Messages in this thread |  | | | Date | Tue, 15 Jul 2008 00:16:07 -0400 (EDT) | | From | Steven Rostedt <> | | Subject | Re: current linux-2.6.git: cpusets completely broken |
On Mon, 14 Jul 2008, Linus Torvalds wrote:
> >
> > Oh, I'm not arguing. My mind is going off to an even bigger picture, where
> > something in the future would need to stop migration to a particular CPU,
> > and that it could simply clear the bit and call synchronize_sched. The run
> > queue lock is only visible to the scheduler. Sorry, I may have been day
> > dreaming out loud ;-)
>
> Well, you'd be stuck right now anyway.
>
> At least in my trivial patch, the cpu_active_map locking is protected by
> 'cpu_add_remove_lock' which is static to cpu.c. The only thing that
> modifies it (apart from the initial setup before SMP has been brought up)
> is the hotplug code.
Yeah, I see that now. I was thinking back to a time I was doing some crazy
kernel hacking and would have liked this feature (stop new tasks from
migrating to a CPU). cpusets today are probably a better answer, and what
I was thinking with using the cpu_active_map is more of a hack.
Sorry for the noise, I'll go back to updating ftrace.txt
-- Steve
|  |