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

From: "Carlo Stonebanks" <stonec(dot)register(at)sympatico(dot)ca>
To: "'James Mansion'" <james(at)mansionfamily(dot)plus(dot)com>
Cc: "'Scott Marlowe'" <scott(dot)marlowe(at)gmail(dot)com>, "'Alvaro Herrera'" <alvherre(at)commandprompt(dot)com>, <pgsql-performance(at)postgresql(dot)org>
Subject: Re: Performance on 8CPU's and 32GB of RAM
Date: 2007-09-06 23:18:40
Message-ID: C7EB427FBE2848FBAC523CF9C9F991DA@serenity
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-performance

Wow - it's nice to hear someone say that... out loud.

Thanks, you gave me hope!

-----Original Message-----
From: James Mansion [mailto:james(at)mansionfamily(dot)plus(dot)com]
Sent: September 6, 2007 4:55 PM
To: Carlo Stonebanks
Cc: Scott Marlowe; Alvaro Herrera; pgsql-performance(at)postgresql(dot)org
Subject: Re: [PERFORM] Performance on 8CPU's and 32GB of RAM

Carlo Stonebanks wrote:
> Isn't it just easier to assume that Windows Server can't do anything
right?
> ;-)
>
>
Well, avoiding the ;-) - people do, and its remarkably foolish of them. Its
a long-standing whinge that many people with a UNIX-background seem to
just assume that Windows sucks, but you could run 40,000 sockets from a
single Win32 process for a while and some well-known UNIX systems would
still struggle to do this, libevent or no. Admitedly, the way a Win32
app is architected would be rather different from a typical POSIX one.

Windows has been a cheap target bt its remarkably adequate and the
TPC results speak for themselves.

In response to

Browse pgsql-performance by date

  From Date Subject
Next Message Tom Lane 2007-09-06 23:18:46 Re: Reasonable amount of indices
Previous Message Scott Marlowe 2007-09-06 22:35:11 Re: SAN vs Internal Disks