RE: Slightly OT : Latest tpC benchmark results

From: Boivin, Patrice J <BoivinP_at_mar.dfo-mpo.gc.ca>
Date: Fri, 07 Jul 2000 11:45:30 -0300
Message-Id: <10551.111432@fatcity.com>

There was a post a few days ago in the Developer listserv about why Microsoft withdrew their benchmark submission:

-----Original Message-----
From: Jesse, Rich [SMTP:Rich.Jesse_at_qtiworld.com] <mailto:[SMTP:Rich.Jesse_at_qtiworld.com]>=20

Sent:	Friday, June 30, 2000 6:26 PM
To:	Multiple recipients of list ORACLE-L
Subject:	Microsloth Withdraws SQueaL Server TPC-C Benchmark Today

A co-worker tossed me this tidbit. Thought this might interest some = folks
here:
http://www.tpc.org/new_result/c-withdrawn-results.idc <http://www.tpc.org/new_result/c-withdrawn-results.idc>=20

Rich Jesse                          System/Database Administrator

Rich.Jesse_at_qtiworld.com <mailto:Rich.Jesse_at_qtiworld.com> QTI-Sussex, WI USA

This message is forwarded from the newsgroup = "comp.databases.oracle.server".
----------- Begin Forwarded Message ----------- Newsgroups: comp.databases.ms-sqlserver, comp.databases.oracle.server,=20 microsoft.public.sqlserver.server, comp.databases.sybase,=20 comp.databases.ibm-db2
Finally this thread made to the DB2 newsgroup, eh? Here are my 2 (biased) cents:
1. Microsoft was sued over that benchmark because they violated one of = the
rules.

I.e. SQL Server cannot update the column used to partition the view
over the

federated database. The TPC-C benchmark requires updateability of ALL

columns. It seems like they'll get away with flagging their violation
and a raised

		finger.
		To be fair I should add that updating of partitioning keys

is no
trivial excercise.
2. The benchmark did not use mirroring. As stated in earlier posts running such a

beast in a company would be quite - unstable. One has to watch this
when

looking at the price/performance numbers. 3. Jim Gray said himself that the environment was very hard to set up and to keep

running through the audit.
Finally a federated database is not the same as an MPP system like e.g. DB2 EEE.
In an MPP system the whole query plan gets compiled with MPP in mind = and
parts of the execution get distributed to the participating nodes. The = whole
thing is still one database, partitioned tables are still tables and = the
integration is VERY tight.
A federated database sits on top of other database systems. Parts of = the
query get shipped (like SQL Servers pass through queries) to the target systems and the results get shipped back. On DB2 side this would be Datajoiner or the new DB2 V7.1 where SQL queries get reverse engineered = post
optimization and send to the target systems through public interfaces. = The
connection is loose compared to MPP and involves sending the SQL = (rather
than "executable sub query plans"). Partitioned tables are represented = as
views with all their advantages and disadvantages. just my two cents
Serge

I have not verified the veracity of this information.

Regards,
Patrice Boivin
Systems Analyst (Oracle Certified DBA)

Systems Admin & Operations | Admin. et Exploit. des syst=E8mes
Technology Services        | Services technologiques
Informatics Branch         | Direction de l'informatique=20
Maritimes Region, DFO      | R=E9gion des Maritimes, MPO

E-Mail: boivinp_at_mar.dfo-mpo.gc.ca <mailto:boivinp_at_mar.dfo-mpo.gc.ca>=20

	-----Original Message-----
	From:	Deshpande, Kirti [SMTP:kirti.deshpande_at_verizon.com]
	Sent:	Friday, July 07, 2000 10:47 AM
	To:	Henry.O'Keeffe_at_ft.com
	Cc:	oracledba_at_quickdoc.co.uk
	Subject:	RE: Slightly OT : Latest tpC benchmark results -

without Oracle!

From Q&A at http://www.tpc.org/faq_TPCC.html=20

Q: I notice that some TPC results are labelled "withdrawn." Could you

explain what that means?

The TPC felt that users should be made aware of what results drop from the TPC's official results list and why those results no longer appear. Some vendors withdraw results because they feel these results no longer have market relevance. Other vendors withdraw results after compliance to the benchmark specification has been challenged by someone within the TPC. Rather than defend their implementation (and perhaps expend further resources to demonstrate compliance), the vendor chooses to withdraw the result. Finally, if the Council votes that a result is non-compliant, the Council will drop the result from the official results list.=20

HTH..

