linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Bulent Abali" <abali@us.ibm.com>
To: Linus Torvalds <torvalds@transmeta.com>
Cc: Rik van Riel <riel@conectiva.com.br>, linux-mm@kvack.org
Subject: Re: [PATCH] swap_state.c thinko
Date: Fri, 6 Apr 2001 16:20:17 -0400	[thread overview]
Message-ID: <OFF70E8B5F.A2073252-ON85256A26.006E7BF4@pok.ibm.com> (raw)


>So I don't think it would necessarily be wrong to say
>something like
>
>    free -= num_physpages >> 6;
>
>to approximate the notion of "keep 1 percent slop" (remember, the 1% may
>well be on the swap device, not actually kept as free memory).


Hi,

I suggested the same thing to Rik but he rightfully said that it would
not work well for diskless (or swap-less) machines.  You may want to
consider the following instead.

     free -= (nr_swap_pages)? num_physpages >> 6 : 0;

By the way, disk space is cheap why not give more than 1 percent slop?
This is really accounted in the swap space and not the memory.
It will also help system out of oom_killer's radar.

Bulent Abali  (abali@us.ibm.com)



--
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/

             reply	other threads:[~2001-04-06 20:20 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-04-06 20:20 Bulent Abali [this message]
2001-04-06 20:33 ` Jeff Garzik
  -- strict thread matches above, loose matches on Subject: below --
2001-04-05 15:56 Ben LaHaise
2001-04-05 16:05 ` Rik van Riel
2001-04-05 17:11   ` Ben LaHaise
2001-04-05 23:40     ` Andrea Arcangeli
2001-04-06  0:32     ` Linus Torvalds
2001-04-06 16:31       ` Hugh Dickins
2001-04-06 17:21         ` Linus Torvalds
2001-04-06 18:23           ` Hugh Dickins
2001-04-06 18:57             ` Linus Torvalds
2001-04-06 19:06               ` Rik van Riel
2001-04-06 18:47           ` Andrea Arcangeli
2001-04-06 18:37             ` Hugh Dickins
2001-04-06 19:09               ` Andrea Arcangeli
2001-04-06 18:53                 ` Hugh Dickins
2001-04-06 19:14                 ` Andrea Arcangeli
2001-04-06 19:03                   ` Hugh Dickins
2001-04-06 20:03                     ` Andrea Arcangeli
2001-04-06 19:12               ` Richard Jerrell
2001-04-06 19:52               ` Linus Torvalds
2001-04-06 20:22                 ` Andrea Arcangeli
2001-04-06 21:04                   ` Rik van Riel
2001-04-07  1:27                     ` Andrea Arcangeli
2001-04-09 18:16                   ` Alan Cox
2001-04-09 18:45                     ` Andrea Arcangeli
2001-04-09 20:32                     ` Linus Torvalds
2001-04-09 20:54                       ` David L. Parsley
2001-04-10 21:07                       ` James Antill
2001-04-10 22:20                         ` Jeff Garzik
2001-04-06 20:48                 ` Hugh Dickins
2001-04-05 17:21 ` Hugh Dickins
2001-04-05 21:39   ` Richard Jerrell

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=OFF70E8B5F.A2073252-ON85256A26.006E7BF4@pok.ibm.com \
    --to=abali@us.ibm.com \
    --cc=linux-mm@kvack.org \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox