RE: More slower CPUs vs. fewer faster CPUs

From: Weaver, Walt <wweaver_at_rightnow.com>
Date: Fri, 23 Feb 2001 07:23:13 -0800
Message-ID: <F001.002BBC1D.20010223070620@fatcity.com>

Say, would anyone have any knowledge on how to benchmark this sort of thing?

I'll be receiving, as part of a hardware evaluation, a VA Linux 4450 and a Sun E450 to see how they compare as a backend database server for our web applications. It would be fun to test some different cpu configurations. Each machine will come with 4 cpu's.

If anyone has any good benchmarking and testing procedures, would you be willing to share'em?

On a semi-connected thread, does anyone know of a good way to compare x86 processors with RISC processors? From what I've heard/read, x86 processors are faster at lower loads but don't scale nearly as well as RISC.

I get to spend the next month just playing with free hardware. Hoo Hah!

Thanks,
--Walt Weaver

Bozeman, Montana, USA

-----Original Message-----

Sent: Friday, February 23, 2001 7:06 AM
To: Multiple recipients of list ORACLE-L

I realize too that it depends on the number of concurrent user sessions.

Patrice Boivin
Systems Analyst (Oracle Certified DBA)

        -----Original Message-----
        From:   Boivin, Patrice J [SMTP:BoivinP_at_mar.dfo-mpo.gc.ca]
        Sent:   Friday, February 23, 2001 9:20 AM
        To:     Multiple recipients of list ORACLE-L
        Subject:        More slower CPUs vs. fewer faster CPUs

        I was wondering if it would be better to have three or four
relatively
        slower CPUs than having only two faster ones.

        I think I remember that Ixora says fewer faster CPUs is better
because the
        CPUs are constantly negotiating who should do what.  The more CPUs
exist the
        more time-consuming the debate (this is very simplified, I realize).

        Jonathan Lewis in Practical Oracle8i: Building Efficient Databases,
Adison
        Wesley, p. says the opposite.

        Is this another one of those questions that has "it depends" as the
only
        answer?  Or that has very plausible theoretical answers that are
mitigated
        in real life?  I imagine that the I/O patterns play a part in the
validity
        of either answer.

        Has anyone on this list tested to see which would be faster?

        We are on Compaq Tru64 UNIX alphas, upgrading to ES-40s with up to
four
        CPUs.  My database is a mix (mess) of background tables for web
apps, ad hoc
        querying, sporadic intensive data loads and in the near future:

replication.

Opinons?

        TIA
        Patrice Boivin
        Systems Analyst (Oracle Certified DBA)

        Systems Admin & Operations | Admin. et Exploit. des systèmes
        Technology Services        | Services technologiques
        Informatics Branch         | Direction de l'informatique 
        Maritimes Region, DFO      | Région des Maritimes, MPO

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


        -- 
        Please see the official ORACLE-L FAQ: http://www.orafaq.com
        -- 
        Author: Boivin, Patrice J
          INET: BoivinP_at_mar.dfo-mpo.gc.ca

        Fat City Network Services    -- (858) 538-5051  FAX: (858) 538-5051
        San Diego, California        -- Public Internet access / Mailing
Lists
        --------------------------------------------------------------------
        To REMOVE yourself from this mailing list, send an E-Mail message
        to: ListGuru_at_fatcity.com (note EXACT spelling of 'ListGuru') and in
        the message BODY, include a line containing: UNSUB ORACLE-L
        (or the name of mailing list you want to be removed from).  You may
        also send the HELP command for other information (like subscribing).

--

Please see the official ORACLE-L FAQ: http://www.orafaq.com
--

Author: Boivin, Patrice J
INET: BoivinP_at_mar.dfo-mpo.gc.ca

Fat City Network Services    -- (858) 538-5051  FAX: (858) 538-5051
San Diego, California        -- Public Internet access / Mailing Lists


--------------------------------------------------------------------

To REMOVE yourself from this mailing list, send an E-Mail message

to: ListGuru_at_fatcity.com (note EXACT spelling of 'ListGuru') and in the message BODY, include a line containing: UNSUB ORACLE-L (or the name of mailing list you want to be removed from). You may also send the HELP command for other information (like subscribing).
--

Please see the official ORACLE-L FAQ: http://www.orafaq.com
--

Author: Weaver, Walt
INET: wweaver_at_rightnow.com

Fat City Network Services    -- (858) 538-5051  FAX: (858) 538-5051
San Diego, California        -- Public Internet access / Mailing Lists


--------------------------------------------------------------------

To REMOVE yourself from this mailing list, send an E-Mail message