[pulseaudio-discuss] Latency vs CPU

[Tanu Kaskinen]

On Mon, 2012-01-30 at 07:12 -0500, Sean McNamara wrote:
> So my conclusion is that either
> (A) time-based scheduling isn't implemented for module-null-sink, or
> (B) there is some bug causing this strange behavior.
> 
> In case (A), would it be possible, even in principle, to implement it?
> In case (B), is this a bug that anyone can look into? Can provide as
> much additional info as required.

IIRC, module-null-sink simulates a timer-based sink (due to being a null
sink, it's timer-based anyway, but I think it tries to act similarly to
an alsa sink that uses timer-based scheduling). So it looks like case B.
I can't speak for others, but I probably won't look into this bug myself
in the near future. If you file a bug, I may investigate this at some
later time.

> Maybe there's some other third possibility, but I'm just not expecting
> this kind of behavior out of PA. I thought all the tsched work was to
> help to juggle latency-intensive streams simultaneously with
> high-latency streams without impacting the latter's CPU usage?

At least when there are no low-latency clients, the latency should
return to the higher level. I'm not so sure about whether the current
implementation is supposed to keep the latency high for high-latency
clients when there are low-latency clients at the same time. I think it
should be possible to do that, though, even if the current
implementation doesn't try to achieve that.

-- 
Tanu