Re: [linux-audio-dev] Re: laptop audio performance chart ... any realworld tests ?

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

Subject: Re: [linux-audio-dev] Re: laptop audio performance chart ... any realworld tests ?
From: Benno Senoner (sbenno_AT_gardena.net)
Date: Tue Jul 10 2001 - 18:25:39 EEST


On Tuesday 10 July 2001 13:59, you wrote:
> I'm experimenting with latencytest on a Dell Inspiron 3800, which uses the
> Maestro 3i PCI for sound (PIII 700Mhz, 256MHz SDRAM, 100Mhz FSB, udma IDE
> drive, ATI Mobility, XFree4.1). Under linux 2.4.5 with the low-latency
> patch and the ext3 patch applied, the best result so far is 8 ms maximum
> latency. (I mounted the filesystem as ext2 before doing the test.)
> Unfortunately, I get tons of overuns at 3x256. I'll see about finding a
> place to post the results.

remember to set the lowlatency entry in /proc to 1 in the case you compiled
the kernel with the sysctl option. (I prefer to compile the ll kernel without
sysctl support .. you never know .. it could slow down things a bit :-) )

>
> The OSS maestro3 driver is still marked EXPERIMENTAL, so it's possible
> (likely?) that the driver is the limiting factor. (In an earlier thread,
> the the problem I was having with using non-blocking writes was with a
> maestro driver.)
>
> Has latencytest been adapted to use alsa natively?

No, but it should not matter it's just a small wrapper over the alsa api
therefore the overhead is negligible.

If you suspect that your soundcard driver might be broken, then run the
RTC latencytest (see the README) if it comes out clean (without significant
spikes) then you might be right about the broken audio driver.
Otherwise the source of the problem lies somewhere else.

Benno.

>
> -chris


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

This archive was generated by hypermail 2b28 : Tue Jul 10 2001 - 18:22:10 EEST