Subject: Re: [linux-audio-user] Tracking down overruns
From: Mark Knecht (markknecht_AT_comcast.net)
Date: Sun Sep 14 2003 - 01:14:18 EEST
On Sat, 2003-09-13 at 13:16, Benji Flaming wrote:
> Greetings all! I am attempting to initiate a long unattended 2-channel
> audio recording - perhaps lasting for an hour or two - but I am prevented
> from doing so by periodic overruns which occur at regular intervals. This
> interval changes according to my system configuration. Currently, I
> consistently get an overrun about 20 minutes after I start recording.
Pretty interesting. Does it really seem to come after 20 minutes from
when recording started? Or is one maybe happening every 20 minutes?
I do not remember anyone bringing anything like this up before.
> http://www.comevisit.com/NorthernSunrise/latency/test2/3x256.html
The 5 second interval on the disk copy stress test would be the journal
file getting written, I think. The location of the journal file is at a
different place on the disk than the sequential data you're writing, so
the disk head has to seek for that location, causing a bit of delay.
It's not particularly bad.
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.
;-)
> Any help or advice (or reminders about what
> info I've neglected to give) would be very much appreciated!
>
lspci
cat /proc/interrupts
Just more general info on the hardware you are using.
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.
Good luck,
Mark
This archive was generated by hypermail 2b28 : Sun Sep 14 2003 - 01:20:13 EEST