Linux-audio-user June 2011

linux-audio-user@lists.linuxaudio.org

116 participants
128 discussions

[LAU] 2.6.39.1 threadirqs vs. the rest: some numbers

by Fernando Lopez-Lezcano

Hi all, I just built a threaded-irqs enabled 2.6.39.1 kernel and used cyclictest to try to get an initial feeling of how good it might be. Cyclictest tests scheduling delays of the kernel it is running on[*]. These tests were run on a Fedora 13 T510 Lenovo laptop, with the ugly binary Nvidia driver (caveat emptor). In the menu: 2.6.39.1 with threaded irqs and PREEMPT active 2.6.33.13-rt31 2.6.34.8-rt31 (a forward port of rt31 to 2.6.34) plain Fedora kernel (2.6.34.8-68.fc13.i686.PAE) Now, before someone points it out, this is just a synthetic test that measures scheduling latency, not a real audio application. See below for details... (look at the "Avg:" and "Max:" latency values, those are in microseconds) Unless I have done something wrong, it looks like we have a long way to go with regards to scheduling latency in anything other than 2.6.33 + rt patches. But, with threaded irqs in 2.6.39 maybe the performance with audio applications running under jack will be good anyway as we will be able to tune irq processing. Seems to me unlikely. I have not tested that yet. Tests were done after a clean reboot, initially with the machine idle and then while loading thunderbird with tons of emails and firefox with tons of pages. No audio work. YMMV... -- Fernando [*] https://rt.wiki.kernel.org/index.php/RT_PREEMPT_HOWTO ---------------------------------------------------------------------- LENOVO T510 ---------------------------------------------------------------------- 2.6.33.13-149.rt31.2.fc13.ccrma.i686.rtPAE ---------------------------------------------------------------------- $ while true ; do ./cyclictest -t1 -p 80 -n -i 10000 -l 10000 ; done policy: fifo: loadavg: 0.02 0.20 0.11 1/405 7024 T: 0 ( 7024) P:80 I:10000 C: 10000 Min: 3 Act: 75 Avg: 54 Max: 121 policy: fifo: loadavg: 0.08 0.17 0.10 2/405 7027 T: 0 ( 7026) P:80 I:10000 C: 10000 Min: 3 Act: 73 Avg: 75 Max: 126 policy: fifo: loadavg: 0.01 0.12 0.09 1/405 7029 T: 0 ( 7029) P:80 I:10000 C: 10000 Min: 3 Act: 90 Avg: 49 Max: 141 policy: fifo: loadavg: 0.37 0.21 0.12 1/405 7031 T: 0 ( 7031) P:80 I:10000 C: 10000 Min: 4 Act: 70 Avg: 76 Max: 148 policy: fifo: loadavg: 0.27 0.21 0.12 1/405 7033 T: 0 ( 7033) P:80 I:10000 C: 10000 Min: 4 Act: 46 Avg: 73 Max: 144 policy: fifo: loadavg: 