Resolved JACK issues on notebook

Finally got around troubleshooting the issues I was facing with JACK on my notebook, a BTO that is actually a Clevo W170ER. Somehow I couldn’t go lower than -p128 with USB audio interfaces. When I thought I had tried every option, even disabling hyperthreading, I noticed two unidentified entries in my lsusb output:

Bus 001 Device 003: ID 8087:07da Intel Corp. 
Bus 002 Device 003: ID 5986:0401 Acer, Inc

The first entry is a Bluetooth adapter and the second entry is a webcam. Both devices are unnecessary when making music so I thought, why not unbind them. First I had to figure out their respective bus ID’s:

$ tree /sys/bus/usb/drivers/usb
/sys/bus/usb/drivers/usb
??? 1-1 -> ../../../../devices/pci0000:00/0000:00:1a.0/usb1/1-1
??? 1-1.3 -> ../../../../devices/pci0000:00/0000:00:1a.0/usb1/1-1/1-1.3
??? 2-1 -> ../../../../devices/pci0000:00/0000:00:1d.0/usb2/2-1
??? 2-1.6 -> ../../../../devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1.6
??? bind
??? uevent
??? unbind
??? usb1 -> ../../../../devices/pci0000:00/0000:00:1a.0/usb1
??? usb2 -> ../../../../devices/pci0000:00/0000:00:1d.0/usb2
??? usb3 -> ../../../../devices/pci0000:00/0000:00:14.0/usb3
??? usb4 -> ../../../../devices/pci0000:00/0000:00:14.0/usb4

Since the Bluetooth adapter sits on bus 1 and the webcam on bus two their respective ID’s should be 1-1 and 2-1. So I echoed the ID’s to the unbind file in the same directory:

$ echo -n "1-1" | sudo tee /sys/bus/usb/drivers/usb/unbind
$ echo -n "2-1" | sudo tee /sys/bus/usb/drivers/usb/unbind

Good riddance:

$ lsusb
Bus 001 Device 002: ID 8087:0024 Intel Corp. Integrated Rate Matching Hub
Bus 002 Device 002: ID 8087:0024 Intel Corp. Integrated Rate Matching Hub
Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 002 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 003 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
Bus 004 Device 001: ID 1d6b:0003 Linux Foundation 3.0 root hub

Then I started JACK again with -p64 using an USB audio interface connected to bus 3 (so no rate matching hub in between) and no more xruns, not even with a generic kernel and using WiFi and all. Next hurdle is the onboard sound. Below -p128 I get bursts of massive xruns and so far I didn’t manage to pinpoint the culprit.

Edit #1: I’ve found out that the Bluetooth adapter is the main bottleneck. Also, by echoing the aformentioned ID’s (1-1 and 2-1) you disable the whole USB bus apparently. To disable just the USB device echo the last ID in the respective path names, so for the Bluetooth adapter that’s 1-1.3 and for the webcam 2-1.6. This way you can still use the USB bus on which these devices are residing. In my case disabling the whole bus is not an option, this would mean I’d have to connect all my USB interfaces to bus 3 (bus 4 doesn’t have any external inputs) which could result in these devices getting in each other’s way with regard to bandwidth. After echoing the ID’s the output of the tree command looks like this:

$ tree /sys/bus/usb/drivers/usb
/sys/bus/usb/drivers/usb
??? 1-1 -> ../../../../devices/pci0000:00/0000:00:1a.0/usb1/1-1
??? 2-1 -> ../../../../devices/pci0000:00/0000:00:1d.0/usb2/2-1
??? bind
??? uevent
??? unbind
??? usb1 -> ../../../../devices/pci0000:00/0000:00:1a.0/usb1
??? usb2 -> ../../../../devices/pci0000:00/0000:00:1d.0/usb2
??? usb3 -> ../../../../devices/pci0000:00/0000:00:14.0/usb3
??? usb4 -> ../../../../devices/pci0000:00/0000:00:14.0/usb4

The lsusb command still shows the devices though.

Edit #2: unbinding drivers like described above won’t persist across reboots. If you’d like to make the unbinding persistent you could add the unbind command to /etc/rc.local or create a script that runs at login. There are other options of course like blacklisting the Bluetooth drivers.

