From: Linus Torvalds <torvalds@transmeta.com>
To: Kanoj Sarcar <kanoj@google.engr.sgi.com>
Cc: "Stephen C. Tweedie" <sct@redhat.com>,
Ben LaHaise <bcrl@redhat.com>,
linux-mm@kvack.org
Subject: Re: [patch] first bit of vm balancing fixes for 2.3.52-1
Date: Mon, 20 Mar 2000 13:31:28 -0800 (PST) [thread overview]
Message-ID: <Pine.LNX.4.10.10003201329470.4818-100000@penguin.transmeta.com> (raw)
In-Reply-To: <200003202058.MAA47885@google.engr.sgi.com>
On Mon, 20 Mar 2000, Kanoj Sarcar wrote:
> >
> > The current behaviour is highly suboptimal: if you have two zones to
> > pick from for a given alloc_page(), and the first zone is at its
> > pages_min threshold, then we will always allocate from that first zone
> > and push it into kswap activation no matter how much free space there is
> > in the next zone.
>
> With Linus' change to the page alloc code in pre2, yes, spreading
> the allocation is an option, but I would be real careful before
> putting that in 2.4.
It's not an option: it is how things work.
My code expliticly says: ok, walk the list of zones, if any of them have
plenty of memory free just allocate it.
Only if none of the zones is an obvious target for allocation do we
balance, and then we mark all the appropriate zones for balancing at once.
Linus
--
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.eu.org/Linux-MM/
next prev parent reply other threads:[~2000-03-20 21:31 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2000-03-13 22:50 Ben LaHaise
2000-03-13 22:55 ` Linus Torvalds
2000-03-13 23:28 ` Kanoj Sarcar
2000-03-13 23:31 ` Linus Torvalds
2000-03-14 0:23 ` Kanoj Sarcar
2000-03-14 0:32 ` Linus Torvalds
2000-03-17 12:35 ` Stephen C. Tweedie
2000-03-20 20:58 ` Kanoj Sarcar
2000-03-20 21:31 ` Linus Torvalds [this message]
2000-03-20 22:06 ` Linus Torvalds
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=Pine.LNX.4.10.10003201329470.4818-100000@penguin.transmeta.com \
--to=torvalds@transmeta.com \
--cc=bcrl@redhat.com \
--cc=kanoj@google.engr.sgi.com \
--cc=linux-mm@kvack.org \
--cc=sct@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox