Subject: Re: [linux-audio-dev] Re: [DATAPOINT] kernels and latencies
From: Benno Senoner (sbenno_AT_gardena.net)
Date: Tue Jul 04 2000 - 17:14:02 EEST
On Tue, 04 Jul 2000, Andrew Morton wrote:
>
> True, but sys_mmap() is not appearing on the radar screen.
>
> The point the audio guys have been making is that they require
> reasonable latency on a *dedicated machine*. That changes the game a
> lot.
sorry I do not understand: what do you mean with a dedicated machine ?
the mmap() case has to be handled as well, or we will still be in a situation
where linux will be unsuitable for professional work.
>
> I'll take a peek at sys_msync(), but I think "don't do that" is a
> solution here.
I disagree here, who can ensure that while doing low-latency work
you don't do this and that and that other ?
a low-latency OS means that it can achieve reasonable (1-5ms) under
high load conditions (at least for ONE SCHED_FIFO task),
all the other solutions not acceptable and I prefer to work with high
latencies reliably rather than having low latencies with a nice
crackle/noise floor in the audio stream.
>
> Pretty soon, I'll ask the audio people to put their money where their
> mouthes are, and start testing, analysing and helping to "file off the
> high spots".
Yes this is a good strategy, at least we will see which
"random pre-emption points" are pretty useless.
>
> In the meanwhile, this probably means that people who require low
> latency will need to buy an RS232 mouse. That's OK.
PS2 is causing high latencies, on std kernels, Ingo's kernel handles this just
nicely.
Benno.
This archive was generated by hypermail 2b28 : Tue Jul 04 2000 - 17:48:59 EEST