> I've tried whether having nmi_watchdog has any influence, to no
> distinguishable result; readprofile always says zero times. And
> I'm sure I have LOCAL_APIC=y (see attached config.gz)
Damn, forgot the attachement. Here it goes.
Sorry.
--
rncbc aka Rui Nuno Capela
[EMAIL PROTECTED]
config-2.6
> * Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
>
>> After several trials, with CONFIG_PROFILING=y and profile=1
>> nmi_watchdog=2 as boot parameters, I'm almost convinced I'm doing
>> something wrong :)
>>
>> - `readprofile` always just outputs one line:
>>
>> 0 total
* Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
> After several trials, with CONFIG_PROFILING=y and profile=1
> nmi_watchdog=2 as boot parameters, I'm almost convinced I'm doing
> something wrong :)
>
> - `readprofile` always just outputs one line:
>
> 0 total
> * Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
>
>> OTOH, I'll take this chance to show you something that is annoying me
>> for quite some time. Just look to the attached chart where I've marked
>> the spot with an arrow and a question mark. Its just one example of a
>> strange behavior/phenomenon
> * Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
>
>> OTOH, I'll take this chance to show you something that is annoying me
>> for quite some time. Just look to the attached chart where I've marked
>> the spot with an arrow and a question mark. Its just one example of a
>> strange behavior/phenomenon
* Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
> OTOH, I'll take this chance to show you something that is annoying me
> for quite some time. Just look to the attached chart where I've marked
> the spot with an arrow and a question mark. Its just one example of a
> strange behavior/phenomenon wh
>> -- - -
>> RT-V0.7.51-13 RT-V0.7.49-01
>> -- - -
>
>> Delay Maximum . . . . . . . . : 333 295 usecs
>> Cycle Maximum . . . . . . . .
* Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
> OK.
>
> Just for the heads up, here goes todays summary results regarding my
> jack_test4.2 test suite against 2.6.12 kernels configured with
> PREEMPT_RT, but... now with 99.9% certainty :)
thanks for the testing!
> --
OK.
Just for the heads up, here goes todays summary results regarding
my jack_test4.2 test suite against 2.6.12 kernels configured with
PREEMPT_RT, but... now with 99.9% certainty :)
-- - -
RT-V0.7.51-13 RT-V0.
> * Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
>
>> Hi all,
>>
>> These are one of my latest consolidated results while using (my)
>> jack_test4.2 suite, against a couple of 2.6.12 kernels patched for
>> PREEMPT_RT, on my [EMAIL PROTECTED]/UP laptop.
>>
>> See anything funny?
>
> hm, you dont seem
* Ingo Molnar <[EMAIL PROTECTED]> wrote:
> i have just done a jack_test4.1 run, and indeed larger latencies seem
> to have crept in. (But i forgot to chrt the sound IRQ above the
> network IRQ, so i'll retest.)
with the sound irq chrt-ed to prio 90 the latencies look pretty good:
***
* Rui Nuno Capela <[EMAIL PROTECTED]> wrote:
> Hi all,
>
> These are one of my latest consolidated results while using (my)
> jack_test4.2 suite, against a couple of 2.6.12 kernels patched for
> PREEMPT_RT, on my [EMAIL PROTECTED]/UP laptop.
>
> See anything funny?
hm, you dont seem to have
> Hi all,
>
> These are one of my latest consolidated results while using (my)
> jack_test4.2 suite, against a couple of 2.6.12 kernels patched for
> PREEMPT_RT, on my [EMAIL PROTECTED]/UP laptop.
>
> See anything funny?
>
> As it seems, the kernel latency performance is in some unfortunate
> regre
Hi all,
These are one of my latest consolidated results while using (my)
jack_test4.2 suite, against a couple of 2.6.12 kernels patched for
PREEMPT_RT, on my [EMAIL PROTECTED]/UP laptop.
See anything funny?
As it seems, the kernel latency performance is in some unfortunate
regression, and I'm ex
14 matches
Mail list logo
