[RC5] OGR percent done

Wilson, Bruce bwilson at fers.com
Tue Feb 22 15:58:18 EST 2000


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1


__
Bruce Wilson, Manager, FERS
bwilson at fers.com, 312.245.1750, http://www.fers.com
PGP KeyID: 5430B995, http://www.geocities.com/bruce-wilson/

"In your CONFIG.SYS, you forgot to specify BUGS=OFF."


| I think the question was asking "what will OGR-25 be like, 
|given that OGR-24
|takes time T_24?"

It's not necessarily proportional, if that's what you mean.  OGR-25
might actually be easier than OGR-24.  Or harder.  Can't say until we
do it.

| On a related topic, won't it be the case that the work-unit 
|rate for OGR-24
|will slow down, since the easy work units will get done 
|sooner, so after a
|while, more and more computers will be sitting on big work 
|units.  Since we
|are measuring completion % by work units and not nodes 
|(right?), won't the
|rate we're calculating for ourselves slow down as the node/stub ratio
|increases?  Or are the "hard" work-units rare enough that this 
|isn't an issue?
|I imagine that the node/stub ratio could start to climb, since 
|clients that
|finish an easy work unit return it and start another one, so 
|the easy work
|units are the only ones going back to the servers so far.

Short version: No, it won't slow down because of easy/hard units.

The hard/easy distinction is continuously variable, and the difficulty
of work handed out is fairly equally distributed, overall.  In other
words, the odds of your stub having 1% of the work of the hardest stub
is about the same as the odds of having 50% of the work of the hardest
stub.  The node rate will be fairly constant, regardless of the
individual stubs, because random-work stubs, begun at random times will
be returned in a random but fairly steady stream.



|
| (I don't think that last paragraph makes as much sense as I 
|wish it did.
|Hopefully you can figure out what I'm getting at :)
|
|-- 
|#define X(x,y) x##y
|DUPS Secretary ; http://is2.dal.ca/~dups/
|Peter Cordes ;  e-mail: X(peter at cordes.phys. , dal.ca)
|
|"The gods confound the man who first found out how to 
|distinguish the hours!
| Confound him, too, who in this place set up a sundial, to cut and
| hack my day so wretchedly into small pieces!" -- Plautus, 200 BCE 
|
|--
|To unsubscribe, send 'unsubscribe rc5' to 
|majordomo at lists.distributed.net
|rc5-digest subscribers replace rc5 with rc5-digest
|
|
|

-----BEGIN PGP SIGNATURE-----
Version: PGP Personal Privacy 6.5.1

iQA/AwUBOLMGdvWcoJZUMLmVEQLckQCfU0iLUArFbAfV3anX2DU2q8/rT2gAoKmQ
Ly4eE9HDY39qrRNBPijgbJIG
=GDlJ
-----END PGP SIGNATURE-----

--
To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
rc5-digest subscribers replace rc5 with rc5-digest



More information about the rc5 mailing list