* [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes
@ 2008-10-13 13:34 Jan Kiszka
2008-10-13 13:49 ` Jan Kiszka
2008-10-13 13:51 ` Philippe Gerum
0 siblings, 2 replies; 6+ messages in thread
From: Jan Kiszka @ 2008-10-13 13:34 UTC (permalink / raw)
To: xenomai-core
Sigh, this is not my day: Can anyone confirm that we are leaking memory
with current SVN head? I'm seeing a constant increase on slab
"size-1024" on a x86_64 box when running arbitrary Xenomai apps in a loop.
[ Besides that, I have an occasional deadlock in xnpipe_wakeup_proc due
to an inconsistent xnpipe_sleepq - likely a different story... :-/ ]
Jan
--
Siemens AG, Corporate Technology, CT SE 2
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes
2008-10-13 13:34 [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes Jan Kiszka
@ 2008-10-13 13:49 ` Jan Kiszka
2008-10-13 13:51 ` Philippe Gerum
1 sibling, 0 replies; 6+ messages in thread
From: Jan Kiszka @ 2008-10-13 13:49 UTC (permalink / raw)
Cc: xenomai-core
Jan Kiszka wrote:
> Sigh, this is not my day: Can anyone confirm that we are leaking memory
> with current SVN head? I'm seeing a constant increase on slab
> "size-1024" on a x86_64 box when running arbitrary Xenomai apps in a loop.
I loose 1k per invocation, and this already from applying "-lrtdm" to an
innocent application (which just means xeno_bind_skin_opt). Strange.
Digging deeper.
Jan
--
Siemens AG, Corporate Technology, CT SE 2
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes
2008-10-13 13:34 [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes Jan Kiszka
2008-10-13 13:49 ` Jan Kiszka
@ 2008-10-13 13:51 ` Philippe Gerum
2008-10-13 14:00 ` Jan Kiszka
1 sibling, 1 reply; 6+ messages in thread
From: Philippe Gerum @ 2008-10-13 13:51 UTC (permalink / raw)
To: Jan Kiszka; +Cc: xenomai-core
Jan Kiszka wrote:
> Sigh, this is not my day: Can anyone confirm that we are leaking memory
> with current SVN head? I'm seeing a constant increase on slab
> "size-1024" on a x86_64 box when running arbitrary Xenomai apps in a loop.
>
> [ Besides that, I have an occasional deadlock in xnpipe_wakeup_proc due
> to an inconsistent xnpipe_sleepq - likely a different story... :-/ ]
>
Any luck with CONFIG_XENOMAI_OPT_DEBUG_QUEUES on?
> Jan
>
--
Philippe.
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes
2008-10-13 13:51 ` Philippe Gerum
@ 2008-10-13 14:00 ` Jan Kiszka
2008-10-13 14:13 ` Jan Kiszka
0 siblings, 1 reply; 6+ messages in thread
From: Jan Kiszka @ 2008-10-13 14:00 UTC (permalink / raw)
To: rpm; +Cc: Gilles Chanteperdrix, xenomai-core
Philippe Gerum wrote:
> Jan Kiszka wrote:
>> Sigh, this is not my day: Can anyone confirm that we are leaking memory
>> with current SVN head? I'm seeing a constant increase on slab
>> "size-1024" on a x86_64 box when running arbitrary Xenomai apps in a loop.
>>
>> [ Besides that, I have an occasional deadlock in xnpipe_wakeup_proc due
>> to an inconsistent xnpipe_sleepq - likely a different story... :-/ ]
>>
>
> Any luck with CONFIG_XENOMAI_OPT_DEBUG_QUEUES on?
As usual no luck: the bug disappeared (likely some race). Will dig into
that next after fixing this leak:
xnshadow_sys_event()
XNSHADOW_CLIENT_ATTACH -> xnarch_alloc_host_mem(xnsys_ppd)
XNSHADOW_CLIENT_DETACH -> ???
Jan
--
Siemens AG, Corporate Technology, CT SE 2
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes
2008-10-13 14:00 ` Jan Kiszka
@ 2008-10-13 14:13 ` Jan Kiszka
2008-10-13 18:06 ` Gilles Chanteperdrix
0 siblings, 1 reply; 6+ messages in thread
From: Jan Kiszka @ 2008-10-13 14:13 UTC (permalink / raw)
To: rpm; +Cc: Gilles Chanteperdrix, xenomai-core
Jan Kiszka wrote:
> Philippe Gerum wrote:
>> Jan Kiszka wrote:
>>> Sigh, this is not my day: Can anyone confirm that we are leaking memory
>>> with current SVN head? I'm seeing a constant increase on slab
>>> "size-1024" on a x86_64 box when running arbitrary Xenomai apps in a loop.
>>>
>>> [ Besides that, I have an occasional deadlock in xnpipe_wakeup_proc due
>>> to an inconsistent xnpipe_sleepq - likely a different story... :-/ ]
>>>
>> Any luck with CONFIG_XENOMAI_OPT_DEBUG_QUEUES on?
>
> As usual no luck: the bug disappeared (likely some race). Will dig into
> that next after fixing this leak:
>
> xnshadow_sys_event()
> XNSHADOW_CLIENT_ATTACH -> xnarch_alloc_host_mem(xnsys_ppd)
> XNSHADOW_CLIENT_DETACH -> ???
That was the key, now fixed with #4218.
Jan
--
Siemens AG, Corporate Technology, CT SE 2
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes
2008-10-13 14:13 ` Jan Kiszka
@ 2008-10-13 18:06 ` Gilles Chanteperdrix
0 siblings, 0 replies; 6+ messages in thread
From: Gilles Chanteperdrix @ 2008-10-13 18:06 UTC (permalink / raw)
To: Jan Kiszka; +Cc: xenomai-core
Jan Kiszka wrote:
> Jan Kiszka wrote:
>> Philippe Gerum wrote:
>>> Jan Kiszka wrote:
>>>> Sigh, this is not my day: Can anyone confirm that we are leaking memory
>>>> with current SVN head? I'm seeing a constant increase on slab
>>>> "size-1024" on a x86_64 box when running arbitrary Xenomai apps in a loop.
>>>>
>>>> [ Besides that, I have an occasional deadlock in xnpipe_wakeup_proc due
>>>> to an inconsistent xnpipe_sleepq - likely a different story... :-/ ]
>>>>
>>> Any luck with CONFIG_XENOMAI_OPT_DEBUG_QUEUES on?
>> As usual no luck: the bug disappeared (likely some race). Will dig into
>> that next after fixing this leak:
>>
>> xnshadow_sys_event()
>> XNSHADOW_CLIENT_ATTACH -> xnarch_alloc_host_mem(xnsys_ppd)
>> XNSHADOW_CLIENT_DETACH -> ???
>
> That was the key, now fixed with #4218.
Ok. I think this one is mine. Sorry.
--
Gilles.
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2008-10-13 18:06 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-10-13 13:34 [Xenomai-core] [BUG?] mem leak on slab size-1024 with Xenomai processes Jan Kiszka
2008-10-13 13:49 ` Jan Kiszka
2008-10-13 13:51 ` Philippe Gerum
2008-10-13 14:00 ` Jan Kiszka
2008-10-13 14:13 ` Jan Kiszka
2008-10-13 18:06 ` 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.