I'll give a good test when the next build is out, but I won't be able to reproduce the experimental conditions until Einstein is issuing work again - dry on all relevant boxes. So we get to relax a bit over the weekend.
----- Original Message ----- From: "David Anderson" <[email protected]> To: "Richard Haselgrove" <[email protected]> Cc: "BOINC Developers Mailing List" <[email protected]> Sent: Thursday, April 23, 2009 10:45 AM Subject: Re: [boinc_dev] [boinc_alpha] 6.6.20 and work scheduling] > It's too early to tell, but Paul indeed may have won the prize: > a guided tour of the UCB Space Sciences Laboratory, > lunch (but not airfare) included. > > -- David > > Richard Haselgrove wrote: >> Well done Paul, I think you claim the prize: >> >> http://boinc.berkeley.edu/trac/changeset/17860 >> >> ----- Original Message ----- >> From: "Paul D. Buck" <[email protected]> >> To: "David Anderson" <[email protected]> >> Cc: <[email protected]>; "BOINC Developers Mailing List" >> <[email protected]> >> Sent: Thursday, April 23, 2009 7:50 AM >> Subject: Re: [boinc_dev] [boinc_alpha] 6.6.20 and work scheduling] >> >> >>> On Apr 22, 2009, at 4:17 PM, David Anderson wrote: >>> >>>> "now" is a member of CLIENT_STATE. >>>> In member functions of CLIENT_STATE it's referred to as "now"; >>>> elsewhere it's referred to as "gstate.now". >>>> There is no function now(). >>>> >>>> Now that that's straightened out, maybe we can return to the issue >>>> of why preemptions happen too soon. >>> Sorry about this, can't stop thinking about it. >>> >>> I think we actually have two issues colliding that creates the one >>> symptom. >>> >>> The first is that all tasks are always considered preemptable and are >>> tagged as such on each cycle. >>> >>> The second is that the client assumes / calculates deadline problems >>> incorrectly and, in essence, panics about tasks missing deadlines and >>> schedules them to run when, in fact, they only need to be run on the >>> next available resource. >>> _______________________________________________ >>> 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. >>> >> >> >> _______________________________________________ >> 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. > > _______________________________________________ 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.
