Re: [LAD] [Jack-Devel] tschack ... early version of smp enabled jack1

PrevNext  Index
DateThu, 28 Jan 2010 08:01:08 +0100
From Stéphane Letz <[hidden] at grame dot fr>
To"Gabriel M. Beddingfield" <[hidden] at gmail dot com>
CcJACK Developers <[hidden] at lists dot jackaudio dot org>, Linux Audio Developers <[hidden] at lists dot linuxaudio dot org>
Le 28 janv. 2010 à 05:39, Gabriel M. Beddingfield a écrit :

> 
> 
> On Wed, 27 Jan 2010, Stéphane Letz wrote:
> 
>> JACK2 code base can be instrumented (using the "--profile Build with engine profiling" option ) to give more precise understanding of the source of possible Xruns.
>> 
>> See : http://www.grame.fr/Ressources/pub/JACK2_lac2009.pdf
>> 
>> We cannot fix possible issues if they are not reported with some precise infos on what happens.
> 
> I started playing with this -- and this is pretty cool. Great work!
> 
> I had been avoid this because I figured it comes with a performance overhead (like -gprof does).  Or, perhaps it only has overhead when you use it (like Sun's strace). What overhead does compiling with --profile introduce?  Why not have it enabled by default?

It mainly consume additional memory (a big array that is progressively filled with timing measures...), this is why it is off by default.

> 
> Suggestion/Issue:  I have PDF issues with the TimingN.plot (gnuplot) files that it outputs.  They always issue the command 'set terminal pdf' and try to output a PDF file.  These create an error on my system and I have to manually delete them or change them to something like SVG or EPS.

Yep, any suggestion to improve the .plot files? like kind of conditional generation of PDF?
> 
> Apparently, there's a license issue with libpdflite (which gnuplot uses to generate PDFs)... so some distro's won't have it installed.
> 
> Thanks,
> Gabriel


Stéphane
PrevNext  Index

1264662096.30208_0.ltw:2,a <91ED0A70-04A7-4BDF-B26E-2892C98BDBE0 at grame dot fr>