Am Mittwoch, 26. November 2008 13:39:27 schrieb Werner Almesberger: > Andy Green wrote: > > Probably nothing, some other driver with higher interrupt priority can > > be blocking service for 30ms enforcing latency... not sure what to > > recommend about identifying which one unfortunately. > > A 30ms interrupt handler would be pretty evil :-( > > My find-irq-blockers.patch could be adapted to monitor the time > interrupt handlers spend doing their thing, by adding the > intrumentation not to disable/enable pairs but to handle_IRQ_event. > > Another thing to consider are paths that involve a workqueue. > Since lots of things get sent to workqueues these days, you may > end up sharing it with something that takes a very long time to > complete. > > - Werner
Thanks you for your fast answers, I'm a student and in my research project I have to do inertial navigtion and therefor I need this. What would you recommend me to do, is this a problem of the current kernel and will perhaps be fixed in the next one, so should I only wait? Do you think that I can help in any way to solve this problem without deeper kernel and arm development skills? I forgot to say that I'm using FSO, can it be a distribution problem? Or do you think it will be a bigger problem and will last longer than 2 months when I have to be ready with my project? Greets Michael
_______________________________________________ devel mailing list [email protected] https://lists.openmoko.org/mailman/listinfo/devel
