From: Norris <jcheong@cooper.com.hk>
Subject: Re: Microsoft destroys TPC-C records!
Date: 2000/03/03
Message-ID: <89n6fq$1hb0$1@adenine.netfront.net>#1/1
References: <38ace385$1$8288@readdo01.news> <isGr4.1172$x5.89278@news1.frmt1.sfba.home.com> <38B8BCE6.E45FD33E@qnet.com> <89et1e$1fn$1@web1.cup.hp.com>
X-Complaints-To: news@netfront.net
X-Trace: adenine.netfront.net 952048954 50528 202.81.252.1 (3 Mar 2000 02:02:34 GMT)
Organization: Netfront http://www.netfront.net/
User-Agent: tin/pre-1.4-980818 ("Laura") (UNIX) (FreeBSD/3.2-RELEASE (i386))
NNTP-Posting-Date: 3 Mar 2000 02:02:34 GMT
Newsgroups: comp.databases,comp.databases.oracle.misc,comp.databases.oracle.server,comp.databases.sybase,comp.sys.sun.misc,comp.unix.aix


SQL Server 2000 achieved its impressive scores using a new feature
called distributed partitioned views. This configuration let Microsoft
physically distribute slices of a single table across multiple servers
but logically access the table as an integrated whole. Microsoft calls
this configuration a "federated database," a precursor to the 100
percent shared-nothing cluster architecture plans for Yukon (the
version after SQL Server 2000). Microsoft spread the federated database
across 12 Compaq servers, each running 8 CPUs for a combined total of
96 CPUs. The best Oracle score came on a single SMP-based IBM machine
running 24 CPUs.

In comp.databases.sybase Rick Jones <foo@bar.baz.invalid> wrote:
> If someone can do a benchmark in a "shared nothing" manner (or perhaps
> a "shared hardly anything" manner) the benchmark becomes more about
> how many systems can you get your hands-on for the measurement than
> anything else, and it will tend to scale even if you link the nodes
> with lengths of wet string :)
 
> rick jones
> -- 
> these opinions are mine, all mine; HP might not want them anyway... :)
> feel free to email, OR post, but please do NOT do BOTH...
> my email address is raj in the cup.hp.com domain...




