Re: [uml-devel] preemption

[BlaisorBlade <blaisorblade_spam@yahoo.it>]

Alle 20:38, martedì 18 maggio 2004, Jeff Dike ha scritto:
> On Tue, May 18, 2004 at 06:47:26AM -0700, Sam King wrote:
> > >From what I can tell, when the guest kernel takes a
> >
> > timer interrupt (SIGALRM) it eventually updates the
> > tsk->need_resched parameter for processes that have
> > been running for too long.  However, I do not see
> > where the actual switch takes place except in the
> > interrupt_end() function which is only called as a
> > result of guest application system calls and signals.
>
> Exactly.  Every kernel entrance is either a system call or signal (a UML
> signal, not a process signal, BTW), so there is a preemption opportunity
> at every return to userspace.
But when you say "UML signal" (I guess a signal between the host UML threads) 
you mean even a timer interrupt, right? Otherwise I don't see how a 
non-syscalling process (a true CPU-hog, like SETI@home or such things) could 
be interrupted.
-- 
Paolo Giarrusso, aka Blaisorblade
Linux registered user n. 292729



-------------------------------------------------------
This SF.Net email is sponsored by: Oracle 10g
Get certified on the hottest thing ever to hit the market... Oracle 10g. 
Take an Oracle 10g class now, and we'll give you the exam FREE.
http://ads.osdn.com/?ad_id149&alloc_id66&opÌk
_______________________________________________
User-mode-linux-devel mailing list
User-mode-linux-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/user-mode-linux-devel