Resolved JACK issues on notebook

Hacking an Android TV stick, the sequel

jeremy@rk3066:~$ uname -a
Linux rk3066 3.0.36-rt58 #1 SMP PREEMPT RT Thu Jul 4 13:18:23 CEST
2013 armv7l GNU/Linux

Managed to compile and run a real-time kernel on the Android TV stick with the RK3066 SoC. Packaged the latest version of amSynth (1.4.0 which has been released recently), installed it, fired up JACK and amSynth and so far no xruns, nothing. And this is with -p64!

jackd -P84 -p32 -t2000 -dalsa -dhw:Device -n3 -p64 -r44100 -s -P

I should measure the latency of the $2 USB audio interface I’m using to find out what the total latency of this set-up is. Well, at least I got the system latency for usage with softsynths like amSynth down to 64/44100*2=3ms. Now that’s a usable situation.

jeremy@rk3066:~$ lsusb | grep -i c-media
Bus 002 Device 006: ID 0d8c:000e C-Media Electronics, Inc. Audio Adapter (Planet
UP-100, Genius G-Talk)
jeremy@rk3066:~$ cat /proc/asound/cards 0 [RK29RK1000 ]: RK29_RK1000 - RK29_RK1000 RK29_RK1000 1 [HDMI ]: ROCKCHIP_HDMI - ROCKCHIP HDMI ROCKCHIP HDMI 2 [Device ]: USB-Audio - Generic USB Audio Device Generic USB Audio Device at usb-usb20_host-1.1, full speed

A big pro of this stick is that it suffers less from SD card corruption than my RPi. Yesterday evening I wrecked up yet another SD card when testing my RPi with a real-time kernel, it’s getting a bit cumbersome. Speaking of real-time kernels, it was quite some work to apply the RT patchset to the RockChip kernel source. Had to add stuff by hand and when I finally got everything in place it wouldn’t compile. But I managed to solve all the build errors. After flashing the kernel image the TV stick wouldn’t boot of course, it hung at some point. But I quickly saw that the issue was with the SD card reader and that it was similar to the SD card reader issue on the RPi for which I found a workaround. So I added an #ifdef clause to the RockChip SD card reader driver, recompiled, reflashed and wham, it continued booting. Now I have to clean up my build directory and get a usable diff of it against the pristine RK3066 kernel sources.

Hacking an Android TV stick, the sequel

ZASFX? PHASEX!

Weet je, eigenlijk vind ik PHASEX ([P]hase [H]armonic [A]dvanced [S]ynthesis [EX]periment) een veel fijnere softsynth dan ZynAddSubFX:

  • MIDI Learn, dus elke knopje in PHASEX is aan te sturen via MIDI. In ZynAddSubFX kun je een paar dingetjes aansturen via MIDI, in PHASEX gewoon alles.
  • Echte arpeggio’s, die arpeggio presets in ZynAddSubFX zijn niet meer dan een toon met een echootje.
  • Geen gekraak en geen xruns bij het wisselen van presets/patches. OK, ZASFX 2.4.0 heeft geen last meer van xruns bij het wisselen van presets maar het kraakt nog steeds wel aan alle kanten wat behoorlijk irritant is. PHASEX heeft hier nagenoeg geen last van.
  • Mogelijkheid om presets/patches te wisselen via MIDI. In ZASFX kan dit alleen met de muis.
  • Één overzichtelijk scherm waar je alles in kan stellen ipv al die losse schermpjes. Scheelt ook een hoop geklik, in ZASFX moet je soms wel 20x klikken om iets in te stellen.
  • GTK GUI ipv dat afgrijselijke FLTK.

ZynAddSubFX heeft natuurlijk ook zijn pro’s, zoals de vele presets en de enorme hoeveelheid mogelijkheden, maar vanwege de complexiteit werkt het wel een stuk minder intuïtief.

[P]hase [H]armonic [A]dvanced [S]ynthesis [EX]periment

ZASFX? PHASEX!

Die vermaledijde xruns!

Je kent het wel, ben je lekker met JACK bezig, hang je Audacity er aan, beetje editten en in ene wordt het je systeempje te veel. Gevolg: xruns, xruns en nog meer xruns. Op mijn netbookje heb ik hier dus last van en waarschijnlijk ligt dat aan een brakke geluids- of codecmodule. Ik heb er maar een soort van noodknop voor gemaakt die de gehele soundstack opnieuw laadt. Daarna zijn de xruns gelukkig weer weg. Ik moet maar eens gaan uitzoeken hoe die ALSA drivers nou precies aan de kernel hangen, zijn het nou kernel afhankelijke modules of staan ze los van de kernel die je gebruikt? Het moet wel allemaal een beetje stabiel draaien, juist ook met het onboard geluidskaartje, ik ga niet de hele tijd een externe geluidskaart meeslepen.

De noodknop is eigenlijk niet meer dan een scriptje (heb het maar restartsound genoemd) dat alle geluidsmodules uit de kernel trekt, alsa stopt, de modules weer laadt en alsa weer opstart.

Die vermaledijde xruns!