All of lore.kernel.org
 help / color / mirror / Atom feed
* [Xenomai-help] do memory functions switch to secondary mode ?
@ 2006-07-11 12:27 Roderik_Wildenburg
  2006-07-11 14:55 ` Jan Kiszka
  2006-07-15  1:38 ` Philippe Gerum
  0 siblings, 2 replies; 3+ messages in thread
From: Roderik_Wildenburg @ 2006-07-11 12:27 UTC (permalink / raw)
  To: xenomai

Does any of the memory functions like :
memcopy,
memset,
bzero,

:
:

cause Xenomai to switch to secondary mode ?
I am asking as I have a high priority task, which mesures its
periodicity (set to 1ms).
This task is using just rt_-functions and memcpy.
When in low priority tasks memory intensively is used (memset,
rt_heap_alloc, rt_heap_create, NFS-transfers in Linux threads), the
cycle time of the high priority task inreases to nearly twice the time
it has been set up (2ms++; at least 1 time, as I just measure maxima).

Is this possible, or am I doing something wrong ?

Tanks a lot
Roderik


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

* Re: [Xenomai-help] do memory functions switch to secondary mode ?
  2006-07-11 12:27 [Xenomai-help] do memory functions switch to secondary mode ? Roderik_Wildenburg
@ 2006-07-11 14:55 ` Jan Kiszka
  2006-07-15  1:38 ` Philippe Gerum
  1 sibling, 0 replies; 3+ messages in thread
From: Jan Kiszka @ 2006-07-11 14:55 UTC (permalink / raw)
  To: Roderik_Wildenburg; +Cc: xenomai

[-- Attachment #1: Type: text/plain, Size: 1139 bytes --]

Roderik_Wildenburg@domain.hid wrote:
> Does any of the memory functions like :
> memcopy,
> memset,
> bzero,
> 
> :
> :
> 
> cause Xenomai to switch to secondary mode ?
> I am asking as I have a high priority task, which mesures its
> periodicity (set to 1ms).
> This task is using just rt_-functions and memcpy.
> When in low priority tasks memory intensively is used (memset,
> rt_heap_alloc, rt_heap_create, NFS-transfers in Linux threads), the
> cycle time of the high priority task inreases to nearly twice the time
> it has been set up (2ms++; at least 1 time, as I just measure maxima).
> 
> Is this possible, or am I doing something wrong ?

Try catching unwanted context switches via the SIGXCPU signal. Given you
have a sane glibc, non of those functions should cause a context switch
- unless you touch some piece of memory for the first time (lazy
mapping...).

[Unfortunately, the I-pipe tracer is only available over 2.6 so far.
Otherwise, putting a xntrace_user_freeze() right at that line in your
application where you detect the deadline miss would give a nice view
back in history.]

Jan


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

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

* Re: [Xenomai-help] do memory functions switch to secondary mode ?
  2006-07-11 12:27 [Xenomai-help] do memory functions switch to secondary mode ? Roderik_Wildenburg
  2006-07-11 14:55 ` Jan Kiszka
@ 2006-07-15  1:38 ` Philippe Gerum
  1 sibling, 0 replies; 3+ messages in thread
From: Philippe Gerum @ 2006-07-15  1:38 UTC (permalink / raw)
  To: Roderik_Wildenburg; +Cc: xenomai

On Tue, 2006-07-11 at 14:27 +0200, Roderik_Wildenburg@domain.hid wrote:
> Does any of the memory functions like :
> memcopy,
> memset,
> bzero,
> 
> :
> :
> 
> cause Xenomai to switch to secondary mode ?

No, unless a page fault is raised as a result of treading on the target
memory.

> I am asking as I have a high priority task, which mesures its
> periodicity (set to 1ms).
> This task is using just rt_-functions and memcpy.
> When in low priority tasks memory intensively is used (memset,
> rt_heap_alloc, rt_heap_create, NFS-transfers in Linux threads), the
> cycle time of the high priority task inreases to nearly twice the time
> it has been set up (2ms++; at least 1 time, as I just measure maxima).
> 
> Is this possible, or am I doing something wrong ?
> 

Do you observe this weird behaviour at the same time the kernel emits
allocation failure messages?

> Tanks a lot
> Roderik
> 
> _______________________________________________
> Xenomai-help mailing list
> Xenomai-help@domain.hid
> https://mail.gna.org/listinfo/xenomai-help
-- 
Philippe.




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

end of thread, other threads:[~2006-07-15  1:38 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2006-07-11 12:27 [Xenomai-help] do memory functions switch to secondary mode ? Roderik_Wildenburg
2006-07-11 14:55 ` Jan Kiszka
2006-07-15  1:38 ` Philippe Gerum

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.