0.15 0.20 0.12 1/405 7035 T: 0 ( 7035) P:80 I:10000 C: 10000 Min: 3 Act: 90 Avg: 77 Max: 142 policy: fifo: loadavg: 0.07 0.15 0.11 2/405 7037 T: 0 ( 7037) P:80 I:10000 C: 10000 Min: 3 Act: 16 Avg: 71 Max: 135 policy: fifo: loadavg: 0.05 0.12 0.10 1/405 7040 T: 0 ( 7039) P:80 I:10000 C: 10000 Min: 3 Act: 84 Avg: 72 Max: 142 policy: fifo: loadavg: 0.01 0.08 0.08 1/405 7042 T: 0 ( 7042) P:80 I:10000 C: 10000 Min: 3 Act: 105 Avg: 51 Max: 146 policy: fifo: loadavg: 0.00 0.05 0.07 1/406 7045 T: 0 ( 7044) P:80 I:10000 C: 10000 Min: 4 Act: 11 Avg: 50 Max: 121 policy: fifo: loadavg: 0.07 0.06 0.07 1/406 7047 T: 0 ( 7047) P:80 I:10000 C: 10000 Min: 2 Act: 73 Avg: 76 Max: 140 policy: fifo: loadavg: 0.01 0.04 0.06 1/406 7049 T: 0 ( 7049) P:80 I:10000 C: 10000 Min: 3 Act: 67 Avg: 70 Max: 137 policy: fifo: loadavg: 0.02 0.04 0.06 1/406 7051 T: 0 ( 7051) P:80 I:10000 C: 9573 Min: 3 Act: 68 Avg: 47 Max: 146 policy: fifo: loadavg: 0.02 0.04 0.06 1/406 7053 ---------------------------------------------------------------------- 2.6.34.8-68.fc13.i686.PAE ---------------------------------------------------------------------- $ while true ; do ./cyclictest -t1 -p 80 -n -i 10000 -l 10000 ; sleep 10; done policy: fifo: loadavg: 0.20 0.33 0.15 1/298 2559 T: 0 ( 2521) P:80 I:10000 C: 10000 Min: 3 Act: 12 Avg: 36 Max: 354 policy: fifo: loadavg: 0.34 0.30 0.16 1/332 2676 T: 0 ( 2583) P:80 I:10000 C: 10000 Min: 3 Act: 12 Avg: 31 Max: 1749 policy: fifo: loadavg: 0.39 0.38 0.20 1/350 2835 T: 0 ( 2726) P:80 I:10000 C: 10000 Min: 2 Act: 9 Avg: 33 Max: 12861 policy: fifo: loadavg: 0.11 0.29 0.18 2/350 2839 T: 0 ( 2838) P:80 I:10000 C: 10000 Min: 3 Act: 12 Avg: 43 Max: 133 policy: fifo: loadavg: 0.02 0.19 0.16 1/348 2842 T: 0 ( 2842) P:80 I:10000 C: 10000 Min: 4 Act: 75 Avg: 48 Max: 17789 policy: fifo: loadavg: 0.07 0.15 0.14 1/347 2858 T: 0 ( 2845) P:80 I:10000 C: 10000 Min: 4 Act: 56 Avg: 50 Max: 1808 policy: fifo: loadavg: 0.18 0.15 0.14 1/347 2861 T: 0 ( 2861) P:80 I:10000 C: 10000 Min: 3 Act: 11 Avg: 52 Max: 187 policy: fifo: loadavg: 0.34 0.19 0.15 1/345 2864 T: 0 ( 2864) P:80 I:10000 C: 10000 Min: 4 Act: 69 Avg: 46 Max: 119 policy: fifo: loadavg: 0.39 0.28 0.19 1/346 2869 T: 0 ( 2867) P:80 I:10000 C: 10000 Min: 3 Act: 14 Avg: 27 Max: 361 policy: fifo: loadavg: 0.10 0.20 0.17 1/347 2875 T: 0 ( 2872) P:80 I:10000 C: 10000 Min: 4 Act: 14 Avg: 31 Max: 425 policy: fifo: loadavg: 0.01 0.13 0.15 1/346 2882 T: 0 ( 2879) P:80 I:10000 C: 10000 