A couple of months ago we ran a webcast with Intel Fellow, Rich Uhlig, VMware Chief Platform Architect, Rich Brunner and myself. The goal was to talk about the past, present and future of virtualization. In preparation for the webcast we solicited questions from all of you, unfortunately we only had an hour during the webcast to address them. Rich Uhlig from Intel, Rich Brunner from VMware and our own Johan de Gelas all agreed to answer some of your questions in a 6 part series we're calling Ask the Experts. Each week we'll showcase three questions you guys asked about virtualization and provide answers from our panel of three experts. These responses haven't been edited and come straight from the experts.

If you'd like to see your question answered here leave it in the comments. While we can't guarantee we'll get to everything, we'll try to pick a few from the comments to answer as the weeks go on.

Question #1 by Andrew D.

How would you compare the product offering of VMWare to those of its key competitors, whit kind of performance hit can I expect running Windows from within a virtualized environment, are there any advantages/disadvantages for leveraging an Intel platform as opposed to an AMD one for a VMWare solution?

Answer #1 by Johan de Gelas, AnandTech Senior IT Editor

The performance hit depends of course on your application and your hardware. I am going to assume your server is a recent one, with support for hardware accelerated pages and hardware virtualization. You can get an idea of the performance hit by looking at perfmon and the taskmanager of Windows. In the performance tab of the task manager you can enable "show kernel times". The more time your application spends in the kernel, the higher performance hit. The performance hit also depends on the amount of I/O that you have going on.

If your app spends a lot of time in the kernel and has high amounts of I/O going on, the performance hit may be high (15-30%). But that does mean your application will have to suffer this performance hit. If you spend more time on optimizing (database buffering, jumbo frames) and if you use paravirtualized drivers (VMXnet, PVSCSI) the performance will get a lot smaller (5-10%). In short, performance hit can be high if you just throw your native application in a VM, but modern hypervisors are able to keep the performance hit very small if you make the right choices and you take some time to tune the app and the VM.

If your application is not I/O intensive, but mostly CPU intensive, the performance hit can be unnoticeable (1-2%).

AMD versus Intel: we have numerous articles on that on Anandtech. There are two areas where Intel has an objective advantage. The first one is licensing. The twelve-core AMD Opteron 6100 and six-core Xeon 5600 perform more or less the same. However if you like to buy VMware vSphere essentials (which is an interesting option if you can run your services on 3 servers) you get a license for 3 servers, 2 CPUs per servers and 6 cores per CPU. You have buy additional licences if you have more cores per CPU.

If your IT strategy involves buying servers with the best RAS capabilities out there, Intel has also an advantage. Servers based on the Xeon 7500 series have the best RAS features available in the x86 space and can also address the most memory. These servers need more power than typical x86 servers, but you can consolidate more VMs on them.

For all other cases, and that is probably 80-90% of the market, only one suggestion: read our comparisons in the IT section of Anandtech :-). The situation can quickly change.

Question #2 by Colin R.

How is the performance of virtualization of high throughput devices like networking and storage developing?

Answer #2 by Rich Uhlig, Intel Fellow

One trend is that new standards are being developed to make I/O devices more “virtualization friendly”. For example, the PCI-SIG has developed a specification for PCI-Express devices to make their resources more easily shareable among VMs. The specification – called “Single Root I/O Virtualization” (or SR-IOV for short) – defines a way for devices to expose multiple “virtual functions” (VFs) that can be independently and directly assigned to guest OSes running within VMs, and remove some of the overheads of virtualization in the process. As an example, Intel supports SR-IOV in our recent network adaptors. A big challenge with direct assignment of I/O devices is that it can complicate other important virtualization capabilities like VM migration, since exposing a physical I/O resource directly to a guest OS can make it harder to detach from the resource when moving VM state to another physical platform. We’ve been working with VMM vendors to tackle these issues so that we can get the performance benefits of direct I/O assignment through SR-IOV, while preserving the ability to do VM migration.

Question #3 by Bill L.

Are the days of bare metal OS installs numbered? If so, when should we expect to see ALL NEW servers ship with a hypervisor? Will hypervisors have virtual switches in them in the future or will network and storage traffic bypass the hypervisor all together using technologies such as SR-IOV, MR-IOV, VMDirectPath, etc.?

Answer #3 by Rich Brunner, VMware Chief Platform Architect

I do expect that at some point, bare metal hypervisor installs will reach a plateau in the enterprise and service provider environments, but I do not expect that embedded hypervisors will be the only alternative. There has been some industry buzz about PXE boot of hypervisors (this is much more than PXE boot of an installer) and a move toward a truly stateless model. I expect to see more of this; stay tuned. SMB may still want a turn-key solution which either has an installed hypervisor from the Server Manufacturer or an embedded hypervisor.

I do not expect that the network and storage control traffic will ever "bypass" the hypervisor; the hypervisor will always be involved in ensuring QoS, ACLs, and routing for this traffic. Even for SR-IOV, there is a fair amount of control required by the hypervisor to make this work. I can see that the actual data traffic can bypass the hypervisor to reduce CPU overhead provided that the hypervisor has sufficient audit control of this data. VMware and others are working to ensure that in the future for SR-IOV devices.

MR-IOV can be transparent to the hypervisor on a single system instance, but the load balancing is a perfect target for control by a centralized management agent across the multiple system images that share the resource (e.g. blades in a chassis share a high-performance NIC which is load-balanced by the management agent across the blades ).

POST A COMMENT

42 Comments

View All Comments

  • duploxxx - Wednesday, July 28, 2010 - link

    then VMware will have to take all the trouble of the different vendors, combinations, hw changes, patches.

    check the Vmware history, they want to stay vendor nuetral as much as possible.

