Posts tagged with AMD
Windows 7: The Dawn of the Age of Client Virtualization
Posted by Margaret Lewis in 10:00 AM
I spend a lot of time on this blog talking about server virtualization – and rightfully so. The benefits are undeniable. But, client virtualization is something that I’m also passionate about. In fact, I’ve blogged about how I, along with other industry experts, am predicting a bright future for this market. Well, I’ve got exciting news for you: the future is now.
To me, today’s launch of Windows 7 represents a turning point. The benefits for client virtualization have been clear in the enterprise for a while: you can remotely manage a fleet of PCs, empowering your staff with greater flexibility when accessing information and you can potentially save costs on individual hardware for hundreds, or thousands of employees, depending of course on the size of your organization. For SMBs, the cost savings and direct impact was less clear, and for consumers it just hasn’t been something that’s ever truly broken into the mainstream.
But now, with Windows 7, every user can – and should – benefit from client virtualization. Whether you’re a Fortune 500 company with offices around the world, a small start up with 5 employees, or simply a consumer looking to get more out of your PC – there’s something for everyone here.
Let me explain.
SMBs around the world that rely on Windows are undoubtedly considering the upgrade to Windows 7. However, an upgrade process can be costly, time-intensive and complicated when you’re trying to make certain all of your business-critical applications will migrate. With Windows 7, SMBs can rely on XP Mode enabled via AMD-VTM virtualization technology to ensure their Windows XP applications can be used as part of their new Windows 7 OS.
Consumers can also benefit from XP Mode for the same compatibility reasons, but also for added security and customization, as XP allows them the freedom to operate a completely separate OS. This can assist with balancing work information and documents with home information and documents, or can allow you to deploy a separate OS (say, for children) to ensure your critical files are safe.
Consumers and business users alike want access to documents saved on their PC while they’re on the go. That’s where solutions like Citrix XenDesktop4 become so crucial with Windows 7. As Aimee Catalano wrote on our blog earlier this week, “This enables complete workplace flexibility, business continuity and user mobility.” I couldn’t have said it better myself. At AMD, we’re very focused on addressing today’s PC lifestyle, which includes both what users do on their PC, and how they access their applications and information.
It’s an exciting time to be in this industry. Multi-core hardware is more advanced than ever, the software keeps getting better and better and virtualization is at the core of how these new solutions allow dynamic user experiences. I’m predicting very big things for the client virtualization market not only in the coming years – but starting right now.
Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
The Virtual Desktop Revolution Is Here…for Everyone…
Posted by AMD in 6:19 PM
…And the timing couldn’t be better. Customers are looking for simpler ways to manage desktops, just as Windows 7 begins to drive another desktop refresh cycle. And, in these economic times, everyone’s looking to increase flexibility and efficiency. This is the promise of the virtual desktop, and why the Citrix announcement of the new XenDesktop 4 is making such a big splash in the market right now.
Citrix is excited to team with AMD to drive virtual desktops into the computing mainstream and make this all possible by making this ground-breaking product available for use with AMD hardware.
Join the Revolution NOW!
So, what makes XenDesktop 4 so special and unique compared to what’s currently out there? The answer is with five very important features:
- Any device, anytime, anywhere. Whether working from an office thin client, home PC or mobile device, users can instantly and securely access their desktops from office or remote locations using XenDesktop. This enables complete workplace flexibility, business continuity and user mobility – something Citrix and AMD are both focused on. Users can add or remove applications using a self-service enterprise app store from a variety of devices, including PC, Mac, thin client or Smartphone.
- HDXTM user experience. Deliver a high definition experience, over the network, with superior reliability and higher availability than a traditional PC. With Citrix HDXTM technology, users get an experience that rivals a local PC, even when using multimedia, real-time collaboration tools, USB peripherals, and 3D graphics.
- FlexCastTM delivery technology. Different types of workers across the enterprise need different types of desktops. Some require simplicity and standardization, while others need performance and personalization. XenDesktop is designed to meet all these requirements in a single solution with our unique Citrix FlexCastTM delivery technology. With FlexCastTM delivery technology, IT can deliver virtual desktops to user, on a variey devices. Each desktop is tailored to meet the performance, security and flexibility requirements with the goal of providing the best desktop for every user, every time.
- On-demand apps by XenAppTM. To help reduce desktop management costs, XenDesktop offers the full range of Citrix application virtualization technologies. With application virtualization, IT can control data access, manage fewer desktop images, reduce system conflicts, and reduce application regression testing. Adding, updating and removing apps is simple and self-service for users, enabling them to access applications instantly from anywhere on the network, while getting a high-definition user experience.
