All of lore.kernel.org
 help / color / mirror / Atom feed
* [Xenomai-core] nkpod->watchdog_trigger per CPU?
@ 2006-04-07  7:43 Jan Kiszka
  2006-04-07  8:05 ` Philippe Gerum
  0 siblings, 1 reply; 3+ messages in thread
From: Jan Kiszka @ 2006-04-07  7:43 UTC (permalink / raw)
  To: xenomai-core

[-- Attachment #1: Type: text/plain, Size: 409 bytes --]

Hi,

analysing the watchdog characteristics in our scenarios, I just wondered
if it is SMP-aware (we have no SMP in use, it's a pure analytical concern).

The watchdog timeout is stored system-wide in nkpod->watchdog_trigger,
but it is based on a per-CPU clock (TSC). Is the tick IRQ bound to a
specific CPU in SMP scenarios so that this doesn't matter? Or am I just
overseeing some detail?

Jan


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 250 bytes --]

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [Xenomai-core] nkpod->watchdog_trigger per CPU?
  2006-04-07  7:43 [Xenomai-core] nkpod->watchdog_trigger per CPU? Jan Kiszka
@ 2006-04-07  8:05 ` Philippe Gerum
  2006-04-07 13:31   ` Gilles Chanteperdrix
  0 siblings, 1 reply; 3+ messages in thread
From: Philippe Gerum @ 2006-04-07  8:05 UTC (permalink / raw)
  To: Jan Kiszka; +Cc: xenomai-core

Jan Kiszka wrote:
> Hi,
> 
> analysing the watchdog characteristics in our scenarios, I just wondered
> if it is SMP-aware (we have no SMP in use, it's a pure analytical concern).
> 
> The watchdog timeout is stored system-wide in nkpod->watchdog_trigger,
> but it is based on a per-CPU clock (TSC). Is the tick IRQ bound to a
> specific CPU in SMP scenarios so that this doesn't matter? Or am I just
> overseeing some detail?
> 

Good catch. This code was written before per-CPU ticking became the 
"official" implementation, so it needs to be updated.

> Jan
> 
> 
> 
> ------------------------------------------------------------------------
> 
> _______________________________________________
> Xenomai-core mailing list
> Xenomai-core@domain.hid
> https://mail.gna.org/listinfo/xenomai-core


-- 

Philippe.


^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [Xenomai-core] nkpod->watchdog_trigger per CPU?
  2006-04-07  8:05 ` Philippe Gerum
@ 2006-04-07 13:31   ` Gilles Chanteperdrix
  0 siblings, 0 replies; 3+ messages in thread
From: Gilles Chanteperdrix @ 2006-04-07 13:31 UTC (permalink / raw)
  To: Philippe Gerum; +Cc: Jan Kiszka, xenomai-core

Philippe Gerum wrote:
 > Jan Kiszka wrote:
 > > Hi,
 > > 
 > > analysing the watchdog characteristics in our scenarios, I just wondered
 > > if it is SMP-aware (we have no SMP in use, it's a pure analytical concern).
 > > 
 > > The watchdog timeout is stored system-wide in nkpod->watchdog_trigger,
 > > but it is based on a per-CPU clock (TSC). Is the tick IRQ bound to a
 > > specific CPU in SMP scenarios so that this doesn't matter? Or am I just
 > > overseeing some detail?
 > > 
 > 
 > Good catch. This code was written before per-CPU ticking became the 
 > "official" implementation, so it needs to be updated.

The watchdog is handled on a per-cpu basis with revision 901.

-- 


					    Gilles Chanteperdrix.


^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2006-04-07 13:31 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2006-04-07  7:43 [Xenomai-core] nkpod->watchdog_trigger per CPU? Jan Kiszka
2006-04-07  8:05 ` Philippe Gerum
2006-04-07 13:31   ` Gilles Chanteperdrix

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.