Kirti=20

> -----Original Message-----

	> From:	Henry.O'Keeffe_at_ft.com [SMTP:Henry.O'Keeffe_at_ft.com]
	> Sent:	Friday, July 07, 2000 5:38 AM
	> To:	Alex Afanassiev
	> Cc:
	>

IMCEAOPENMAIL-John+20J+2E+20Kanagaraj+20_FIC321+2COPENMAIL_o=3DBRUNEI+5C= +20S

> HELL+5C+20PETROLEUM+5C+20SERIA_at_team.telstra.com; oracledba_at_quickdoc.co.uk;

	> ORACLE-L_at_fatcity.com
	> Subject:	RE: Slightly OT : Latest tpC benchmark results -
without
	> Oracle!
	>=20
	> Does anybody understand what "withdrawn" means?  Why would MS
withdraw
	> these=20
	> results? Why would results which COULD be withdrawn be published
in the
	> first=20
	> place?
	>=20
	> H.
	>=20
	>=20
	>=20
	>=20
	> "Alex Afanassiev" <Alex.Afanassiev_at_team.telstra.com> on 07/07/2000
	> 12:13:10 PM
	> To:=20
	>

IMCEAOPENMAIL-John+20J+2E+20Kanagaraj+20_FIC321+2COPENMAIL_o=3DBRUNEI+5C= +20S

	> HELL+5
	> C+20PETROLEUM+5C+20SERIA_at_team.telstra.com
	> cc: oracledba_at_quickdoc.co.uk, ORACLE-L_at_fatcity.com (bcc: Henry=20
	> O'Keeffe/PSD/LONDON/FTI)
	>=20
	> Subject: RE: Slightly OT : Latest tpC benchmark results - without
Oracle!
	>=20
	>=20
	> Hi John=20
	>=20
	> I cannot say that ' ...Latest tpC benchmark results - without
Oracle...'
	> as
	> 8 of top 10 TPC-C Results by Performance  (positions 2-7, 9,10 )
have
	> Oracle
	> in the database column.
	>=20
	> Also under ** on
	> http://isource.ibm.com/cgi-bin/goto?it=3Dusa_press&on=3D2000070605
	> can see
	> ....
	>=20
	> **Total solution availability date estimated to be Dec. 7, 2000.
Solution
	> specification, pricing and availability information
	> is subject to change without notice.
	>=20
	> ...
	>=20
	> So we'll see in December. Hopefully there won't be any withdraws
:)
	>=20
	>=20
	> With regards
	> Alex Afanassiev
	> Oracle DBA, TOC Operations Support/IDO
	> Tel:    (03) 8 661 20 61
	> Fax:    (03) 9 650 36 74
	>=20
	>=20
	> > -----Original Message-----
	> > From: John J. Kanagaraj /FIC321,OPENMAIL/o=3DBRUNEI SHELL
PETROLEUM SERIA
	> > On Behalf Of John J. Kanagaraj /FIC321,OPENMAIL/o=3DBRUNEI SHELL
PETROLEUM
	> > SERIA
	> > Sent: Friday, July 07, 2000 11:34 AM
	> > To:   oracle-l_at_fatcity.com; oracledba_at_quickdoc.co.uk
	> > Subject:      Slightly OT : Latest tpC benchmark results -
without
	> Oracle!
	> >=20
	> > Hi Listers,
	> >=20
	> > Came across this note recently. IBM and Micro$oft (unlikely=20
	> > combination!) broke the 400000 tpmC mark using a DB2 Database.=20
	> >=20
	> > IBM, Intel, Microsoft Eclipse Sun Microsystems and Oracle with
World's=20
	> > Fastest Commercial Server Cluster (9.6KB)=20
	> >=20
	> > http://isource.ibm.com/cgi-bin/goto?it=3Dusa_press&on=3D2000070605
	> >=20
	> > Earlier on, M$ had announced that they had broken 152207 tpmC
(at=20
	> > $18.93/tpmC) and 227079 tpmC (at $19.12/tpmC) with the Compaq
Proliant=20
	> > 8500-64P and -96P respectively on 17/Feb/00 and then WITHDREW
the=20
	> > result on 30/June/00. See=20
	> > http://www.tpc.org/new_result/c-withdrawn-results.idc
	> >=20
	> > John Kanagaraj
	> > Brunei Shell Petroleum
	> > http://www.geocities.com/john_sharmila
	> >=20
	> > God so loved the world that He didn't send a committee! (See
John 3:16=20
	> > for details)
	> > ** Opinions expressed here are solely mine and not necessarily
those of=20
	> > my employer **
	> >  << File: ATT2260013.txt >>=20
	>=20


	> --------

	> If you're bored, then visit the list's website:
http://www.lazydba.com
	> (updated=20
	> daily)
	> to unsubscribe, send a blank email to
oracledba-unsubscribe_at_quickdoc.co.uk
	> to subscribe send a blank email to
oracledba-subscribe_at_quickdoc.co.uk
	>=20
	>=20
	>=20
	>=20
	>=20
	>=20
	>
*********************************************************************
	> * Please visit the web site of the Financial Times at:
*
	> *                         http://www.ft.com
*
	> *
*
	> * This E-Mail is intended for the use of the addressee only and
may *
	> * contain confidential information. If you are not the intended
*
	> * recipient, you are hereby notified that any use or dissemination
*
	> * of this communication is strictly prohibited.
*
	> * If you receive this transmission in error, please notify us
*
	> * immediately then delete this E-Mail.
*
	> *
	> *
*
	> * postmaster_at_ft.com
*
	>
*********************************************************************
	>=20


	> --------

	> If you're bored, then visit the list's website:
http://www.lazydba.com
	> (updated daily)
	> to unsubscribe, send a blank email to
oracledba-unsubscribe_at_quickdoc.co.uk
	> to subscribe send a blank email to

Received on Fri Jul 07 2000 - 09:45:30 CDT