Min: 4 Act: 58 Avg: 55 Max: 186 policy: fifo: loadavg: 0.09 0.12 0.13 1/346 2887 T: 0 ( 2885) P:80 I:10000 C: 10000 Min: 4 Act: 67 Avg: 50 Max: 129 policy: fifo: loadavg: 0.10 0.12 0.13 1/347 2890 ---------------------------------------------------------------------- 2.6.39.1-1.threadirqs.1.fc14.ccrma.i686.PAE ---------------------------------------------------------------------- $ while true ; do ./cyclictest -t1 -p 80 -n -i 10000 -l 10000 ; sleep 10; done policy: fifo: loadavg: 0.13 0.25 0.12 1/290 2279 T: 0 ( 2279) P:80 I:10000 C: 10000 Min: 5 Act: 42 Avg: 45 Max: 1015 policy: fifo: loadavg: 0.64 0.36 0.18 1/338 2567 T: 0 ( 2299) P:80 I:10000 C: 10000 Min: 4 Act: 48 Avg: 44 Max: 3124 policy: fifo: loadavg: 0.20 0.30 0.18 1/337 2583 T: 0 ( 2571) P:80 I:10000 C: 10000 Min: 3 Act: 43 Avg: 50 Max: 10301 policy: fifo: loadavg: 0.07 0.22 0.16 2/341 2592 T: 0 ( 2586) P:80 I:10000 C: 10000 Min: 5 Act: 30 Avg: 46 Max: 15227 policy: fifo: loadavg: 0.48 0.33 0.21 3/340 2602 T: 0 ( 2595) P:80 I:10000 C: 10000 Min: 4 Act: 7 Avg: 29 Max: 992 policy: fifo: loadavg: 0.17 0.28 0.21 1/340 2613 T: 0 ( 2610) P:80 I:10000 C: 10000 Min: 3 Act: 15 Avg: 32 Max: 99 policy: fifo: loadavg: 0.34 0.27 0.21 4/346 2660 T: 0 ( 2616) P:80 I:10000 C: 10000 Min: 3 Act: 14 Avg: 36 Max: 1326 policy: fifo: loadavg: 0.14 0.25 0.22 2/342 2680 T: 0 ( 2665) P:80 I:10000 C: 10000 Min: 3 Act: 14 Avg: 38 Max: 709 policy: fifo: loadavg: 0.18 0.24 0.22 1/342 2687 T: 0 ( 2683) P:80 I:10000 C: 10000 Min: 4 Act: 17 Avg: 44 Max: 17692 policy: fifo: loadavg: 0.15 0.23 0.22 1/343 2690 ---------------------------------------------------------------------- 2.6.34.8-68.rt0.3.fc13.ccrma.i686.rtPAE ---------------------------------------------------------------------- while true ; do ./cyclictest -t1 -p 80 -n -i 10000 -l 10000 ; sleep 10; done policy: fifo: loadavg: 0.19 0.30 0.13 1/355 2561 T: 0 ( 2542) P:80 I:10000 C: 10000 Min: 3 Act: 27 Avg: 33 Max: 143 policy: fifo: loadavg: 0.03 0.20 0.11 1/354 2565 T: 0 ( 2564) P:80 I:10000 C: 10000 Min: 6 Act: 15 Avg: 55 Max: 135 policy: fifo: loadavg: 0.53 0.27 0.14 3/401 2780 T: 0 ( 2568) P:80 I:10000 C: 10000 Min: 3 Act: 9 Avg: 21 Max: 134 policy: fifo: loadavg: 0.50 0.39 0.20 1/405 2899 T: 0 ( 2869) P:80 I:10000 C: 10000 Min: 3 Act: 66 Avg: 36 Max: 119 policy: fifo: loadavg: 0.13 0.28 0.18 1/404 2902 T: 0 ( 2902) P:80 I:10000 C: 10000 Min: 3 Act: 48 Avg: 31 Max: 116 policy: fifo: loadavg: 0.10 0.27 0.17 1/405 2905

