Markus Trippelsdorf wrote: > On 2011.11.02 at 13:15 +0100, Clemens Ladisch wrote: > > Markus Trippelsdorf wrote: > > > This just happend once yet (during "make check" of glibc). > > > > It appears that these checks manage to create latencies of several > > milliseconds in the USB driver. > > > > AFAIK the USB HC drivers handle URB completions in their interrupt > > handler. You don't happen to be using a closed-source graphics driver > > on irq 16 or 17? > > No. Well, I don't know what the glibc checks are doing, but something in there manages to put a strain on your system. Pierre, do we actually need this debug message? The delay calculation itself appears to work fine. > The only other odd timer related issue I sometimes see are these > messages (happening once every 3-4 days): > kernel: CE: hpet increased min_delta_ns to 20113 nsec > But I guess they're unrelated. Yes, and harmless. Regards, Clemens -- To unsubscribe from this list: send the line "unsubscribe linux-usb" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
