Home > Blogs > Virtual Reality


It’s no surprise that vSphere 5 holds up under pressure, but what about Hyper-V?

Before we head out to VMworld, I want to share with you some fascinating test results just published by Principled Technologies that compare vSphere 5 performance and scalability to Microsoft Hyper-V Server R2 SP1.

When Microsoft released Windows Server 2008 R2 SP1, they added a feature called “Dynamic Memory” that they claimed brought them into parity with vSphere in VM density – the number of VMs doing useful work a host can support. We’d tested previous releases of Hyper-V without Dynamic Memory and found that, without the ability to overcommit memory, Hyper-V would hit a VM density brick wall far before vSphere reached the point of diminishing returns. Would Dynamic Memory yield a breakthrough improvement for Hyper-V? We had our doubts because of Dynamic Memory’s reliance on in-guest ballooning as its only way to reclaim memory from guests to support memory overcommitment. We knew from our history with ESX, ESXi and vSphere that getting good, predictable performance when VM density gets high and host memory is overcommitted requires more than just ballooning. We’ve built an array of technologies into vSphere that have been optimized for over a decade to make it a platform our customers feel comfortable with when pushing resources to the limit.

To get an answer, VMware commissioned Principled Technologies to do a side-by-side comparison of vSphere 5 and Hyper-V R2 SP1 throughput when running a SQL Server workload under high VM densities. They used the well-respected DVD Store Version 2 benchmark to measure total throughput delivered by a host running 24 VMs, and then 30 VMs. With 24 4GB VMs, the 96GB host was just reaching full memory commit, and 30 VMs pushed it to 25% memory overcommit – familiar territory for vSphere users.

The results won’t surprise vSphere customers – here’s how the VM-by-VM score looked:

clip_image002

When Principled Technologies added up the throughput of each VM, vSphere 5 delivered 19% more aggregate throughput (orders per minute as measured by DVD Store) on the host running 30 VMs.

clip_image004

Findings that really pleased our vSphere engineers became evident when Principled Technologies dug into the benchmark results a little deeper. One of the key behaviors we seek with vSphere is fairness across the VMs. Assuming equal resource shares and limits, we want each VM to perform as well as its neighbors. Too much variability would be unfair to your users who might get their workloads stuck on an underperforming VM. vSphere 5 came out ahead in fairness as shown in the figure below with a tighter standard deviation in throughput across the 30 VMs as the smaller height of the vSphere box shows in the chart below.

clip_image006

Another striking validation of vSphere 5’s scalability advantage over Hyper-V R2 SP1 was shown when Principled Technologies compared aggregate DVD Store throughput for the 24 VM and 30 VM cases. For Hyper-V, its throughput dropped by 3% when six VMs were added. Evidently, Hyper-V with Dynamic Memory doesn’t hold up so well when you make your VMs do some real work once the host memory becomes overcommitted. In contrast, vSphere 5 throughput increased by 11% as those six additional VMs were added. vSphere 5 is clearly handling the 25% memory overcommit condition with ease.

clip_image008

So, thanks to Principled Technologies, we have the answer to our question: vSphere 5 holds up better under workload and memory pressure to let our users reliably achieve higher VM densities and that means better scalability and lower costs. You can access the full report from Principled Technologies titled, “Virtualization Performance: VMware vSphere 5 vs. Microsoft Hyper-V R2 SP1” on their Web site here, or we’ve also posted a copy on our site here.

9 thoughts on “It’s no surprise that vSphere 5 holds up under pressure, but what about Hyper-V?

  1. Sergey

    Have you ever seen any benchmark there VMWare lost to any other technology?
    No! It is just because you need to get approval from VMWare to publish your findings. Guess what will happen if VMWare don`t like your findings? They will sue you for publishing it.
    As a result industry faces only good reviews about VMWare.It is so bulllshit.

  2. Eric Horschman

    Sergey,
    Sorry, but VMware regularly reviews and approves requests to publish performance benchmarks of our products where other products come out looking good. Take a look at some of the reports by Project Virtual Reality Check (www.projectvrc.com) for examples.
    Eic

  3. Mike Kline

    This tells me that Hyper-V is catching up and Windows 8 is on the horizon. VMWare has to be worried about that.
    Other Microsoft products that caught up and now are the leader. Exchange, Active Directory, SQL, and Sharepoint.

  4. Dennis Marinos

    I currently use Vmware.
    Hyper V is free, VMware costs over $30,000 a year in my environment.
    With that $30,000 i can save i will be moving to Hyper V and buying another Host and have change left over.
    The new host will give me more than then 18.9% increase in performance i would have got from Vmware.

  5. Eric Horschman

    Dennis,
    If you’re looking for a free hypervisor, check out vSphere Hypervisor. It has all the architectural and performance advantages of ESXi 5.
    What separates free hypervisors from complete virtualization solutions is the management component. You’ll find if you want to manage Microsoft’s free hypervisor that you’ll need to purchase System Center (Microsoft does not give it away.) When you add in the costs of the System Center pieces you need to come close to vSphere + vCenter, you’ll end up spending more with Microsoft. I recommend you run your numbers in the VMware Cost Per Application Calculator (www.vmware.com/go/costperappcalc) before making a decision that’s likely to cost you more money.
    Eric

  6. YesYouAreDumb

    Saying Hyper-V is free is like saying getting food from the dumpster behind your grocery store is free. Yes you didn’t pay up front for it, but you’ll be feeling the pain later, trust me.

  7. randy

    While I am always cautious about vendor propaganda, Eric is right about total outlay of cost and functional comparison. My group did a 6 month comparison between hyper v and ESXI 4.1. Results were similar functionality but ease of Vm management was greatly improved using ESXI.
    Then we compared the same host environments after purchasing Sys Center and VC 4.1 Ent plus. VM was the clear leader and while slightly higher in cost the gap was closed when we got a volume discount

  8. WA

    MS is claiming they made improvements in Server 2012, not only on the hyper-v part but also on the supporting storage side.
    Lost of marketing talk but still the numbers tell me they blow VMware away.
    Check the following for a ppx and video stream
    http://channel9.msdn.com/Events/TechEd/NorthAmerica/2012/VIR311
    Is there any comment from VMware on this? Do we have any comparisons from independent sources?
    MS Server 2012 is still to be released but looks promising in its virtualization capabilities.
    Point is my company is paying for the full MS package and is paying extra on top for VMware and the top of the edge SAN. And more for the replication to our DR site where we will get that included in Server 2012. Why?
    (a powerpoint will not make me change the virtualization solution that we have in place for 600+ servers but am just wondering about numbers, how does it compare)

  9. Eric Horschman

    WA – The Microsoft IOPS benchmark used an all-solid state drive setup, so it is not comparable to storage benchmarks published by VMware that used disk-based SANs. It’s not a directly comparable result.
    Regarding the Hyper-V Replica feature, keep in mind that it does not provide any of the DR automation features included in vCenter Site Recovery Manager. All you get is basic virtual disk replication, so you’d need to add lots of manual processes or brittle scripting or orchestration setups to get a true DR solution. With vCenter SRM, all of that is in the box.

Comments are closed.