SQL Stress Tool Benchmark

Our first benchmark was custom-written in .NET, using ADO.NET to connect to the database. The AnandTech Forums database, which is over 14GB in size at the time of the benchmark, was used as the source database. We'll dub this benchmark tool "SQL Stress Tool" for the purposes of discussing what it does. We have done some updates to the tool since we first used it; it now supports Oracle, and MySQL. We also adjusted the test time for this test and future tests to 20 minutes. The reason for this was to ensure that we used as much memory as possible for future planned 64 bit tests.


Click to enlarge.

SQL Stress allows us to specify the following: an XML based workload file for the test, how long the test should run, and how many threads it should use in which to load the database. The XML workload file contains queries that we want executed against the database, and some random ID generator queries that populate a memory resident array with ID's to be used in conjunction with our workload queries. The purpose of using random ID's is to keep the test as real-world as possible by selecting random data. This test should give us a lot of room for growth, as the workload can be whatever we want in future tests.

Example workload:


    Select1
    select count(iuserid) as usercount from ftdb_forumusers where iforumid = 1


    Select2
    select count(u.iuserid) as currusercount from ftdb_users u,ftdb_forumusers fu where fu.iforumid = 1 and u.iuserid = fu.iuserid and dtlastvisiteddate > '[q]qGetLastVisitDate[/q]'


Example Random ID Generator:


    qGetLastVisitDate
    select dtlastvisiteddate,newid() as ldate from ftdb_users where dtlastvisiteddate is not null order by ldate


The workload used for the test was based on every day use of the Forums, which are running FuseTalk. We took the most popular queries and put them in the workload. Functions, such as reading threads and messages, getting user information, inserting threads and messages, and reading private messages, were in the spotlight. Each reiteration of the test was run for 20 minutes, with the first being from a cold boot. SQL was restarted in-between each test that was run consecutively.

The importance of this test is that it is as real world as you can get; for us, the performance in this test directly influences what upgrade decisions we make for our own IT infrastructure.

Web Tests - FuseTalk .NET SQL Stress Results
Comments Locked

144 Comments

View All Comments

  • Jep4444 - Thursday, April 21, 2005 - link

    I don't like how you use the Opteron to give a rough estimation on the A64 X2 as their are other architectural changes between Opteron and A64

    That aside maybe AMD could bring out X2s using 256KB of cache per core to get slightly lower price points and atleast compete with the 830(3ghz)
    I doubt it'll be too bandwidth limited given AMD is selling Semprons with only 128KB of L2 cache
  • KillerBob - Thursday, April 21, 2005 - link

    It is usual to see that Anandtech favors the AMD, looks at the artificial tests, and not the real-world tests, where Intel wins out (as usual).

    In other tests itis pointed out the the PEE can be overclocked past 4GHz, in which case it'll kick everything's ass.
  • KillerBob - Thursday, April 21, 2005 - link

  • dannybin1742 - Thursday, April 21, 2005 - link

    drool, i want one
  • Doormat - Thursday, April 21, 2005 - link

    Typo P13: Intel's "975x" at bottom of page.

    The high price of the dual core opterons kinda puts me off. I was hoping for 2x the price of the single core, instead of 3.5x (I'm looking at 246 vs 270s). It looks like I'll be going single core (or just holding off) instead of dual core (at least until the end of the year and AMD gets price competition from Intel on the server DC front).

    The 3.5x doesn't even make sense from the yield standpoint. If AMD's yeilds are 70% (wild talking-out-of-my-ass guess, no real factual grounding in picking that number), then their dual core yields will only be 49% (70% for the first core, 70% for the second core). So out of a batch of 1000 chips, instead of 700 you only get 490. Thats 210 chips you need to make up for. If opterons have a Avg selling price of $500, then the "adjusted" selling price would be around $715, an increase of 43%, not 250%. Granted, if AMD's yields are higher, the numbers look better (from our perspective - lower prices), but if their yields are less, it looks really bad (if their yield was only 50%, they'd only get 25% yield on dual core, and would have to double price).

    I guess AMD is just trying to squeeze every dime they can out of this... hopefully that extra money goes to pay for Fab36 and more capacity.
  • cbuchach - Thursday, April 21, 2005 - link

    Wow....Very impressive offering from AMD. I think the quote that sums it up best for me is: "you no longer have to make a performance decision between great overall performance or great media encoding performance, AMD delivers both with the Athlon 64 X2."

    I was very impressed with Intel dual core chips, but now I know that my next system will go back to be AMD-based. Overall the dual core Athlon64 should be killer.

    As for cost, yes it is expensive, but the performance is really phenomenal. I am sure that it too will come down.
  • Griswold - Thursday, April 21, 2005 - link

    All hail teh X2!
  • bob661 - Thursday, April 21, 2005 - link

    All I can say is.....WHOODOGGIE!!!!
  • Brian23 - Thursday, April 21, 2005 - link

    ME WANTY!!!
  • jamawass - Thursday, April 21, 2005 - link

    quote: Despite AMD's lead in getting dual core server/workstation CPUs out to market, Intel has very little reason to worry from a market penetration standpoint. We've seen that even with a multi-year performance advantage, it is very tough for AMD to steal any significant business away from Intel, and we expect that the same will continue to be the case with the dual core Opteron. It's unfortunate for AMD that all of their hard work will amount to very little compared to what Intel is able to ship, but that has always been reality when it comes to the AMD/Intel competition."
    This statement should be qualified. The Rendering market is much more adventurous than the standard server market(didn't they use winxp-64 beta running on opterons to render SWIII?) and will continue to rapidly adopt opterons.There're tangible benefits (faster rendering, lower energy costs=$$$) in moving to opteron for rendering farms. Also more oems like supermicro and broadcom have embraced AMD which should result in much more rapid market penetration than 2 yrs ago.

Log in

Don't have an account? Sign up now