mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Dan Maas" <dmaas@dcine.com>
To: "Rik van Riel" <riel@conectiva.com.br>
Cc: <linux-kernel@vger.kernel.org>
Subject: Re: Swap
Date: Tue, 20 Nov 2001 16:26:57 -0500	[thread overview]
Message-ID: <037701c1720a$159ee9a0$1a01a8c0@allyourbase> (raw)
In-Reply-To: <fa.kmf405v.j74f21@ifi.uio.no> <fa.ns5ugpv.q02sbg@ifi.uio.no>

> I bet they're getting mmap()d, like all mp3 programs seem to do

Just a note here - I see much fewer buffer underruns and more consistent
read-ahead/drop-behind behavior (i.e. no paging of other programs) when
using plain read(), as opposed to mmap(). This is in a video playback
program that pumps 3.6MB/sec!

MP3 datarates are less than 50KB/sec, so I don't really see why they stand
to benefit from mmap()... With mmap() you pay the extra cost of setting
up/tearing down the mapping, and the kernel->user copy is virtually
insignificant anyway (you already are paying for a single copy plus cache
pollution when moving the data from filesystem buffer to sound card DMA
buffer, so a second copy isn't a big deal)...

Regards,
Dan


       reply	other threads:[~2001-11-20 21:39 UTC|newest]

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <fa.kmf405v.j74f21@ifi.uio.no>
     [not found] ` <fa.ns5ugpv.q02sbg@ifi.uio.no>
2001-11-20 21:26   ` Dan Maas [this message]
2001-11-20 22:05     ` Swap Rik van Riel
2001-11-20 22:11     ` Swap David S. Miller
2001-11-20 22:19       ` Swap Rik van Riel
2001-11-20 22:34         ` Swap Dan Maas
2001-11-20 23:05           ` Swap Andrew Morton
     [not found]           ` <fa.jc73ejv.1s6e80t@ifi.uio.no>
2001-11-21  1:45             ` Swap Håvard Kvålen
2001-11-21  4:23               ` Swap Andreas Dilger
2001-11-20 22:23       ` Swap Andrew Morton
2001-11-20 23:01       ` Swap David S. Miller
2001-11-20 23:35         ` Swap Rik van Riel
2001-11-20 23:40         ` Swap David S. Miller
2001-11-21  0:19           ` Swap Rik van Riel
2001-11-21  0:21           ` Swap David S. Miller
     [not found] <fa.kb6ct7v.pgku0d@ifi.uio.no>
     [not found] ` <fa.k8qdvcv.184ak2l@ifi.uio.no>
2001-11-20 22:46   ` Swap Dan Maas
2001-11-20 23:17     ` Swap Trond Myklebust
     [not found] <fa.inl6g6v.1mmbp4@ifi.uio.no>
     [not found] ` <fa.heevhav.sjs8an@ifi.uio.no>
2001-11-18 22:15   ` Swap Dan Maas
2001-11-18 22:43     ` Swap François Cami
2001-11-19  9:18       ` Swap James A Sutherland
2001-11-19 10:51         ` Swap Remco Post
2001-11-19 13:33           ` Swap James A Sutherland
2001-11-19 13:46             ` Swap Remco Post
2001-11-19 16:58               ` Swap Rik van Riel
     [not found]                 ` <Pine.LNX.4.33L.0111191458150.1491-100000@duckman.distro.conecti va>
2001-11-19 21:13                   ` Swap Alex Bligh - linux-kernel
2001-11-19 21:17                     ` Swap Rik van Riel
     [not found]                       ` <Pine.LNX.4.33L.0111191917000.1491-100000@duckman.distro.conecti va>
2001-11-19 21:52                         ` Swap Alex Bligh - linux-kernel
2001-11-19 16:36             ` Swap Jesse Pollard
2001-11-20 14:51             ` Swap J.A. Magallon
2001-11-20 16:01               ` Swap Wolfgang Rohdewald
2001-11-20 16:06                 ` Swap Remco Post
2001-11-20 16:12                 ` Swap Nick LeRoy
2001-11-20 16:20                 ` Swap Richard B. Johnson
2001-11-20 17:14                   ` Swap Christopher Friesen
2001-11-20 17:40                     ` Swap Richard B. Johnson
2001-11-20 18:14                       ` Swap Nick LeRoy
2001-11-21 10:17                         ` Swap Helge Hafting
2001-11-21 11:17                           ` Swap Alan Cox
2001-11-20 23:20                       ` Swap Luigi Genoni
2001-11-21 16:44                       ` Swap Remco Post
2001-11-20 17:58                     ` Swap Wolfgang Rohdewald
2001-11-20 21:05                     ` Swap Steffen Persvold
2001-11-20 21:18                       ` Swap Mike Fedyk
2001-11-20 21:33                         ` Swap Nick LeRoy
2001-11-20 21:44                           ` Swap Mike Fedyk
2001-11-20 22:00                             ` Swap Nick LeRoy
2001-11-21 16:53                             ` Swap Remco Post
2001-11-20 21:43                         ` Swap Richard B. Johnson
2001-11-20 21:19                       ` Swap Nick LeRoy
2001-11-21 16:48                       ` Swap Remco Post
2001-11-20 20:58               ` Swap Mike Fedyk
2001-11-19 10:03       ` Swap Tim Connors
2001-11-19 10:16         ` Swap Dan Maas
2001-11-18 21:12 Swap war
2001-11-18 21:25 ` Swap James A Sutherland
2001-11-18 21:28   ` Swap war
2001-11-18 21:42     ` Swap François Cami
2001-11-18 21:45       ` Swap war
2001-11-18 23:03     ` Swap Erik Gustavsson
2001-11-19 18:12       ` Swap Eric W. Biederman
2001-11-19 18:43         ` Swap Rik van Riel
2001-11-20  2:49           ` Swap Eric W. Biederman
2001-11-20  3:33             ` Swap Ryan Cumming
2001-11-20 11:43               ` Swap Rik van Riel
2001-11-20 11:41             ` Swap Rik van Riel
2001-11-19 19:12         ` Swap James A Sutherland
2001-11-20  2:47           ` Swap Eric W. Biederman
2001-11-20  9:16             ` Swap James A Sutherland
2001-11-18 22:05   ` Swap J.A. Magallon
2001-11-18 22:21     ` Swap François Cami
2001-11-18 22:36     ` Swap Charles Marslett
2001-11-18 22:54       ` Swap J.A. Magallon
2001-11-18 23:36     ` Swap Bernd Eckenfels

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='037701c1720a$159ee9a0$1a01a8c0@allyourbase' \
    --to=dmaas@dcine.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=riel@conectiva.com.br \
    /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

Powered by JetHome