On Thu, Apr 17, 2014 at 3:11 AM, michael noble <looplog(a)gmail.com> wrote:
On Thu, Apr 17, 2014 at 3:37 PM, Paul Davis <paul(a)linuxaudiosystems.com>wrote;wrote:
I really don't understand the goal here.
I'm guessing the goal is to see if better performance in driving
softsynths can be obtained by using zita-j2a to handle output rather than
using jack directly interfacing with Alsa. I don't think it was intended to
be a jack1/jack2 match off. To me it seems like an interesting experiment,
and I hope Jonathan keeps up the tests, despite the so far only negative
feedback.
One of the fun things about being an ignorant user is to sometimes try
stuff out just for the heck of it and find things even the original creator
of something didn't intend. If people only followed rules, entire genres of
music wouldn't likely exist, so I say bring on the experimentation.
absolutely agreed.
Which is not to say the tests can't be improved. Apart from criticisms
already raised, from my limited knowledge it seems to essentially be
comparing full-duplex performance of the jack alsa backend with single
duplex performance of zita-j2a, which hardly seems fair. Another question I
have is to whether zita is adding latency in addition to that reported by
jack, which the tests don't seem to indicate.
the zita internal client in jack1 can be configured to any latency
settings, but the default (and optimal) setting matches those of the
server. so in those tests using -A SB, the bridge follows the server
configuration and adds no latency.