Oracle FAQ Your Portal to the Oracle Knowledge Grid
HOME | ASK QUESTION | ADD INFO | SEARCH | E-MAIL US
 

Home -> Community -> Usenet -> c.d.o.server -> Re: Linux vs. Windows performance.

Re: Linux vs. Windows performance.

From: Paul Drake <drak0nian_at_yahoo.com>
Date: 14 Feb 2004 18:41:56 -0800
Message-ID: <1ac7c7b3.0402141841.fd325fd@posting.google.com>


norwoodthree_at_my-deja.com (NorwoodThree) wrote in message news:<ba03e2c.0402141225.413103b3_at_posting.google.com>...
> Something else to consider-
>
> On the Linux side, I know that if you use Dell equipment and a Pentium
> 4 processor, you can enable hyper-threading for the processor in the
> BIOS. This essentially gives you 2 processors in one. It basically
> is a virtual 2 processor configuration.
>
> Not sure if Windows takes advantages of the HyperThreading, but Linux
> and Oracle do. And it is fully supported.

"supported" is a funny term here.

for w2k server, if there is a single physical CPU installed with hyperthreading enabled, 2 CPUs will be recognized by the OS, which will not be able to differentiate between physical and logical processors.

for w2k3 server, if there is a single physical CPU installed with hyperthreading enabled, 2 CPUs will be recognized by the OS, which will be able to differentiate between physical and logical processors.

if the OS were to schedule execution of 2 processes on both the physical and logical CPUs of a single physical processor, while not schedule execution of a process on either the physical or logical CPU of the second physical processor, I would certainly not consider that to be "support".

this has been covered in detail in this forum before, as well as in documentation available at Microsoft's knowledgebase.

Unfortunately, I can't help you out with benchmarks on such things for now.

Pd Received on Sat Feb 14 2004 - 20:41:56 CST

Original text of this message

HOME | ASK QUESTION | ADD INFO | SEARCH | E-MAIL US