Sebastian Kuzminsky wrote: > > A typical EPP transaction for this driver consists of two address cycles > and 16 data cycles, for a total of about 20 or 25 microseconds of no > interrupts. It occasionally (rarely) spikes as high as 75 microseconds. > > > There's a judgement call here, and I seek your advice. Is 25 > microseconds too long to run with interrupts off? > >
Memory refresh is usually done by interrupt, and you don't want to delay that too much. What happens if the EPP bus hangs? 20-25 uS could turn into hundreds of us if the driver doesn't have some abort strategy when it gets an EPP timeout (which should never happen, but plug falling out, slave board losing power, etc. could cause it) I know that a hard timeout condition with my PPMC boards will eventually cause the whole system to freeze. Since it is central to the motion control job, if this happens, everything stops, and the controller watchdog will go to E-stop, so it isn't a major safety thing, and crashing the computer would be a minor annoyance. My guess is that your 25 us periods of interrupt masking would have little impact. The only thing it might SEEM to impact is ethernet packet handling, but that would be blocked anyway by the real time thread. Jon ------------------------------------------------------------------------- This SF.Net email is sponsored by the Moblin Your Move Developer's challenge Build the coolest Linux based applications with Moblin SDK & win great prizes Grand prize is a trip for two to an Open Source event anywhere in the world http://moblin-contest.org/redirect.php?banner_id=100&url=/ _______________________________________________ Emc-developers mailing list Emc-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/emc-developers
