21st Century Server Choices

Lots of people base their server form factor choice on what they are used to buying. Critical database applications equal a high-end server. Less critical applications: midrange server. High-end machines used to find a home at larger companies and cheaper servers would typically be attractive to SMEs. I am oversimplifying but those are the clichés that pop up when you speak of server choices.

Dividing the market into who should or should not buy high-end servers is so... 20th century. Server buying decisions today are a lot more flexible and exciting for those who keep an open mind. In the world of virtualization your servers are just resource pools of networking, storage and processing. Do you buy ten cheap 1U servers, four higher performance 2U, one “low cable count” blade chassis, or two high-end servers to satisfy the needs of your services?

A highly available service can be set up with cheap and simple server nodes, as Google and many others show us every day. On the flipside of the coin, you might be able to consolidate all your services on just a few high-end machines, reducing the management costs while at the same time taking advantage of the advanced RAS features these kind of machines offer. It takes a detailed study to determine which strategy is the best one for your particular situation, so we are not saying that one strategy is better than all the others. The point is that the choice between cheap clustered nodes and only a few high-end machines cannot be answered by simply looking at the size of the company you are working for or the "mission critical level" of your service. There are corner cases where the choice is clear, but that is not the case for the majority of virtualized datacenters.

So is buying high-end servers as opposed to buying two or three times more 2-socket systems an interesting strategy for your virtualized cluster if you are not willing to pay a premium for RAS features? Until very recently, the answer was simple: no. High-end quad socket systems were easily three times and more as expensive and never offered twice as much performance compared to dual socket systems. There are many reasons for that. If we focus on Intel, the MP series were always based on mature but not the cutting edge technology. Also, quad socket systems have more cache coherency overhead, and the engineering choices favor reliability and expandability over performance. That results in slower but larger memory subsystems and sometimes lower clock speeds too. The result was that the performance advantage of the quad system was in many cases minimal.

At the end of 2006, the Dual Xeon X5300 were more than a match for the Xeon X7200 quad systems. And recently, dual Xeon 5500 servers made the massive Xeon 7400 servers look slow. The most important reason why these high-end systems were still bought were the superior RAS features. Other reasons include the fact that some decision makers never really bothered to read the benchmarks carefully and simply assumed that a quad system would automatically be faster since that is what the OEM account manager told them. You cannot even blame them: a modern CIO has to bury his head in financial documents, must solve HR problems, and is constantly trying to explain to the upper management why the complex IT sytems are not aligned with the business goals. Getting the CIO down from the “management penthouse” to the “cave down under”, also called the datacenter, is no easy task. But I digress.

Virtualization can shatter the old boundaries between the midrange and high-end servers. They can be interesting for the rest of us, the people that do not normally consider these high-end expensive systems. The condition is that the high-end systems can consolidate more services than the dual socket systems, so performance must be much better. How much better? If we just focus on capital investment, we get the figures below.

Type Server CPUs Memory Approx. Price
Midrange Dell R710 2x X5670 18 x 4GB = 72GB $9000
Midrange Dell R710 2x X5670 16 x 8GB = 128GB $13000
High-end Dell R910 4x X7550 64 x 4GB = 256GB $32000

So these numbers seem to suggest that we need 2.5 to 3 times better performance. In reality, that does not need to be the case. The TCO of two high-end servers is most likely a bit better than that of four midrange servers. The individual components like the PSU, fans, and motherboard should be more reliable and thus result in less downtime and less time spent on replacing those components. Even if that is not the case, it is statistically more likely that a component fails in a cluster with more servers, and thus more components. Less cables and less hypervisor updates should also help. Of course, the time spent in managing the VMs is probably more or less the same.

