From: Andrew Morton <akpm@zip.com.au>
To: Rusty Russell <rusty@rustcorp.com.au>
Cc: torvalds@transmeta.com, linux-kernel@vger.kernel.org,
k-suganuma@mvj.biglobe.ne.jp
Subject: Re: [PATCH] 2.5.21 Nonlinear CPU support
Date: Tue, 11 Jun 2002 00:42:32 -0700 [thread overview]
Message-ID: <3D05A9E8.FF0DA223@zip.com.au> (raw)
In-Reply-To: <E17Hflq-0005Hf-00@wagner.rustcorp.com.au>
Rusty Russell wrote:
>
> Linus, please apply. Tested on my dual x86 box.
>
> This patch removes smp_num_cpus, cpu_number_map and cpu_logical_map
> from generic code, and uses cpu_online(cpu) instead, in preparation
> for hotplug CPUS.
umm. This patch does introduce a non-zero amount of bloat:
> ...
> - ntfs_compression_buffers = (u8**)kmalloc(smp_num_cpus * sizeof(u8*),
> + ntfs_compression_buffers = (u8**)kmalloc(NR_CPUS * sizeof(u8*),
and slowdown:
> ...
> --- linux-2.5.21.24110/kernel/sched.c Mon Jun 10 16:03:56 2002
> +++ linux-2.5.21.24110.updated/kernel/sched.c Tue Jun 11 13:53:32 2002
> ...
> @@ -530,15 +530,16 @@
>
> busiest = NULL;
> max_load = 1;
> - for (i = 0; i < smp_num_cpus; i++) {
> - int logical = cpu_logical_map(i);
> + for (i = 0; i < NR_CPUS; i++) {
> + if (!cpu_online(i))
> + continue;
>
and for the majority of SMP machines it gives nothing back, yes?
Is there some way of optimising all that?
-
next prev parent reply other threads:[~2002-06-11 7:39 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-06-11 7:08 [PATCH] 2.5.21 Nonlinear CPU support Rusty Russell
2002-06-11 7:42 ` Andrew Morton [this message]
2002-06-11 9:09 ` Rusty Russell
2002-06-11 9:10 ` David S. Miller
2002-06-12 6:58 ` Rusty Russell
2002-06-12 9:26 ` David S. Miller
2002-06-13 5:01 ` Rusty Russell
2002-06-13 5:55 ` David S. Miller
2002-06-11 9:27 ` Andrew Morton
2002-06-11 11:22 ` Anton Altaparmakov
2002-06-12 5:57 ` Rusty Russell
2002-06-12 7:54 ` Anton Altaparmakov
2002-06-12 8:06 ` Rusty Russell
2002-06-12 8:25 ` Anton Altaparmakov
2002-06-12 19:32 ` Linus Torvalds
2002-06-12 13:10 ` Mikael Pettersson
2002-06-13 2:42 ` Rusty Russell
2002-06-12 0:53 ` Rusty Russell
2002-06-12 8:36 ` Helge Hafting
2002-06-11 10:57 ` Anton Altaparmakov
2002-06-11 17:59 ` Robert Love
2002-06-12 4:11 ` Rusty Russell
2002-06-11 19:29 ` Denis Vlasenko
2002-06-11 14:54 ` Anton Altaparmakov
2002-06-12 19:32 ` Denis Vlasenko
2002-06-12 15:08 ` Anton Altaparmakov
2002-06-12 17:36 ` Andreas Dilger
2002-06-12 18:34 ` Anton Altaparmakov
2002-06-12 19:39 ` Andreas Dilger
2002-06-12 20:41 ` Anton Altaparmakov
2002-06-12 21:03 ` Andreas Dilger
2002-06-12 21:15 ` Anton Altaparmakov
2002-06-12 20:03 ` H. Peter Anvin
2002-06-12 20:54 ` Robert Love
2002-06-12 20:57 ` Anton Altaparmakov
2002-06-12 22:21 ` H. Peter Anvin
2002-06-13 1:33 ` Anton Altaparmakov
2002-06-13 1:38 ` H. Peter Anvin
2002-06-13 1:45 ` Anton Altaparmakov
2002-06-13 2:13 ` H. Peter Anvin
2002-06-13 2:21 ` Anton Altaparmakov
2002-06-13 8:43 ` Helge Hafting
2002-06-11 18:01 ` Robert Love
2002-06-12 7:57 ` Alan Cox
2002-06-12 8:01 ` Rusty Russell
[not found] <Pine.LNX.4.33.0206121226550.1533-100000@penguin.transmeta. com>
2002-06-12 21:29 ` Anton Altaparmakov
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=3D05A9E8.FF0DA223@zip.com.au \
--to=akpm@zip.com.au \
--cc=k-suganuma@mvj.biglobe.ne.jp \
--cc=linux-kernel@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
--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