On Friday 06 October 2006 11:48 am, Christopher "Monty" Montgomery wrote:
> > You still don't seem to understand. Kernel latency by itself _cannot_ > > cause a bandwidth reservation to be lost. > > I call bullshit. A single well-placed printk inside the spinlock is > enough latency to cause all the iso streams to lose sync. That > spinlock can also be held be preemptible code. Etc. I saw your followup/correction, but you probably haven't yet seen my post about the EL2NSYNC thing yet. To summarize, in current code (before your patches, which doesn't touch EL2NSYNC as far as I've skimmed them so far): - There are simple cases where the EL2NSYNC is wrongly returned, since the code assumed that all uncompleted ITDs were still active; - Even in cases where it's "correctly" returned, the desirable outcome is to schedule the URB (which previously would have implied possible re-budgeting) instead of failing (which is what made the upper level driver give up the reservation). I'm not sure what what the best way to report that loss-of-synch, but drivers should currently be able to notice it by noticing that urb->start_frame had a hiccup. - Dave ------------------------------------------------------------------------- Take Surveys. Earn Cash. Influence the Future of IT Join SourceForge.net's Techsay panel and you'll get the chance to share your opinions on IT & business topics through brief surveys -- and earn cash http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV _______________________________________________ linux-usb-devel@lists.sourceforge.net To unsubscribe, use the last form field at: https://lists.sourceforge.net/lists/listinfo/linux-usb-devel
