A couple of months ago we shared with you the CPUs that are going into our new server farm. We've actually started physically installing the machines (hence the brief outage over the weekend) so it's time to share another piece of the server puzzle.

The final configuration we decided on was 12 machines. This is a significant reduction of the number of systems we have installed (currently nearly 30) but the performance per box is much higher, allowing for consolidation through virtualization.

We are building two private clouds: a lighter cloud of 8 machines for our application serving needs (including some redundancy in the cloud), and a 4 machine DB cloud to handle the heavier IO. We'll dive into our infrastructure design in the later, full article but for now let's talk about memory.

The application server cloud is light on memory. Each system in this cloud has 12GB of memory (6 x 2 DDR3-1333 DIMMs). The DB server cloud on the other hand has 48GB of memory per box (12 x 4GB DDR3-1333 DIMMs).

Kingston was nice enough to supply the memory for our project with. The 96 sticks of memory were broken down into 48 x KVR1333D3D4R9S/4GI and 48 x KVR1333D3D8R9S/2GI. If you want to see what 288GB of memory looks like, check out the gallery below.

Note that for all of the components we selected for this project, we decided upon the components first and then petitioned the manufacturers second. The stipulation was that the AnandTech server farm would be a publicly visible test bed. Any failures of the hardware are public failures and would obviously reflect poorly on the manufacturer. For CPUs and memory it's not so big of a deal - physical failures there are fairly rare, but for SSDs this provided an interesting challenge. More on that in our next installment.

POST A COMMENT

69 Comments

View All Comments

  • Thermogenic - Thursday, October 28, 2010 - link

    When you are receiving payments from companies whose products you review, your integrity is lost. Reply
  • iGo - Thursday, October 28, 2010 - link

    Did you read?? This at the end of the article:
    <i>
    Note that for all of the components we selected for this project, <b>we decided upon the components first and then petitioned the manufacturers second. The stipulation was that the AnandTech server farm would be a publicly visible test bed.</b> Any failures of the hardware are public failures and would obviously reflect poorly on the manufacturer. For CPUs and memory it's not so big of a deal - physical failures there are fairly rare, but for SSDs this provided an interesting challenge. More on that in our next installment.
    </i>
    Reply
  • Thermogenic - Saturday, October 30, 2010 - link

    Yes, I did read. Being transparent about it doesn't really change things. It's like saying that Unions don't influence political parties with their money because their campaign donations are public information. Reply
  • fepple - Wednesday, November 03, 2010 - link

    Its not like saying that Reply
  • Anand Lal Shimpi - Thursday, October 28, 2010 - link

    We don't receive payment for any product reviewed, period.

    We allowed manufacturers to supply us with hardware for our server upgrade if they were interested in being mentioned as a part of the process. This is what we've always done for our server upgrades. We choose the hardware and then approach the manufacturer about the partnership - in every situation we've done this, our first choice has agreed.

    This applied to our first Xeon servers, our move to AMD K7 and Athlon MP servers as well as the minor upgrades along the way.

    Take care,
    Anand
    Reply
  • vol7ron - Saturday, October 30, 2010 - link

    You receive payment for me ;) Reply
  • Thermogenic - Saturday, October 30, 2010 - link

    Not saying you do, but it's things like this that make one question the veracity of reviews. I use this site as my primary source of reviews, but things like this remind me that you guys' are more friendly with vendors than I would prefer.

    Think of it this way - we people still trust Consumer Reports' reviews on cars if we found out their corporate fleet was donated to them by Ford Motors? Of course not.
    Reply
  • Thermogenic - Saturday, October 30, 2010 - link

    Bad english lol.

    "we people" = "would people"
    Reply
  • SlyNine - Sunday, October 31, 2010 - link

    So what. Either you trust them or you don't. To me, having bought many things they have reviewed I can say their benchmarks are almost always in line with the product.

    It's there methodology you should be worried about, not if companies send them parts to review. Besides if you can think of a better way to get parts in, Review them, and still make a profit i'd like to hear it, Anand isn't doing this for free you know.
    Reply
  • ProDigit - Tuesday, November 02, 2010 - link

    "I can say their benchmarks are almost always in line with the product."

    bwahaha!

    Best joke ever!
    Reply

Log in

Don't have an account? Sign up now