how are work units produced this fast?
Moderators: Site Moderators, FAHC Science Team
how are work units produced this fast?
in serverstats, i see the total work units on server count always remain within the 120000 count. how are work units produced so fast that even at around 100 petaflops, the count stays that constant?
-
Joe_H
- Site Admin
- Posts: 7990
- Joined: Tue Apr 21, 2009 4:41 pm
- Hardware configuration: Mac Studio M1 Max 32 GB smp6
Mac Hack i7-7700K 48 GB smp4 - Location: W. MA
Re: how are work units produced this fast?
Until a project reaches completion, each WU turned in results in the next Gen WU for its Project, Run and Clone being created. So the count will stay relatively stable for those Work Servers actually reporting a value of available WU's on the Server Status page.
This underscores the sequential part of this distributed computing project. Part of the work is done in parallel, but each generation of a particular Run and Clone for a specific project depends on completion of the previous generation WU to set the initial state. So to get Gen 100 (or higher), all previous WU's need to have been processed and turned in sequence, they can not be done out of sequence.
This underscores the sequential part of this distributed computing project. Part of the work is done in parallel, but each generation of a particular Run and Clone for a specific project depends on completion of the previous generation WU to set the initial state. So to get Gen 100 (or higher), all previous WU's need to have been processed and turned in sequence, they can not be done out of sequence.