Re: [linux-audio-user] Tracking down overruns

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

Subject: Re: [linux-audio-user] Tracking down overruns
From: Benji Flaming (lau_AT_solobanjo.com)
Date: Sun Sep 14 2003 - 01:53:47 EEST


[Note - I accidentally sent a copy of this message from another e-mail
address. I'm sending this copy since I don't expect the first to show up.
Sorry for the double-post if I am mistaken in my expectation.]

On Sat, 13 Sep 2003 15:14:18 -0700, Mark Knecht wrote:

> Pretty interesting. Does it really seem to come after 20 minutes from
> when recording started? Or is one maybe happening every 20 minutes?

I haven't double-checked with my current configuration (I will do so and
confirm) but I did test this with an earlier configuration, and waiting an
arbitrary length of time before initiating recording didn't affect the
length of time before the overrun.

I'm beginning to wonder whether this is related to disk-caching. My theory
would be:

1. System begins recording with an empty cache
2. Cache fills with audio data
3. System flushes cache, attempting to write too much data at once
4. Overrun caused
5. Recording stops
6. Back to 1

This would explain the consistent timing of the overrun, and would
potentially explain the 4 ms spike showing up at exactly the same spot in
both latency tests.

I'm certainly a newcomer to Linux audio configuration, but I do know that
Pro Tools users under MacOS 9 were told to reduce disk cache size. I can't
remember what the recommended size was - somewhere between 256k and 512k
IIRC - but problems would appear if the cache was either too big or too
small. I'll be googling for info on Linux disk cache settings as soon as I
send this message.

> The one time 4mS spike is anybodies guess at this point. Maybe you want
> to look very carefully at every process that's running to see if any of
> them would use your audio drive. While you showed hda and hdb, normally
> that would be two drives on the same IDE cable. If this is how you are
> set up, and presuming that hda is the system and hdb is a second hard
> drive for audio, then I would consider putting the second hard drive on
> a separate IDE cable. If you are recording to your system drive, then
> this spike could be kernel related, or anything else that's mysterious.

hda is Linux, hdb is Windows. I shouldn't have even bothered with specs for
hdb. Sorry for complicating the diagnostic process.

> lspci

http://www.comevisit.com/NorthernSunrise/latency/lspci
(I told it to be verbose)

> cat /proc/interrupts
http://www.comevisit.com/NorthernSunrise/latency/interrupts

Motherboard is an Iwill XP333:
http://www.iwillusa.com/products/ProductDetail.asp?vID=8&CID=93

> BTW - MY opinion is that unless you are doing recording and playback
> together, you should not bother recording with such a low latency
> setting. There is no advantage in getting the audio to disk in 3mS vs.
> 10mS when you are just recording. Even though my system can do 1.2mS And
> seems to work, I never use it. Back off on the buffer size and let the
> system breath a bit.

I certainly could for this particular application. Realtime audio
processing is essential to some of the other things I'll be working on,
however, and for this reason I'm trying to get the problems ironed out now.
:)

Thanks again for the help!

|)
|)enji

Benjamin Flaming
--------------------
"The trouble with computers, of course, is that they're very sophisticated
idiots."


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

This archive was generated by hypermail 2b28 : Sun Sep 14 2003 - 01:59:28 EEST