lkml.org 
[lkml]   [2003]   [Dec]   [1]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: a few question on threads affinity and CPU shielding.
On Mon, Dec 01, 2003 at 06:43:16PM +0100, Nicolas Castagné wrote:
> I was very pleased that some patches for controlling CPU affinities
> were merged in the 2.5 (and 2.6) releases of the kernel.
>
> Where may I find precisions on the patches that are now included ?

> - is there also a patch to shield cpu against the scheduler ?

I have a patch around that does this (against RedHat's backported O(1)).
Forward porting it should be no more difficult that creating it in the first
place :) I was waiting until after 2.6.x was more stable to offer it.

> - is there also a patch to shield cpu against all interruptions
> (especially hard clock interrups) ?

This could be added to my patch.

What my patch added was a sched_setprocstate() syscall, which lets you set a
CPU's run state. Currently I support:

ENABLED - run any task
RESTRICTED - run only tasks with (cpus_allowed == 1 << cpu)
ISOLATED - run only tasks with
(cpus_allowed == 1 << cpu && cpus_allowed_mask == 1 << cpu)

Tim
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:59    [W:0.861 / U:0.596 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site