 20:23 ` Alan Cox
2001-08-05 20:33 ` Linus Torvalds
2001-08-05 20:33 ` Linus Torvalds
2001-08-04 16:21 ` Mark Hemment
2001-08-04 16:21 ` Mark Hemment
2001-08-07 15:45 ` Ben LaHaise
2001-08-07 15:45 ` Ben LaHaise
2001-08-07 16:22 ` Linus Torvalds
2001-08-07 16:22 ` Linus Torvalds
2001-08-07 16:51 ` Ben LaHaise
2001-08-07 16:51 ` Ben LaHaise
2001-08-07 17:08 ` Linus Torvalds
2001-08-07 17:08 ` Linus Torvalds
2001-08-07 18:17 ` Andrew Morton
2001-08-07 18:17 ` Andrew Morton
2001-08-07 18:40 ` Ben LaHaise
2001-08-07 18:40 ` Ben LaHaise
2001-08-07 21:33 ` Daniel Phillips
2001-08-07 21:33 ` Daniel Phillips
2001-08-07 22:03 ` Linus Torvalds
2001-08-07 21:33 ` Linus Torvalds
2001-08-07 21:33 ` Linus Torvalds
2001-08-07 17:04 ` Linus Torvalds
2001-08-07 17:11 ` Rik van Riel
2001-08-07 19:12 ` Linus Torvalds
2001-08-07 19:21 ` Rik van Riel
2001-08-07 20:50 ` Linus Torvalds
2001-08-07 23:36 ` Linus Torvalds
2001-08-07 17:26 ` Chris Mason
2001-08-07 18:13 ` Daniel Phillips
2001-08-07 18:40 ` Chris Mason
2001-08-07 19:52 ` Linus Torvalds
2001-08-07 20:22 ` Chris Mason
2001-08-08 1:08 ` Theodore Tso
2001-08-08 1:13 ` Linus Torvalds
2001-08-08 2:25 ` Marcelo Tosatti
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=01080501283500.00315@starship \
--to=phillips@bonn-fries.net \
--cc=bcrl@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=marcelo@conectiva.com.br \
--cc=riel@conectiva.com.br \
--cc=torvalds@transmeta.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.