14 years, 5 months

[LAU] LV2 synths for Ardour 3?

by Leigh Dyer

Hi all, With Ardour 3 coming along, and looking set to support only LV2 synth plugins, I've just been writing up some notes on the various LV2 synth plugins that are around at the moment. I've listed them here: http://wootangent.net/2011/06/lv2-synths-for-ardour-3-a-list/ I hope I've covered all the big ones, but are there any that I'm missing? I'd love for this to be a handy resource for new users when Ardour hits the big 3.0. Thanks Leigh

14 years, 5 months

[LAU] Le Puzzle du Batteur - The Drummer's 'G'igsaw: GNU Bash + GNU sed replace gvim

by Phil Hézaine

Le Puzzle du Batteur - The Drummer's 'G'igsaw ***** Polymetric editor for Drums and Percussions based on Lilypond + GUI for randomization. (midi timing and/or volume) ****** PACKAGES You have to install: GNU Lilypond >= 2.12.0 http://lilypond.org/web/install/ midicomp 0.0.4 http://midicomp.opensrc.org/midicomp-0.0.4.tar.gz (compile in /usr/local/midicomp... and move midicomp.bin in /usr/local/bin Python 2.6.x with Tk option activated. Already in your Linux distribution. GNU Bash and GNU sed 4.2 by default in your Linux distribution. As default midi config I use Timidity++ 2.13.2 with eawpatches. ****** INSTALLATION Untar the archive. (tar jxvf ....) In your terminal go to your Drummer-s-Gigsaw's repertory. cd /home/....../Drummer-s-Gigsaw and run the bash script: sh INSTALL.sh You are done. ****** * In this new version you no longer need to gvim. Thus you can use your preferred text editor or even a dedicated editor like Frescobaldi or Lilypondtool... * Now you can write all notes values, from whole note (1) up to * one-hundred-and-twenty-eighth note (128) and even dotted values. * The manual is updated. (translated in my terrible English) * Le Puzzle du Batteur/The Drummer's 'G'igsaw is under GPLv3 or + ****** This new version at: http://philippe.hezaine.free.fr/spip.php?article46 Have fun. Phil.

14 years, 6 months

[LAU] Petri-Foo preview release: 0.0.2

by James Morris

Hello hello, The second official source code release Petri-Foo is now available. IMPORTANT: I have designated this release as a 'preview' release to indicate this is still a work in progress so that users may be aware things may change and their files may not be usable without alteration in future versions. HOWEVER: I feel Petri-Foo has moved along quite nicely since 0.0.1 in April and would like to share that work with a few more of you than are subscribed to the Petri-Foo developers list. WHAT'S NEW.... and good (since 0.0.1): * Default Patch A default patch using a looped generated triangle wave sample, with an ADSR, LFO, and MIDI CC setup with sensible/default values so a new user can immediately hear audio. * Selectable MIDI controllers MIDI controllers are now selectable amongst all the other modulation sources. This has two benefits, the first is being given the choice (of course), and the second is that you can now control how much effect the controller has. * Patchlist context menu You can now right-click on the patch list to get a context menu to allow you to perform add, remove, rename, and duplicate operations on patches. * Keyboard tracking Keyboard tracking has been added to all the parameters, and additionally, to the envelopes where it modifies envelope duration. * LFO Amplitude modulation The LFOs now have amplitude modulation so that. For example, the default patch uses this in combination with the MIDI Mod Wheel controller to control pitch modulation. * RAW sample format loading Allows one to load files never intended to be heard :-) * Removal of LASH support * Removal of ALSA *audio* output (note: ALSA MIDI still supported) * Miscellaneous bug fixes and GUI clean ups. Home pages... http://petri-foo.sourceforge.net http://github.com/jwm-art-net/Petri-Foo Download... http://sourceforge.net/projects/petri-foo/files/Source/petri-foo-0.0.2.tar.… git clone git://github.com/jwm-art-net/Petri-Foo.git Bug reports... https://sourceforge.net/tracker/?group_id=404816 jwm.art.net(a)gmail.com Mailing list... https://lists.sourceforge.net/lists/listinfo/petri-foo-devel please note, if you're not a member your messages ****are automatically rejected**** :-p cheers, regards, James.

