All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andi Kleen <ak@suse.de>
To: peter@horizon.com
Cc: linux-kernel@vger.kernel.org
Subject: Re: Hardwired drivers are going away?
Date: 15 Jan 2002 13:16:04 +0100	[thread overview]
Message-ID: <p736663kdx7.fsf@oldwotan.suse.de> (raw)
In-Reply-To: <20020115025840.11509.qmail@science.horizon.com.suse.lists.linux.kernel>
In-Reply-To: peter@horizon.com's message of "15 Jan 2002 04:04:19 +0100"

peter@horizon.com writes:

> 1) The main kernel is contiguous in physical memory and is mapped with
>    large (4 MB) pages.  This reduces pressure on the TLB.  Modules are
>    loaded in vmalloc memory, which uses small pages, and therefore
>    competes for TLB space.  This is a performance penalty, especially
>    as most current machines have undersized TLBs already.  (A 64-entry
>    TLB with 4K pages maps 256K at a time.  On-chip L2 caches are this
>    large or larger.  Thus, as a crude approximation, every L2 miss also
>    causes a TLB miss.)

-aa tries to load modules into the linear mapping when possible.
That usually works when you load the modules early when the memory 
isn't that fragmented yet.

I agree on that trying to put everything into modules isn't a good idea,
especially because of your second point.

-Andi

       reply	other threads:[~2002-01-15 12:16 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20020115025840.11509.qmail@science.horizon.com.suse.lists.linux.kernel>
2002-01-15 12:16 ` Andi Kleen [this message]
2002-01-15  2:58 Hardwired drivers are going away? peter
2002-01-15 12:44 ` Alan Cox
2002-01-15 12:39   ` David S. Miller
2002-01-15 18:39     ` Rob Landley
     [not found] <mailman.1011034621.1626.linux-kernel2news@redhat.com>
2002-01-14 23:33 ` Pete Zaitcev
     [not found] <fa.g055bvv.qmq0hk@ifi.uio.no>
     [not found] ` <ksahkuv.tg60gl@ifi.uio.no>
2002-01-14 22:22   ` Chris Adams
  -- strict thread matches above, loose matches on Subject: below --
2002-01-14 17:55 ISA hardware discovery -- the elegant solution Mr. James W. Laferriere
2002-01-14 18:08 ` Alan Cox
2002-01-14 18:10   ` Hardwired drivers are going away? Eric S. Raymond
2002-01-14 18:50     ` David Lang
2002-01-14 19:04       ` Alan Cox
2002-01-14 18:57         ` David Lang
2002-01-14 19:03           ` Andrew Pimlott
2002-01-14 19:21           ` Alan Cox
2002-01-15 10:45           ` Horst von Brand
2002-01-15 11:13             ` crispin
2002-01-15 14:25             ` David Lang
2002-01-14 19:00         ` Mr. James W. Laferriere
2002-01-14 19:17           ` Alan Cox
2002-01-14 19:14             ` Mr. James W. Laferriere
2002-01-14 19:37               ` Alan Cox
2002-01-14 20:28                 ` Mr. James W. Laferriere
2002-01-14 19:44             ` David Lang
2002-01-14 20:09               ` Alexander Viro
2002-01-14 20:49                 ` Chris Friesen
2002-01-14 20:55                   ` Alexander Viro
2002-01-14 20:51               ` Ian Molton
2002-01-14 22:11                 ` David Lang
2002-01-14 23:12                   ` Brian Gerst
2002-01-14 23:17                     ` David Lang
2002-01-14 23:22                   ` Ian Molton
2002-01-15  0:40                     ` H. Peter Anvin
2002-01-14 19:54             ` David Lang
2002-01-15 17:27             ` Aaron Lehmann
2002-01-15 17:47               ` Alexander Viro
2002-01-15 19:48               ` Alan Cox
2002-01-18 12:39           ` Florian Weimer
2002-01-18 22:20             ` Mr. James W. Laferriere
2002-01-18 23:22               ` Keith Owens
2002-01-20 23:20                 ` Frank van de Pol
2002-01-21  0:54                   ` Bruce Harada
2002-01-21  3:49                     ` Andreas Ferber
2002-01-21  4:45                       ` Bruce Harada
2002-01-21  5:12                         ` Andreas Ferber
2002-01-21  1:06                 ` Anton Altaparmakov
2002-01-21  1:07                   ` Mr. James W. Laferriere
2002-01-21  1:30                     ` Andrew Morton
2002-01-21  1:53                       ` Keith Owens
2002-01-21  2:04                         ` Andrew Morton
2002-01-21  2:25                           ` Keith Owens
2002-01-21  2:56                             ` Andrew Morton
2002-01-21  3:43                               ` Keith Owens
2002-01-21  4:24                                 ` Andrew Morton
2002-01-21  3:44                             ` yodaiken
2002-01-21 20:57                               ` Kai Henningsen
2002-01-21  2:13                         ` John Levon
2002-01-21  2:31                           ` Keith Owens
2002-01-21 23:52                             ` Thomas Zimmerman
2002-01-21  9:34                       ` Horst von Brand
2002-01-21 14:29                         ` John Levon
2002-01-21  1:31                   ` Anton Altaparmakov
2002-01-14 19:27       ` Alexander Viro
2002-01-15 17:24       ` Aaron Lehmann
2002-01-15 18:17         ` David Lang
2002-01-15 19:25           ` Aaron Lehmann
2002-01-15 19:44         ` Kai Henningsen
2002-01-14 18:54     ` Mr. James W. Laferriere
2002-01-14 18:56     ` Alan Cox
2002-01-14 18:39       ` Eric S. Raymond
2002-01-14 19:09     ` Alexander Viro
2002-01-14 14:19       ` Rob Landley
2002-01-14 22:33         ` Greg KH
2002-01-15 11:35         ` Keith Owens
2002-01-15 15:34           ` Oliver Xymoron
2002-01-14 19:24       ` Alan Cox
2002-01-14 20:17       ` Eric S. Raymond
2002-01-14 14:57         ` Rob Landley
2002-01-14 20:51         ` David Lang
2002-01-14 22:18         ` Oliver Xymoron
2002-01-15 19:20         ` Horst von Brand
2002-01-16  9:00           ` Eric S. Raymond
2002-01-14 23:12       ` Rusty Russell
2002-02-09  0:19     ` Dr. Kelsey Hudson

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=p736663kdx7.fsf@oldwotan.suse.de \
    --to=ak@suse.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peter@horizon.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.