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.
