Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 18 Jul 2007 13:03:02 +0100
From:      Thomas Hurst <tom.hurst@clara.net>
To:        Jack Toering <Jack.Toering@LeadingEdgeITA.com>
Cc:        freebsd-performance@freebsd.org
Subject:   Re: Which SMP CPU for FreeBSD 6.2?
Message-ID:  <20070718120302.GA11968@voi.aagh.net>
In-Reply-To: <02b101c7c8bf$442c2140$6480010a@DELL9400>
References:  <029401c7c8af$e5d19c60$6480010a@DELL9400> <b41c75520707171458q510b7e11xc554ddb4452c38c9@mail.gmail.com> <02b101c7c8bf$442c2140$6480010a@DELL9400>

next in thread | previous in thread | raw e-mail | index | archive | help
* Jack Toering (Jack.Toering@LeadingEdgeITA.com) wrote:

> These are things I need to hear bacause it doesn't make sense for me to
> watch these things until I'm in the market because the technology moves so
> fast.
> 
> Thank you very much for your response!

You probably don't need to follow every move, but it might make sense to
do some actual research if performance matters to you?  You don't even
say what your performance critical server is going to be doing ;)

Core 2 generally performs well, but K8's are still pretty good with many
workloads thanks to their far superior interconnects.  Most numbers I've
seen have been more based on games and media encoding in single socket
configurations, and in 32bit mode at that; not exactly interesting use
cases for most servers.  Things get even less clear cut when you start
worrying about power consumption.

One of our more CPU heavy server uses actually depends very heavily on
memory bandwidth, which Intel are still lagging behind on quite
significantly, and of course things like lights out management and
driver support are generally far more critical than a 10% performance
difference in $random_microbenchmark.

-- 
Thomas 'Freaky' Hurst
    http://hur.st/



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070718120302.GA11968>