While a full TCO calculation is not the goal of this article, it is pretty clear to us that a high-end system should outperform the midrange dual socket systems by at least a factor two to be an economical choice in a virtualization cluster where hardware RAS capabilities are not the only priority. There is a strong trend that the availability of the (virtual) machine is guaranteed by easy to configure and relatively cheap software techniques such as VMware’s HA and fault tolerance. The availability of your service is then guaranteed by using application level high availability such as Microsoft’s clustering services, load balanced web servers, Oracle fail-over, and other similar (but still affordable) techniques.

The ultimate goal is not keeping individual hardware running but keeping your services running. Of course hardware that fails too frequently will place a lot of stress on the rest of your cluster, so that is another reason to consider this high-end hardware... if it delivers price/performance wise. Let us take a closer look at the hardware.

The 32-Core, 64-Thread Beast
Comments Locked


View All Comments

  • davegraham - Wednesday, August 11, 2010 - link

    which is actually why you should be using a Cisco C460 for this type of test.

  • MySchizoBuddy - Wednesday, August 11, 2010 - link

    Is there an exact correlation with number of cores and VMs. How many VMs can a 48 core system support.

    Let's assume you want 100 systems virtualized. What's the minimum number of cores that will handle those 100 VMs.
  • dilidolo - Wednesday, August 11, 2010 - link

    Depends on how many vCPU and memory you assign to each VM and how much physical memory your server has. CPU is rarely the bottleneck , memory and storage are.

    Then not all the VMs have the same workload. So no one can really answer your question.
  • davegraham - Wednesday, August 11, 2010 - link

    was going to say that a small amount of memory oversubscription is "ok" depending on the workload but you'd want that buffered with something a little more powerful than spinning disk (SSD, for example).
  • tech6 - Wednesday, August 11, 2010 - link

    The parameters for determining the optimal configuration for VMWare go well beyond just which CPU is faster. I like the AT stories about server tech but there need to be broader considerations of server features.

    1. Many applications are memory limited and not CPU bound so the memory flexibility may trump CPU power. That is why 256Gb with a dual 75xx or 6xxx series CPU in an 810 may well be the better choice than either a quad socket or dual socket 56xx configuration.

    2. Software licensing is a big part of choosing the server as it is often licensed per socket. Sometime more cores and more memory is cheaper than more sockets.

    3. Memory reliability is another major issue. Large amounts of plain ECC memory will most likely result in problems 2-3 years after deployment. The platforms available with the 6xxx and 75xx series CPUs support memory reliability features that often make it a better choice for VM data centers.

    4. Power and density is another major issue which drive data center costs that must be given consideration when reviewing servers.
  • don_k - Wednesday, August 11, 2010 - link

    Would like to see some non-windows VM benchmarks as well as a different virtualisation application used and by extension an SQL server that does not come from microsoft. Also would like to see benchmarks on para-virtualised VMs along with full hardware virtualised VMs.

    The review as is is quite meaningless to anyone that does not run windows VMs and/or does not use VMware.

    You do have oracle on a windows VM so maybe oracle on a solaris/bsd VM as well as oracle on a linux para-virtualised guest.

    There is also no mention of how, if at all, the VMs were optimised for the workloads they are running. In particular and most importantly how are the DBs using the disks? Where is the data and where are the logs? How are the disks passed on to the VM (local file, separate partition, virtual volume, full access to one/more drives etc etc).

    Way too many variables to make any kind of an accurate conclusion in my opinion.
  • phoenix79 - Wednesday, August 11, 2010 - link

    I'm curious as to why you didn't include a quad-socket Magny-Cours system. I would have been very interested to see how it would have stacked up in this article.
  • Stuka87 - Wednesday, August 11, 2010 - link

    Ditto, I would like to see the best from each CPU maker. To really see which has the best price:performance ratio.
  • davegraham - Wednesday, August 11, 2010 - link

    if vApus II was available i could run it on my Magny-Cours.

  • JohanAnandtech - Thursday, August 12, 2010 - link

    The Dell R815 and quad MC deserve an article on their own.

Log in

Don't have an account? Sign up now