On Apr 26, 2009, at 3:08 AM, Richard Haselgrove wrote: > TarotApprentice wrote: > >> Sometimes tasks take longer than expected. That may then put other >> tasks into deadline pressure. Sure I agree there is no reason to >> check every 60 seconds. I think 5 mins is enough to allow for this >> scenerio assuming some other event didn't already trigger the >> checking. > > I've always been slightly perplexed by BOINC's design here. In > complete contrast to the hyperactive checking and re-checking that > we're discussing on this list, BOINC makes no allowance for tasks > which are taking longer than expected. Instead, it only takes > account of tasks which ***have taken*** - past tense - longer than > expected: i.e. the calculation is only done at task completion, and > stored as Duration Correction Factor.
Yes, but as Barf said, have we gone to plaid? I am not sure how often this happens, I cannot recall seeing this specifically on my systems, of course I also was not looking for it either. But, I have noted that task durations do jump about sometimes in the sense I have a pretty stable "to completion" estimate which suddenly and inexplicably jumps up ... only to work its way back down in time again to a proper value. I have the counter example of MW on my ATI card where the times are all over the map and never correct. Of course that I put down to the non-recognition of the GPU application by BOINC so have been ignoring it as an issue for the moment. For me the time to deadlines is a smaller issue and far less critical to most operational modes I find myself in because I suspect my systems are staying pretty far ahead of the power curve most of the time. I suppose if we are adjusting DCF in the next go rounds then I will need to pay attention to it ... _______________________________________________ boinc_dev mailing list [email protected] http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev To unsubscribe, visit the above URL and (near bottom of page) enter your email address.
