Subject: Re: [linux-audio-dev] Buffer size settings - Mac/Windows
From: Michael Ost (most_AT_museresearch.com)
Date: Sun Jun 13 2004 - 04:38:10 EEST
On Sat, 2004-06-12 at 17:01, Benno Senoner wrote:
> As said low latencies are cool so everyone tries to cheat and provide
> the per-fragment latencies in their settings/specs.
The MAudio driver setup card was downright dishonest. It said "latency:
128 samples", when actually latency was 256... that should have been
labeled "buffer size" to be more honest.
It then said that 128 samples you will get 2 msec latency at 44.1.
That's 2 msec rounded _down_ from 2.9! And real end-to-end latency
couldn't be any less than 5.8 msecs anyway. We were aghast. It's no
wonder everyone is confused!
Given the MAudio settings, and from asking some people at Apple, we are
now confident that a 128 sample buffer size setting in Windows/Mac
matches up with 2 128 sample fragments in ALSA... I think that's the
ALSA terminology; I didn't work on that bit of code so I'm not sure.
>
> Btw what did you mean with
> "We set the ALSA driver to 2x128 and we get results that jibe more with
> the 256 setting in Windows."
>
> english is my 4th language and dictionary.com was not of too much help
> ----
> jibe:
> To make taunting, heckling, or jeering remarks.
> To deride with taunting remarks.
> ---
'Jibe with' can also mean 'in alignment with'. You seem to do pretty
well with English! That's not a usual usage.
> So let me guess: you meant that 2x128 in ALSA provides lower latency
> than Windows at 256frames ?
I meant that setting the ALSA driver to two 128 sample fragments matches
the real measured latency for the 256 sample setting in Windows.
- mo
This archive was generated by hypermail 2b28 : Sun Jun 13 2004 - 04:33:40 EEST