On Wed, Jul 20, 2011 at 12:47:42AM -0400, Sean Collins wrote: > pete.goodeve@xxxxxxxxxxxx wrote: > > >Ouch! (I thought you had at one time said you were getting low latency?) > > I have no idea when it got this bad but I read your email and decided > to check, its getting bad. But, something I overlooked in my last post: you're not experiencing an audio hiatus at boot-up are you? I wonder if the silence only happens on single-core units? Axel -- what's yours? > > >It does seem that the glitches are masked by large buffers. I think they > >can still occur rarely, and latency increases, but the buffers are longer > >than the blackouts, so they cover them quite nicely. > > > I dunno, I know when browsing with webpositive or any other heavy > rendering APP I get glitches on a single core machine I have. Is that HDA/long-latency too? I think the possibility of glitches all depends on how the various buffer sizes (driver and upstream) interact. If the driver buffer always gets filled in time before it actually has to go to the driver, there won't be any crackles. In any case, I'd guess that a multi-core machine might never experience the blackouts, because the core handling the audio would not be bothered by the other one doing the display. > > > > I'd like to try your patchs just to see how they effect my machine. > send me a email with them and I will give them a go. OK, but I don't think you'll actually see any effect. They don't do anything for default latency, and if you aren't hearing glitches they won't improve anything there either. -- Pete --