Re: Performance on 8CPU's and 32GB of RAM

Unfortunately, LINUX is not an option at this time. We looked into it; there
is no *NIX expertise in the enterprise. However, I have raised this issue in
various forums before, and when pressed no one was willing to say that "*NIX
*DEFINITELY* outperforms Windows" for what my client is doing (or if it did
outperform Windows, that it would outperform so significantly that it
merited the move).

Was this incorrect? Can my client DEFINITELY expect a significant
improvement in performance for what he is doing?

DISK subsystem reports: SCSI/RAID Smart Array E200 controller using RAID 1.

-----Original Message-----
From: Scott Marlowe [mailto:scott(dot)marlowe(at)gmail(dot)com]
Sent: September 4, 2007 7:15 PM
To: Alvaro Herrera
Cc: Carlo Stonebanks; pgsql-performance(at)postgresql(dot)org
Subject: Re: [PERFORM] Performance on 8CPU's and 32GB of RAM

On 9/4/07, Alvaro Herrera <alvherre(at)commandprompt(dot)com> wrote:
> Carlo Stonebanks wrote:
> > A client is moving their postgresql db to a brand new Windows 2003 x64
> > server with 2 quad cores and 32GB of RAM. It is a dedicated server to
run
> > 8.2.4.
>
> Large shared_buffers and Windows do not mix. Perhaps you should leave
> the shmem config low, so that the kernel can cache the file pages.

Egads, I'd completely missed the word Windows up there.

I would highly recommend building the postgresql server on a unixish
OS. Even with minimum tuning, I'd expect the same box running linux
or freebsd to stomp windows pretty heavily in the performance
department.

But yeah, the I/O, that's the big one. If it's just a single or a
couple of IDE drives, it's not gonna be able to handle much load.