- Open architecture. XenDesktop works with your existing hypervisor, storage and Microsoft infrastructures, enabling you to leverage your current infrastructure – while providing the flexibility to add or change to alternatives in the future. Whether you use XenServer, Microsoft Hyper-V, or VMware ESX or vSphere, XenDesktop supports them all and simplifies management of networked storage using StorageLinkTM technology. XenDesktop will also closely integrate with Microsoft App-V and System Center for application management.
It’s clear that the demands of today’s workplace and changing how and where technology powers our businesses. I encourage you to attend the on-demand Secrets, Lies and VDI virtual event, where Citrix along with partners, including AMD, decode the myths and uncover the truth about desktop and application virtualization. Here’s a few more to check out:
Watch a video of CEO Mark Templeton discussing how the virtual desktop is revolutionizing IT and the way we work.
Visit the XenDesktop 4 web experience
Join the XenDesktop 4 community
Follow us on Twitter: @XenDesktop and use the hashtag #XD4
Aimee Catalano is a Senior Director of Alliance Marketing at Citrix. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
AMD Showcases Virtualization Innovation at VMworld Conference
Posted by Margaret Lewis in 2:17 PM
The AMD booth has been a busy place during the VMworld Conference. One of the big draws in our booth has been three proof of concept demos that showcase up and coming technology – graphics virtualization, I/O virtualization, and secure boot of a hypervisor. We have just posted images of these demos for folks who could not attend the conference and to showcase AMD’s continued efforts to drive the maturation of virtualization technology. We’ll also be uploading the videos of these demos shortly – so stayed tuned!
Graphics Virtualization
With virtual desktops becoming more commonplace, the need is growing to support richer graphic environments that have not been easily served by traditional server hosted clients methodologies. This proof of concept demo shows how direct device assignment for a graphics card could help support demanding graphics applications like computer aided design (CAD) and digital content creation (DCC). Please note that the upcoming AMD OpteronTM 6100 Series processors, code-named “Magny-Cours” referenced below, are scheduled to be launched in the first quarter of 2010.
The demo runs on an AMD engineering development system featuring two twelve-core AMD OpteronTM 6100 Series processors (code-named “Magny-Cours”), an upcoming AMD SR5690 chipset and an ATI FireProTM professional graphics card. This system is executing 3DMark®06 or “Toy Store”/”Code Zero” from within a virtual machine running on VMware ESX 4.0. The demo compares graphics performance with and without direct device mapping and utilizes AMD I/O virtualization technology for the graphics passthru. Support for AMD I/O virtualization technology is offered experimentally with VMware ESX 4.0.
I/O Virtualization
Certain applications requiring high network throughput have not been considered as candidates for virtualization due to the overhead associated with virtualization. I/O virtualization is designed to help reduce this overhead with a goal of achieving near native network performance. This proof of concept demo compares relative network performance with and without I/O virtualization.
The demo runs on an AMD engineering development system featuring 4 twelve-core AMD Opteron 6100 Series processors (codenamed “Magny-Cours”), four AMD SR5690 chipsets, and a Solarflare 10Ge network interface card (NIC). The system is executing a network benchmark, NetPerf, on a virtual machine running on VMware ES X 4.0. The demo uses VMware’s passthru support for the direct device assignment of a certified NIC. Support for AMD I/O virtualization technology is offered experimentally with VMware ESX 4.0.
Secure Boot
Security is important consideration for virtualization, particularly as more business critical applications move to virtualized servers. This proof of concept demo highlights the use of existing hardware capabilities of a production-level AMD technology-based server for secure configuration control of a hypervisor.
The demo runs on an HP ProLiant DL385 G6 server with 2 Six-Core AMD OpteronTM processors. The DL385 server includes a Trusted Platform Module (TPM) security chip that is built into the motherboard of the system. The demo shows a secure boot of the system with VMware ESX 4.0 using a secure loader written by AMD software engineers. During the boot the configuration of the hypervisor is compared to configuration information stored in the TPM to ensure that there have been no malicious or unintentional modifications to the hypervisor. The status of the hypervisor is reported in the vSphere management console as either being secure or insecure. This allows an operator to avoid using a misconfigured or compromised hypervisor in the datacenter.
Make sure you also check out the AMD Virtual Booth on VMworld.com and the AMD Opteron Friendfeed for more VMworld-related information.
Let me know your views on the evolution of virtualization technology.
Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD.
Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
A New Window on Client Virtualization
Posted by AMD in 4:00 PM
Congratulations to Microsoft as Windows 7 has reached an important milestone with its “release to manufacturing” (RTM), which means it is on its way to becoming pre-loaded on new hardware or a box on a retail shelf. In addition to a sleek interface and a number of new features, this new operating system continues the maturation of the client virtualization and also makes use of AMD innovations.
There are a lot of neat features in Windows 7 that should please consumers. If upgrading from Windows XP, the most noticeable difference for most users will be the new Aero interface. In addition to the rich graphics and intuitive design, there are features built in such as Aero Snap and Aero Clip that allow users to compare windows side by side, or quickly look at inactive windows without minimizing the entire desktop.
