Re: [linux-audio-dev] terrible latencytest results.. why??

New Message Reply About this list Date view Thread view Subject view Author view Other groups

Subject: Re: [linux-audio-dev] terrible latencytest results.. why??
From: Josh Green (jgreen_AT_users.sourceforge.net)
Date: Fri Nov 09 2001 - 04:38:18 EET

On Thu, 2001-11-08 at 07:31, Maarten de Boer wrote:
> Not understanding why I could not get alsa-lib/test/latency.c to work
> well, I decided to run Benno's latency test. It has been a long time
> since I did... The results are surprising, and nothing like the excellent
> results I have seen posted here.
>
> $ ./do_tests none 3 128 0 256
>
> http://193.145.55.36/latencytest/
>
> (yes, I use a very small size for the disk tests, but even then!)
>
> Something is definitely very wrong here. I am running kernel
> 2.4.13 patched with preempt-kernel-rml-2.4.13-2.patch
>
> $ cat /proc/cpuinfo
>
> processor : 0
> vendor_id : AuthenticAMD
> cpu family : 6
> model : 2
> model name : AMD Athlon(tm) Processor
> stepping : 1
> cpu MHz : 704.936
> cache size : 512 KB
> fdiv_bug : no
> hlt_bug : no
> f00f_bug : no
> coma_bug : no
> fpu : yes
> fpu_exception : yes
> cpuid level : 1
> wp : yes
> flags : fpu vme de pse tsc msr pae mce cx8 sep mtrr pge mca cmov pat pse36 mmx fxsr syscall mmxext 3dnowext 3dnow
> bogomips : 1405.74
>
> I will check now what happens with 2.4.14 and Andrews LL patch...
>
> Maarten

I've heard that the PE patch doesn't get as low latency as the LL
patches. The last 3 graphs in your test are rather short, looks like its
because you specified 256 for the disk copy tests. Note that this is in
bytes, so its only reading/writing/copying 256 bytes, which doesn't take
that long :) You probably want 256000000. 

-- 
    Josh Green
    Smurf Sound Font Editor (http://smurf.sourceforge.net)

New Message Reply About this list Date view Thread view Subject view Author view Other groups

This archive was generated by hypermail 2b28 : Fri Nov 09 2001 - 04:32:54 EET