SQL Server 2008

The Flemish/Dutch site Nieuws.be is a web 2.0 website launched in 2008. It gathers news from many different sources and allows the reader a personalized view on all the news. The Nieuws.be site sits on top of a large database—more than 100GB and growing. This database consists of a few hundred separate tables, which have been carefully optimized by our lab (the Sizing Server Lab). We use a log from their site for this test.

99% of the loads on the database are selects and about 5% of them are stored procedures. Network traffic is 6.5MB/s average and 14MB/s at the most, so our Gigabit connection still has a lot of headroom. Disk Queue Length (DQL) is at 2 in the first round of tests, but we only report the results of the next rounds where the database is in a steady state. We measured a DQL close to 0 during these tests, so there is no tangible impact from the hard disk speed.

Note: Starting with our twelve-core Opteron review, we are using a new heavier log. The Nieuws.be application has become more popular and more complex, the database has grown, and queries have become more complex too. The results are no longer comparable to previous results. They are similar, but much lower.

Nieuws.be MS SQL Server 2008 (new heavy log)

At first you might surprised that the Intel chips win here, as this was one of the benchmarks where AMD's high-end CPUs excel. But of course, we should not forget that the Magny-cours chips like the Opteron 6174 had twice as many cores as its Xeon competitors. The "Lisbon" CPU only has 50% more cores than its typical Xeon alternatives.

Virtual Performance on vSphere 4 Idle Power Use
Comments Locked

35 Comments

View All Comments

  • Zoomer - Friday, March 4, 2011 - link

    Sure, obviously McAfee can magically make chips designed and produced before the acquisition more secure.
  • duploxxx - Friday, March 4, 2011 - link

    SAP:
    http://www.sap.com/ecosystem/customers/directories...

    oracle:

    Is turning all heads up side down, once they notice the volume shrink of x86 they will also drop it
    http://www.oracle.com/us/corporate/analystreports/...
  • HangFire - Friday, March 4, 2011 - link

    "...very inexpensive server, with a barebone price of only ~$1500 for two servers."

    Did you mean "sockets"?
  • Penti - Friday, March 4, 2011 - link

    He means two servers. Or rather two nodes if you like. 2 pieces 2-way server.
  • bobbozzo - Monday, March 7, 2011 - link

    That server has 2 dual-socket motherboards in 1U; it's 2 servers in one, each with 2 CPU sockets.
  • ERJ - Friday, March 4, 2011 - link

    Home electric pricing is very different than rack pricing. Consider, for a good datacenter, you need UPS and power generators capable of matching every watt in use. You need pdu's. You have extra heat generation so you need additional cooling.

    For our colo space we pay somewhere in the range of $500 a month for a 30amp 120v circuit. Getting the best performance per watt is definitely part of our criteria.
  • Stuka87 - Friday, March 4, 2011 - link

    I gotta thank you for the laugh. Never have I thought the word "craps" would make me laugh so much. I think it may be that you seem to use that word in every single post combined with one of the most narrow minded points of views I have seen on this site.

    All our craps are belong to you.
  • silverblue - Friday, March 4, 2011 - link

    AMD must be good at the casino, what with all these "craps".

    I've long since filed sans2212 in the same category as SiliconDoc, under "has nothing to bring to the discussion whatsoever aside of (an initial period of) light entertainment for all readers (which rapidly becomes tedious)".
  • VJ - Saturday, March 5, 2011 - link

    "You can get a slightly faster 1.8GHz version, the 4164 EE, but that chip costs more than twice as much ($698). As we are searching for low power and inexpensive CPUs, it didn't make the cut. The only disadvantage other than the lower clock speed is the lower clocked HT3 link at 2GT/s instead of 6.4GT/s."

    It's a bit of a weird paragraph since I was first thinking that you were suggesting the 4164 EE does 6.4GT/s but (for your sake) I can also interpret "instead of" in the final sentence to refer to the other AMD cpus you're testing here.

    But it's still a deficient paragraph considering "the lower clocked HT3", since in reality, this resolves to an HT1 (for the 4162 EE).

    It's like a car test mentioning a "less powerful V8 engine" when they're referring to a V6.

    Gaat lekker, he?
  • oneoho - Tuesday, March 8, 2011 - link

    great article, I was about to build some low power consumption / cooling requirement servers. This will help immensely.

Log in

Don't have an account? Sign up now