Subject: RE: [linux-audio-user] xruns vs. disk activity
From: Mark Knecht (mknecht_AT_controlnet.com)
Date: Wed Apr 30 2003 - 23:55:20 EEST
>
> Thanks for the tips. I have been through the whole hdparm/setpci
> thing, all to
> no avail.
>
> Luckily, Mark Knecht's mail reminded me that I had never got the
> latency test
> program working - so I persevered, and got results (which can be
> found here
> http://homepage.ntlworld.com/robin.fell/ ).
>
> If I understand the output (and Mark's email) correctly I
> probably do have a
> lousy soundcard, though I don't really understand how the program
> guarantees
> to measure my latency woes - so I'm a little reticent to shell
> out 300 notes
> for the terratec I desire.
>
> Being ignorant of the API's used to send sound to the card during it's
> measurements, I don't see how it can tell me anything about how
> well the IDE
> controller is playing with the soundcard on the PCI bus. Can
> anyone explain
> it to me?
>
> Thanks all for your help.
>
> R
Rob,
Looks like you're making a lot of headway. I am struck by how different
your tests and my tests look. Mine are captured on Jan Depner's
configuration pages. The correct page is here:
http://myweb.cableone.net/eviltwin69/Arcana.html#Mark%20Knecht's%20filesyste
m%20tests
Go down to section 2.6 and then to the links, like the one for my ext3
tests:
http://myweb.cableone.net/eviltwin69/Latency_Graphs/ext3_html/3x256.html
Note that my white band (the latency of the disk + CPU) is very tight, while
yours is huge. Very strange.
To understand this plot (at least the way I understand the plot!) the green
line is the amount of time the CPU takes to execute the test when you don't
go to disk. The white is CPU + disk, so that you can see the contributions
of each.
While yours is quite different than mine, still you're disk latencies are
below about 2.1mS. (See info at bottom of each graph.) This means, on paper
anyway, that the disk sub system could run with 3mS latencies from the audio
buffers and you should not have a problem.
However, if I remember your problems, you are getting an xrun every 30
minutes or so. Therefore the chances of you seeing that failure while
running this test is pretty low, assuming it is coming from your disks and
not from something else.
Bottom line, I think the disks are operating OK. Whether a new card is
really going to fix this is another issue.
I had a system here in the office with a SB Audigy in it. I got one xrun, on
the average, about every hour. I turned of crond and they went away
completely. I cannot blame that on the Audigy. I think it was just Linux...
Cheers,
Mark
This archive was generated by hypermail 2b28 : Thu May 01 2003 - 00:16:22 EEST