Il 09/10/2013 14:58, Hans de Goede ha scritto:
I still think we should add my patch in some form, since the lock
starvation
caused by timers set to expire in the past could still happen in other
cases,
esp for timer users who take a time stamp once and then add incremental
values to trigger the next run, these can get behind quite a bit if there
are latency spikes, and we don't wont to run without ever releasing the
lock while these are catching up.
I agree. Do you also agree that the equivalent workaround, before
Alex's patch, was MIN_REARM_TIMER_NS (and thus 250 microseconds)?