If you’re an IT Administrator, there are also features that can make your life a bit easier. If upgrading to Windows 7 and Windows Server 2008 R2 (which also announced RTM this week), a new feature called DirectAccess will allow you to manage remote PCs over the internet. And this same feature will allow your remote users to access network resources such as file servers and intranet sites without having to go through a Virtual Private Network (VPN) connection.
And speaking of remote users, if you are a mobile user who is looking to squeeze every minute of battery life out of your notebook, Windows 7 comes with a number of advanced power management features designed to help you realize power savings whether you are doing email during a layover or watching a movie on a long flight.
But, maybe one of the coolest features in Windows 7 is support of Windows Virtual PC and Windows XP Mode. With XP Mode, Microsoft has built in client virtualization technology that makes it easy to install and run Windows XP applications directly from a Windows 7-based PC, allowing users to enjoy the benefits of Windows 7 while maintaining support for legacy applications. Whether those applications are children’s educational games or Line of Business (LoB) applications for the enterprise – Windows XP mode is easy to install and use.
To run Windows XP Mode you will need to have a processor with hardware-based virtualization capabilities. All currently shipping AMD CPUs, with the exception of very low-end AMD SempronTM processors, include AMD-V TM a hardware-based virtualization technology needed to support XP mode.
Just remember that when using Windows Virtual PC (XP mode), you are essentially running two separate operating systems on your computer. If you don’t lock down that Virtual PC instance, you risk exposing your entire computer to a number of security risks. So remember to apply patches, turn on the Windows firewall, Windows Defender and install anti-virus software. In other words – whatever precautions you used to lockdown your Windows 7 environment? Take those same precautions for your Windows XP instance.
Microsoft has made a number of optimizations for the Virtual Desktop Infrastructure (VDI) environment. Notable is an enhanced version of the Remote Desktop Protocol (RDP) that allows for remote video playback in Windows Media Player 7, multi-monitor support and the ability to print local, without having to install drivers on the server. AMD has worked closely with Microsoft to deliver highly optimized virtualization platforms. Keep in mind that a senior Gartner analyst has predicted that the fastest growing server workload running in the data centre over the next two to three years is going to be the desktop.
In addition to virtualization, AMD has provided very strong support in the graphics arena. In fact, AMD just announced the release of the company’s first WHQL-certified ATI CatalystTM graphics drivers for Windows 7 RTM this week. We’re excited for the new OS here at AMD. How about you?
Matthew Kimball is a Product Marketing Director at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
AMD, Dell Talk Virtualization for SMBs
Posted by Margaret Lewis in 1:24 PM
I’m excited today to tell you about a virtualization webinar that AMD recently hosted with valued hardware partner, Dell. A few years ago Dell and AMD collaborated to create some of the industry’s first servers optimized for virtualization — the Dell PowerEdge R805 and R905 rack servers. In fact, earlier this year the Dell PowerEdge R905 won an InfoWorld Technology of the Year Award for Best Virtualization Server. Since then, we’ve continued to work together to fine-tune virtualization and are now expanding our efforts to reach SMBs — a rapidly growing area for virtualization.
In this Webinar, “Optimal Virtualization with AMD, Dell and Microsoft,” I join Antonio Sanchez, Senior Server Product Manager in Dell’s SMB segment to discuss the hot topic of virtualization for small and mid-sized business. We understand that many small businesses looking to utilize virtualization have questions. This session offers valuable information about how the software, hardware and processor technology must all work together to provide a superior virtualization solution. As you all know, that’s what I’m all about – the magic between the software and the hardware – and Dell and AMD are working hard with software partners like Microsoft to make that magic happen.
This is a must-listen for all you SMBs IT managers thinking about virtualization. Be sure to listen in and if it sparks any thoughts or questions, leave me a comment.
Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD.
Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
Cloudy Forecast for the Client Operating System
Posted by Margaret Lewis in 5:25 PM
Google recently posted a blog highlighting its plans to release the Chrome OS for both x86 and ARM CPUs in 2010. Google is making this move to provide mobile devices like netbooks and smart phones and with a fast and lightweight OS that gets people onto the web in a few seconds. The assumption is that the user experience takes place “in the cloud” – not on the client computing device and the OS is the vehicle to get you there.
A large number of articles and blogs have popped up on the web as the result of this blog. Since everyone loves a fight – everyone is picking a pairing. Some focus on a Google versus Microsoft battle – others on the x86 versus ARM. And of course this provides new fire power for the on-going open source versus proprietary software discussions since the Chrome OS is described as a basic Linux kernel with a new windowing system and the Chrome browser.
I believe the real issue revolves around where applications are executed. The bottom line – somewhere you need CPU and GPU processing power to execute the demanding applications and deliver the high-end visual experience we all have come to love.
