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: Bob Jones <email_at_me.not>
Date: Sun, 15 Feb 2004 18:43:13 GMT
Message-ID: <ef0c097027b0e5d99aa4020bb1817157@news.teranews.com>

"Toby Brown" <toby_brown_at_optusnet.com.au> wrote in message news:2a84f50c.0402142205.3072d711_at_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.
>
> Norwood, my apologies. There is actually a performance advantage
> associated with Hyper-threading. I had been misinformed before.

You have not been completely misinformed. It depends on how you look at it. Hyperthreading does increase CPU utilization but not overall throughput. If CPUs are 100% busy, hyperthreading will not do any good. Advertising one CPU as two is misleading unless the key words "physical" and "logical" are mentioned. Received on Sun Feb 15 2004 - 12:43:13 CST

Original text of this message

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