Re: Microsoft destroys TPC-C records!

>Nuno Souto wrote:

>. I'd say the "application" must still find a way of sharing the
>data it's getting from the multitude of db's.

Actually ... IBM (DB2) does not rely on the application to devise a way to share the data. DB2 handles it all under the covers, making a transition to MPP transparent from the application perspective.

Nuno Souto wrote:

> On Sun, 20 Feb 2000 15:42:40 -0500, Larry Edelstein

> <lsedels_at_us.ibm.com> wrote:
>
> >looking at the vendor/db that has been in the TPC top ten cumulatively
> >and most consistently.
>
> Nah! That would make sense... <G>
>
> >shared. What does this mean for the database? It means that the database
> >must still find a way of "sharing" the data across nodes.
>
> MOL. I'd say the "application" must still find a way of sharing the
> data it's getting from the multitude of db's. But then we are
> benchmarking the application, not the db. Or are we not?
>
> >set and return of one unified result set to the requesting user. I don't
> >know how Microsoft does it, but the term shared nothing is pretty much
> >industry parlance for partitioning of data across nodes, and somehow
> >sharing the partitions in some way, shape, or form without having the
> >nodes actually share the same RAM or disk.
>
> Don't expect MS to give you a clear explanation. All they'll do is
> throw in buzzwords like DCOM and such until everyone is completely
> confused. But a CLEAR, concise explanation of EXACTLY what is the
> application doing to get all those nodes to talk together and make
> sense as a whole, you won't get.
>
> You won't get either their explanation of exactly which version and
> patch level of the software was used to develop all this. Or even if
> the common mortal user can access and make use of such. But then
> again, it's MS we are dealing with here...
>
> Cheers
> Nuno Souto
> nsouto_at_nsw.bigpond.net.au.nospam
> http://www.users.bigpond.net.au/the_Den/index.html
Received on Mon Feb 21 2000 - 09:45:43 CST