14 years, 6 months

[LAU] qjackctl does not reflect state of jackd

by Eric Steinberg

Hi folks, I'm trying to build an audio logger, that can record from six different sources to separate files. I've been using the program rotter, and I thought it was working but have discovered that jackd crashed and recording was interrupted. Unfortunately this was not reflected by qjackctl, which is what I use to launch jackd. The qjackctl display showed that jackd was running, right down to the flashing "RT", but when I tried to launch meterbridge it complained that the jack server was not running. The instances of rotter that I launched were still running, but were making files of just a few bytes, with no audio in them. Is this a bug in qjackctl? I am using Arch, on a Pentium 4, and using a firewire interface (Edirol FA-101). -Steiny (415)819-2009

14 years, 6 months

[LAU] Text-based sound visualisation?

by S. Massy

Hello, Recently, I discovered jack_meter, a simple jack client which acts as a level meter and has a very simple "bar" style text output. Using this, I was able to confirm what my ears were telling me about compression level in different mixes. This led me to wonder whether there were any sound visualisation tools using a similar form of output. A quick google search didn't return anything interesting, but I was wondering if anyone here knew of such a tool. Cheers, S.M. --

14 years, 6 months

[LAU] Patch for qmidiarp-0.4.1

by Frank Kober

Mainly two important issues regarding external synchronization and running stability with only Seq and Lfo modules are fixed by the qmidiarp-0.4.1-fixes.patch file available from the 0.4.1 Download directory. I'd like to thank Louigi Verona, Brendan Jones and Jeremy Jongepier for quickly reporting and insisting on these overseen issues. Please apply this patch to 0.4.1 before building / distributing Frank ----------------- QMidiArp is available for download at http://sourceforge.net/projects/qmidiarp/files/qmidiarp/0.4.1/ Project page http://qmidiarp.sourceforge.net/ Git repo (developers welcome) git://qmidiarp.git.sourceforge.net/gitroot/qmidiarp/qmidiarp

14 years, 6 months

[LAU] Experimental? Ambient?

by Folderol

This is a totally new direction for me, inspired by memories of when I was a child and held my ear to telegraph poles and was awed by the sounds of the wires. http://www.musically.me.uk/music/Wires.ogg -- Will J Godfrey http://www.musically.me.uk Say you have a poem and I have a tune. Exchange them and we can both have a poem, a tune, and a song.

