[64studio-devel] [64 Studio] #287: Possible kernel regression with high jackd sample rates in 32-bit version

[Dick Wright]

Hello Daniel

I have captured the data as requested. Please see the attached files. 
They show that both jack and Ardour consume more processor power in 
64Studio 1.4 compared to Demudi 1.3.

Incidentally, Demudi 1.3 used kernel version 2.6.14.

Regards

Dick
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Top Snap Demudi1.3
Type: application/octet-stream
Size: 1234 bytes
Desc: Top Snap Demudi1.3
Url : http://lists.64studio.com/pipermail/64studio-devel/attachments/20070615/ccafbe7a/attachment-0002.obj 
-------------- next part --------------

-------------- next part --------------
A non-text attachment was scrubbed...
Name: Top Snap 64Studio1.4
Type: application/octet-stream
Size: 1745 bytes
Desc: Top Snap 64Studio1.4
Url : http://lists.64studio.com/pipermail/64studio-devel/attachments/20070615/ccafbe7a/attachment-0003.obj 
-------------- next part --------------


In message <466E87F9.3070402 at 64studio.com>, Daniel James 
<daniel at 64studio.com> writes
>Hi Dick,
>
>> I have just run a comparison of loading using Ardour using various 
>>versions on my hardware. I played back a four-channel recording with 
>>three effect at 44.1 k and 128 sample buffer, 5.8 milliseconds delay. 
>>On DeMudi it used 33% processor and on 64Studio 1.4, kernel 2.6.19 it 
>>uses  58% and similar with 2..6.19.
>
>Thanks for running these tests! My best guess is that the DeMuDi kernel 
>had some optimisation for 32-bit CPUs that we aren't using in our 
>32-bit build. Either that, or the 2.6 kernel just isn't as efficient as 
>the 2.4 kernel, assuming you are running 2.4 on DeMuDi - this seems 
>much less likely though.
>
>Would it be possible for you to snapshot the CPU load of the processes 
>on each system under load, to help us track down where the big 
>differences are?
>
>If you run the 'top' command in a terminal, hit shift-P to sort by CPU 
>load, and take a screenshot, that would be a start. I bet there are 
>much better ways of performance profiling though; perhaps someone on 
>the list could enlighten us :-)
>
>> My system is a 1.8GHz Athlon with an nforce 2 chip set and 1G ram.
>
>It's just possible that one of the drivers you rely on is buggy, and 
>consuming way more CPU than it should in recent kernels.
>
>Cheers!
>
>Daniel

-- 
Regards

Dick Wright