Re[2]:Performance: NT vs. UNIX

From: <dgoulet_at_vicr.com>
Date: Mon, 8 Jan 2001 12:31:28 -0500
Message-Id: <10735.126004@fatcity.com>

Dan,

    What I meant was currently available servers. We're using Compaq's which you can't get with less than 600MHZ in a single CPU configuration. I have not, but others may, seen Oracle allowed by NT to use more than one cpu at a time. We've both a 2 and single CPU servers that have been used as test machines in the past. Given the same data, same size SGA, and a similar disk layout the 2 processor machine did the same task in the same time, with the same results, as the single processor.

Dick Goulet

____________________Reply Separator____________________

Subject: Re:Performance: NT vs. UNIX
Author: Dan.Hubler_at_Metavante.com
Date: 1/8/2001 11:17 AM

For my benefit.................

Could you be a little more specific with your phrase "......NT on a current class server.............."
and what that really means?

Number of CPUs?
Speed of CPUs?

Thanks.

CN=Dan Hubler/OU=DS/O=MICORP_at_vicr.com on 01/08/2001 10:25:36 AM

Sent by: dgoulet_at_vicr.com

Sent From the mail file of: Dan Hubler

To: Dan.Hubler_at_Metavante.com, Multiple recipients of list ORACLE-L

      <ORACLE-L_at_fatcity.com>
cc:

Subject: Re:Performance: NT vs. UNIX

Dan,

    OHHHHH I'm probably going to hate myself, but here goes.

    From a performance point of view, and assuming that you can fit all or most
of the data into the SGA so as to minimize IO traffic, I've found that NT on a
current class server performs as well as an HP-UX single processor machine. Where I've seen real performance improvement is in HP's capability to address
more memory than NT and in our having a faster disk array on the HP's (EMC storage) vs. the NT servers which use Clarion arrays. This gets into some real
numbers when your doing large sorts since on HP they end up being done in memory
whereas NT uses disk & raid being slower than mirrors, well you get the drift.

Where I really prefer HP-UX vs. NT is in stability. Our HP boxes still run for
months without a reboot or other undesirable condition. But the NT servers still require occasional reboots, have occurances of GPF's, and the "blue screen
of death". Also, NT still ships with that idiot DR.Watson.

Dick Goulet

____________________Reply Separator____________________

Subject: Performance: NT vs. UNIX
Author: Dan.Hubler_at_Metavante.com
Date: 1/8/2001 7:00 AM

Used to have just a philosophical debate. Now we are getting into a debate about performance involving the NT bigots and the UNIX bigots.

The latest TPC benchmarks put out by Microsoft appear to have put alot of people in a tizzy about performance.

So............................

Anybody out there have any comparisons of performance of NT vs. UNIX in a single machine environment?
Or even observations/opinions on what "size" NT machine equals the performance of what "size" UNIX machine?

Please withhold the comments on ease of support, cost, etc. Just looking for performance comments.

Thanks.

--

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

Author:
  INET: Dan.Hubler_at_Metavante.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

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 Received on Mon Jan 08 2001 - 11:31:28 CST