14 years, 6 months

Re: [LAU] Kernel 2.6.39

by Ralf Mardorf

On Thu, 2011-06-23 at 12:00 +0000, linux-audio-user-request(a)lists.linuxaudio.org wrote: > > Message: 1 > Date: Thu, 23 Jun 2011 08:42:15 +0100 > From: Rui Nuno Capela <rncbc(a)rncbc.org> > Subject: Re: [LAU] Kernel 2.6.39 > To: linux-audio-user(a)lists.linuxaudio.org > Message-ID: <4E02EE57.7020003(a)rncbc.org> > Content-Type: text/plain; charset=ISO-8859-1; format=flowed > > On 06/23/2011 07:17 AM, Ralf Mardorf wrote: > > > > I used the config from the self-build kernel 2.6.33.9-rt31 and run > > oldconfig only to configure 2.6.39. I didn't make music until now using > > this kernel. Yes, I wish to "emulate" the PREEMPT_RT, since common > > PREEMPT only kernels never did, what I needed. > > > > What do I need to set? > > > > $ cat config-2.6.39.1 | grep PREEMPT > > CONFIG_TREE_PREEMPT_RCU=y > > CONFIG_PREEMPT_RCU=y > > CONFIG_PREEMPT_NOTIFIERS=y > > # CONFIG_PREEMPT_NONE is not set > > # CONFIG_PREEMPT_VOLUNTARY is not set > > CONFIG_PREEMPT=y > > > > IIUC this is correct?! > > > > yes. > > and don't forget to add "threadirqs" to your kernel bootloader > line--only then you'll get "rtirq" to do its magic as it used to do on a > genuine -rt kernel. > > > > > > PS: SCHED_FF? > > > > SCHED_FF is a process/thread attribute, not a kernel configuration > option--jack does that for you when told to run with realtime scheduling. > > > byee > -- > rncbc aka Rui Nuno Capela > rncbc(a)rncbc.org > > > ------------------------------ > > Message: 2 > Date: Thu, 23 Jun 2011 00:59:29 -0700 (PDT) > From: James Warden <warjamy(a)yahoo.com> > Subject: Re: [LAU] Kernel 2.6.39 > To: linux-audio-user(a)lists.linuxaudio.org > Message-ID: > <1308815969.6124.YahooMailClassic(a)web39321.mail.mud.yahoo.com> > Content-Type: text/plain; charset=us-ascii > > > > --- On Thu, 6/23/11, Rui Nuno Capela <rncbc(a)rncbc.org> wrote: > > > From: Rui Nuno Capela <rncbc(a)rncbc.org> > > Subject: Re: [LAU] Kernel 2.6.39 > > To: linux-audio-user(a)lists.linuxaudio.org > > Date: Thursday, June 23, 2011, 3:42 AM > > On 06/23/2011 07:17 AM, Ralf Mardorf > > wrote: > > > > > > I used the config from the self-build kernel > > 2.6.33.9-rt31 and run > > > oldconfig only to configure 2.6.39. I didn't make > > music until now using > > > this kernel. Yes, I wish to "emulate" the PREEMPT_RT, > > since common > > > PREEMPT only kernels never did, what I needed. > > > > > > What do I need to set? > > > > > > $ cat config-2.6.39.1 | grep PREEMPT > > > CONFIG_TREE_PREEMPT_RCU=y > > > CONFIG_PREEMPT_RCU=y > > > CONFIG_PREEMPT_NOTIFIERS=y > > > # CONFIG_PREEMPT_NONE is not set > > > # CONFIG_PREEMPT_VOLUNTARY is not set > > > CONFIG_PREEMPT=y > > > > > > IIUC this is correct?! > > > > > > > yes. > > > > and don't forget to add "threadirqs" to your kernel > > bootloader > > line--only then you'll get "rtirq" to do its magic as it > > used to do on a > > genuine -rt kernel. > > > > And remember to use /etc/default/grub to have this threadirqs boot option permanent: > > /etc/default/grub : GRUB_CMDLINE_LINUX="threadirqs" > > if you are too lazy to compile / recompile /etc, just use the liquorix debian kernel (http://liquorix.net/) > > I use that one (kernel compiled with CONFIG_PREEMPT=y, threadirqs at boot). It does wonders! I tried the cyclictest mentioned by Rui and I got some quite outstanding numbers on my system. > > > (However, the liquorix kernel is not PAE, which prevents the use of more than 4GB RAM for 32bit systems with more than 4GB of physical RAM) > > J. spinymouse@debian:/boot$ less config-2.6.39.1 | grep ONFIG_IRQ_FORCED_THREADING CONFIG_IRQ_FORCED_THREADING=y So I don't need to re-build the kernel? PAE is irrelevant for me, hence I'm using 64-bit architecture. Hm, less seems to be less comfortable, I hope I'm allowed to use cat instead. $ less /etc/default/grub ... needs to copies, so I fall back to cut, it needs just one copy. $ cat /etc/default/grub # If you change this file, run 'update-grub' afterwards to update # /boot/grub/grub.cfg. # For full documentation of the options in this file, see: # info -f grub -n 'Simple configuration' GRUB_DEFAULT=0 GRUB_TIMEOUT=5 GRUB_DISTRIBUTOR=`lsb_release -i -s 2> /dev/null || echo Debian` GRUB_CMDLINE_LINUX_DEFAULT="quiet" GRUB_CMDLINE_LINUX="" So I need to add GRUB_CMDLINE_LINUX="threadirqs" ? Thanks, Ralf OT: > Oberhausen at 11:30 Julien, this is the Ruhrgebiet city I'm living :D.

14 years, 6 months

[LAU] Best file system for audio?

by S. Massy

Hello, all, I know this topic comes up now and again. I'm about to create a partition for audio work and am wondering whether any new consensus has been reached over which is the best file system format for the job. What are you, fellows using? Cheers, S.M. -- --

14 years, 6 months

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

Linux-audio-user June 2011