    There are vendors available like Datacore who offer virtualized storage.
    Reply
  • mpsii - Friday, July 23, 2010 - link

    I am having a hard time trying to determine the best hardware for server and desktop virtualization. There do not seem to be any benchmarks showing the performance comparison of, for example, a Phenom II X6 vs Core i7 (quad) processor. Some questions that arise:

    1) Given that more is better, when considering budget constraints, are more CPU cores better than more systems (one hexa core vs 3 dual core systems)?

    2) Or, is one system with 32 GB of RAM going to perform better than 2 systems with 16GB of RAM?

    3) Is an Opteron any better than a Phenom II?

    4) Is a core i7 that much better than a core i5? Core i7 vs Xeon?

    5) For desktop virtualization, what is the best hardware? or best for price/performance?

    This is information I cannot find to determine what hardware is needed. The difference in price between a single quad-core Xeon and a quad-core i5 is significant. A $200 Phenom II X6 is loads cheaper than a $800 hexacore Opteron.
    Reply
  • spddemon - Friday, July 23, 2010 - link

    mpsii,

    VMware releases benchmarks on server hardware in a virtual environment and there is no such thing as a quad core i5 server CPU.

    here are the vmmark benchmarks.
    http://www.vmware.com/products/vmmark/results.html

    and here is the overview of what vmmark is.
    http://www.vmware.com/products/vmmark/overview.htm...

    anand has discussed vmmark quite a bit and has discussed vmware's support for different hardware platforms equally. But the fact remains. from a support basis it is extremely difficult to support all hardware platforms. thus the necessity for validation and certification...
    Reply
  • mpsii - Monday, July 26, 2010 - link

    Thank you for your response. I have looked through those benchmarks with interest only to find the hardware that I am unable to purchase due to budgetary constraints.

    Though there is no core i5 "server" CPU, there are cases where commodity hardware is cheaper to run than having a dedicated server-class infrastructure. It would be nice to see how VMWare products stack up with commodity hardware such as quad-core i5/i7 or Phenom II X4/X6.

    Utilizing iSCSI storage combined with commodity hardware, a lot of older server systems can be decommissioned while their applications run merrily along for a fraction of the cost (lease or purchase) of dedicated server systems. Personally, any quad-core processor on a motherboard that supports 16GB of RAM qualifies, in my mind, as a potential/entry-level server system. For web nodes, workgroup-class databases, and testing environments, there is a lot to be said for using a desktop quad i5/i7 or Phenom II X4/X6 over even entry-level 1U rack systems.
    Reply
  • HMTK - Wednesday, July 28, 2010 - link

    You use the hardware that is supported by either the software vendor (VMware, Microsoft, Citrix, ...) or you rely on the supplier of the hardware to provide support for the virtualization software. If neither supports the combination you wish to use, you don't use it (for production, testing is something else). You're right that a quad core machine with 16 GB RAM is good for a simple server but you'd run into hardware limitations mighty fast. RAM is the first. Most single cheap socket machines have 6 RAM slots max, more likely 4. If you could use 8 GB modules in such a machine, be prepared to sell a limb or an organ. It would be cheaper to get a dual socket machine with slower CPU's and 2 or 4 GB RAM modules. OR start with a single CPU in such a system and upgrade the CPU along with RAM as you need. So you can see, there would be only a small market for single socket servers and hence no good reason to support them.

    And don't talk to me about no brand products...

    Yes, I've got vSphere 4 running on an Athlon x2 4200 with 8GB RAM and it works fine.
    Reply
  • duploxxx - Wednesday, July 28, 2010 - link

    vmmark is ridiculous and outdated and you can't compare ESX with workstation and server edition. One thing you can conclude though based on for example Vapps from anandtech, you clearly see that Intel can only win with high ghz cpu against high core count low ghz amd. If you know bring this back to home brew design, there is a bit difference, here you have high ghz 6core in phenom x6 for the same price as way lower ghz 4 core intel for the same price. So choice is easy there is no such bargain as the X6 phenom for that price and the virtualization power you get, yes Intel will give you more power but you'll have to pay quite a lot more to buy those uber intel 6cores.

    btw don't forget to buy a decent disk system, that is the first thing that will kill your virtual environment.
    Reply
  • the901 - Saturday, July 24, 2010 - link

    Really? No mention of Citrix at all. XenApp completely smokes vApp in so many ways from a support point of view. View4 really isn't as granular as XenDesktop when it comes to environments that need the detail. From my own testing, HDX is better than PCoIP for my remote users over vpn. Yes, VMware makes it easier to setup and I do like that. In the end, I like the ability to fine tune and Citrix allows that. Reply
  • duploxxx - Wednesday, July 28, 2010 - link

    you can also run xenapp on Vmware you know? Reply
  • Kingstu - Saturday, July 24, 2010 - link

    Is work being done for virtualized OS support on the Intel smartphone platform? I know that a while ago there was talk of VMWare doing that and with mobile processors getting faster and more powerful is that scenario more likely? Reply
  • vision33r - Saturday, July 24, 2010 - link

    Anyone who has seen VMware and Citrix virtualization solutions kows that VMware only excels with standalone servers and they have no end to end solution with Terminal services or distributed VDI techology.

    Vmware falls behind just about any other VDI upstarts today in delivering a virtual desktop.

    Who cares about virtual servers, it's done. HyperV is free if you have Microsoft software assurance and integrates with Windows natively.

    Citrix Xendesktop provides a better distributed vDeskop than anything Vmware has to offer.

    Can VMware rDesktop do Multimedia and graphics intensive apps?? Nope, Citrix has HDX can support graphics intensive apps in their vDesktop.

    Citrix Provisioning services also completely beats Vmware's linked clone disk concept.
    Reply

Log in

Don't have an account? Sign up now