In your opinion. If your host can do at most 10,000 work units, under absolutely optimal conditions (fastest work units of that type, plentiful work, nothing to slow things down), and the limit is 20,000, then 20,000 is exactly the same as infinity.
On the other hand, if one broken machine can soak up all of the work, then error out in such a way that it can't really report them all "gone missing" that hurts everyone. On 5/25/2010 1:44 PM, jay wrote: > That's called "running the world for the sake of the 1%'rs", Martin > (In this case 1/10 of 1%) > It's also why the scheduler is so frakked up in the first place. _______________________________________________ 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.
