Final Thoughts

Looking back at our V40z, we have to applaud Sun for another design win. We didn't achieve the theoretical 80% increase in our test benchmarks, but we did achieve significant performance increases that would be unobtainable without a second core. Benchmarks that were not very CPU intensive but where very thread-sensitive - like ApacheBench - fared the best. Whether or not the extreme cost of such a system is easily justifiable is a matter of debate on more factors. For instance, where density becomes an issue, buying dual core processors are really the only way to obtain faster speeds, even if it is only 50% faster than the current generation. Furthermore, buying a dual core V40z might not be faster than buying two single core V40z servers for the same price, but the long term costs of administration and power consumption put the dual core machine in a more favorable position.

Sun has done a great job capitalizing on the performance of Opteron, but they aren't the only ones selling dual core high-density servers either. PogoLinux recently started selling their 8-way dual core Opteron 875 servers (16 physical cores!) for a price that isn't too distant from Sun's quad Opteron V40z. However when compared to the Tier 1 clan (HP, IBM and Dell), Sun has an extremely competitive pricing structure. HP and IBM have been late to phase in dual core servers, and Dell... Dell has just missed the boat altogether for now.

Solaris 10 proved a fascinating endeavor for us as well. Our experience with the operating system as a whole were mixed, generally due to the amount of sharp edges around such a new OS. On the other hand, tools like DTrace proved invaluable to us and Sun really has a great tool on their hands for developers and administrators alike. Also note that Solaris didn't have a problem keeping up with SLES 9 in most of our benchmarks. SLES 9 is a tad slower than some of the slicker installs out there, but it wouldn't be very insightful to put Gentoo on a $39,000 system either. We were very impressed by the fact that Solaris managed to stay a little bit ahead of SLES during benchmarks with heavy scheduling. We really didn't expect this, so perhaps all the efforts of Sun to incorporate better code into the x86 portion of Solaris 10 really paid off. Coupled with the extensive support community and projects like OpenSolaris, Solaris 10 is a winner.

Without much pressure from Intel, Sun has been pretty free to do what they want with AMD's processors. Sun is even going a bit on the offensive with Intel trade-in programs. Even though both AMD and Sun have been through some hard times recently, Sun is a great ally for AMD for two reasons; first, Sun knows servers - this is a critical market for AMD. Second, Sun isn't afraid of Intel and doesn't have nearly the problems AMD does with their customers.

Compiling
Comments Locked

47 Comments

View All Comments

  • Den - Thursday, June 30, 2005 - link

    Interesting article, I am confused why you are dissapointed in the GCC complile time though. The dual core machine took 369 seconds (with 9 jobs) and the single took 603.18 seconds (with 5 jobs). 603.18/369=1.635 or 63.5% faster which is well in the 50-80% range. Your article says 43% faster, so maybe the GCC compile conclusion is based on a typo?
  • Kilim - Thursday, June 30, 2005 - link

    I saw the title to the PS3/XBOX article. It was a different one than the original article from last week. I clicked on it to read it and nothing showed up. It was an article critical of the CPU's on the two systems I believe. Matbe Anand find some insider stuff that was only limited to a few people inside MS. If so, I think the potential rewards of protecting the source is much better long term than getting them in trouble and burning a bridge. Along with the long term effects of insiders trusting Anand.
  • jwbaker - Thursday, June 30, 2005 - link

    You can no longer get v20z via ebay. I managed to buy a half-dozen of them for $1200-$1500 each, although I admit I had to collude with another buyer to do so. Probably Sun has enough traction with the v\d+z series that they no longer need the eBay channel.

    The only beef I have with the v-series is Sun can ben recalcitrant about supplying the voltage regulator modules. In the v20z there are four removable VRMs and if you bought a single-CPU machine, you only get 2. Additional VRMs sell in pairs for $175 but the lead time is indeterminant and sometimes very long.
  • Houdani - Thursday, June 30, 2005 - link

    32: The article was pulled in order to protect one of the anonymous sources (see comment #10).
  • hondaman - Thursday, June 30, 2005 - link

    Actually, no its not. RHEL is by far and away more widely distributed, and more likely to show results to the people who can most relate to this review.
  • finbarqs - Thursday, June 30, 2005 - link

    i did read the comments, but i still don't know why it was taken down... it just said that it wasn't up to kris to take the article down.
  • Houdani - Thursday, June 30, 2005 - link

    30: What's with the hate?

    And it was quite obvious to me there were multiple sources.
  • Questar - Thursday, June 30, 2005 - link

    So that article was based upon one source?!?!

    translation: It was crap, our source was an idiot.
  • yacoub - Thursday, June 30, 2005 - link

    Is there no performance increase seen with PC3200 RAM over PC2700?
  • PrinceXizor - Thursday, June 30, 2005 - link

    If whomever is really worried about protecting his "insider" source, you might want to contact Google to have them clear the article from their cache (I don't even know if that's possible).

    P-X

Log in

Don't have an account? Sign up now