Home Page for the TeradataForum

Archives of the TeradataForum

Message Posted: Thu, 14 Nov 2002 @ 22:44:19 GMT

  <Prev Next>   <<First <Prev Next> Last>>  

Subj:   Re: Comparing RESNode and BEZ Reports
From:   John Hall

I can't speak to BEZ, I have no experience there.

Given that you have the same number of AMPs/Node, no matter their speed, you would expect to see the slower processors 100% busy while the faster processors are less busy (or stated the other way around, spending more time idle).

After all, the machine is no faster than the slowest AMP and if the AMPs on the slowest processor have the same amount of work to do as an AMP on the fastest processor, then aren't you wasting the power of the fastest processors?

Why not increase the number of AMPs on the faster Nodes and so balance-out the workload in such a way that the AMPs are taking approximately the same amount of time for any given unit of work? Unless NCR has something magical, I would assume that this would have to be done empirically.

  <Prev Next>   <<First <Prev Next> Last>>  
  Top Home Privacy Feedback  
Copyright for the TeradataForum (TDATA-L), Manta BlueSky    
Copyright 2016 - All Rights Reserved    
Last Modified: 28 Jun 2020