linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Zlatko Calusic <Zlatko.Calusic@CARNet.hr>
To: Rik van Riel <H.H.vanRiel@phys.uu.nl>
Cc: "David J. Fred" <djf@ic.net>,
	linux-kernel@vger.rutgers.edu, Linux-MM List <linux-mm@kvack.org>
Subject: Re: unexpected paging during large file reads in 2.1.127
Date: 13 Nov 1998 00:18:44 +0100	[thread overview]
Message-ID: <87k910biuj.fsf@atlas.CARNet.hr> (raw)
In-Reply-To: Rik van Riel's message of "Thu, 12 Nov 1998 14:39:53 +0100 (CET)"

OK, benchmarking done (never faster :))

Methodology: compile kernel, reboot, fire up X, XEmacs, Netscape, few
xterms to (almost) fill memory, copy 1.5GB of files to /dev/null.

I have 64MB of memory, and interesting thing, in both cases I tried,
system decided to swap out cca 16MB, which is fine. Without patching,
kernel would start thrashing very early, during file copy, which
considerably slows down whole operation (and make machine painfully
sloooow).


*** Case 1)

shrink_mmap():
        count_max = (limit<<4) >> (priority>>1);
        count_min = (limit<<4) >> (priority);

Result after copying is finished:
    3 root       7   7     0    0     0 SWN     0  0.0  0.0   0:13 kswapd
                                                              ^^^^


*** Case 2)

shrink_one_page():
        age_page(page);
        age_page(page);
        age_page(page);

Result after copying is finished:
    3 root       7   7     0    0     0 SWN     0  0.0  0.0   0:07 kswapd
                                                              ^^^^


Tested on pre-2.1.128-1.

Q.E.D. :)
-- 
Posted by Zlatko Calusic           E-mail: <Zlatko.Calusic@CARNet.hr>
---------------------------------------------------------------------
		    Bus error (Passengers dumped)
--
This is a majordomo managed list.  To unsubscribe, send a message with
the body 'unsubscribe linux-mm me@address' to: majordomo@kvack.org

      parent reply	other threads:[~1998-11-12 23:20 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <Pine.LNX.3.96.981112143712.20473B-100000@mirkwood.dummy.home>
1998-11-12 22:45 ` Zlatko Calusic
1998-11-16 19:59   ` Stephen C. Tweedie
1998-11-16 20:48     ` Rik van Riel
1998-11-16 23:05       ` Stephen C. Tweedie
1998-11-17  1:21         ` Zlatko Calusic
1998-11-17 12:00           ` Stephen C. Tweedie
1998-11-18 22:50             ` Zlatko Calusic
1998-11-17  6:42         ` Rik van Riel
1998-11-17 12:06           ` Stephen C. Tweedie
1998-11-17 20:25             ` Rik van Riel
1998-11-16 21:56     ` Zlatko Calusic
1998-11-12 23:18 ` Zlatko Calusic [this message]

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=87k910biuj.fsf@atlas.CARNet.hr \
    --to=zlatko.calusic@carnet.hr \
    --cc=H.H.vanRiel@phys.uu.nl \
    --cc=djf@ic.net \
    --cc=linux-kernel@vger.rutgers.edu \
    --cc=linux-mm@kvack.org \
    /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