In the Chrome OS world the entire computational action takes place in server farms with the client device providing a window into this world- it does not execute applications or store data. ”A netbook running Chrome OS isn’t likely to be able to do much when it is not connected to the Internet”, said Al Gillen, an analyst at IDC in a recent article by the Wall Street Journal “Google Targets Microsoft’s Turf.” The Chrome OS is banking on a fast and pervasive adoption of the Cloud Computing model – the web as the delivery vehicle for applications, data, and services.
This is in contrast to today’s most popular desktop, laptops, and mobile devices – most of which can surf the web and also execute applications. What does this mean? These devices have functions even when off-line – like playing games, watching a movie, listening to music, editing photos, or even writing a blog. This is the world where Microsoft Windows runs the majority of devices. In the government and commercial market, which accounts for a majority of PC sales, 70% of applications require Microsoft Windows, Gartner analyst Michael Silver estimates in another Wall Street Journal article “Chrome May Not Shine for Google.” That is why Microsoft is refining the client virtualization model in the upcoming Windows 7 OS to ensure that you – the end user ─ can continue to execute your favorite applications.
So who wins the battle of where applications execute? My crystal ball is cloudy today so I don’t have any predictions – but I believe we are in for an interesting time of innovation. I believe we’re moving toward server farms that can deliver impressive processing power of CPU and GPUs, client devices that can drive richer visual experience, and more and more demanding on-line application environments (take a look at my “Thunder Clouds” post to read about Facebook and some of their requirements).
The HPC world has been using the concept of compute farms to drive applications for years – check out the blog by my colleague Andy Parma wrote called “Is the Cloud a Cluster or is Cluster a Cloud” for interesting viewpoint on how the world is blurring.
And here is a fun fact – the first OS used for real work is generally thought to be GM-NAA I/O, produced in 1956 by the General Motors research division for its IBM mainframe ─ in an era where OS were mainly developed by the end user!
Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
Time for a Quiz? Freeways:LA as CPU Cores:[X]
Posted by Margaret Lewis in 9:29 AM
Earlier this month I attended Microsoft’s TechEd conference in LA, and the question that kept popping up throughout the show was: why more cores??
The interest in multi-core chips has been generated by AMD’s most recent roadmap update outlining our move to processors with 6-, 8- and 12-cores. The benefit of more cores, to me, is most easily equated to something I saw a lot of in LA – freeways.
Adding more cores is like adding extra lanes, allowing for more resources to drive virtual machines more effectively. Further, the more cores you add, the more CPU power you also have to divide among virtual machines, which means you can drive more overall VMs on that preverbal freeway. Essentially, you now have more room and more resources to drive up the efficiency of VMs across an entire system. A more detailed explanation on why more cores are useful can be found on Tim Mueting’s blog post on 4 Socket Servers and Real World Virtualization.
However, even AMD can admit: it’s not all about cores. Advancements in virtualization on the hardware level include features like “HyperTranport assist” – to be introduced with Six-Core AMD Opteron™ processor codename “Istanbul” – to provide optimizations at the cache level that are designed to show a real benefit in 4- and 8-socket systems. Since we are seeing virtualization customers focusing a lot of attention on these larger, robust platforms in terms of cores and memory, this new feature promises to enable improved performance and efficiency (two things we like!). The industry is starting to get excited about “Istanbul” – check out Quick Take: AMD Istanbul Update blog.
Also, as we move to more cores, We’re planning to introduce another exciting development in virtualization – the support of AMD-Vi (IOMMU) which is scheduled to hit the market later this year. AMD-Vi is designed to help improve security and performance by directly assigned devices to virtual machines. Further, continued optimizations are in the works to address the TLB, caches and improving the switching capabilities.
But what about the software? Plain and simple, hypervisors are ready and waiting for more cores. Microsoft, Citrix, VMware all have versions ready to handle the growing number of cores, with Hyper-V, XenServer, and vSphere. Our six-core “Istanbul” is due out in June and will be supported across 2-, 4- and 8- socket servers, which range from 12 to 48 cores! And, as we continue to grow our core count through our 12-core AMD Opteron processor codenamed “Magny-Cours”, expect to see even more collaboration with our software partners to make sure we’re optimizing to provide the most value to the end user.
Finally, talks are heating up around graphic virtualization and live migration across heterogeneous processor environments. Lots to get excited about – stay tuned!
Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
Four-Socket Servers for Real World Virtualization
Posted by AMD in 1:37 PM
Customers are often asking what server configuration they should choose for their virtualization environment. Do they go with a 2-socket multi-core based system, the traditional building block of the Data Center, or should they select a 4-socket server, which typically has more RAS features and better capacity in terms of cores, memory, and I/O better support their needs? It’s kind of like choosing to go on vacation with that convertible you love to drive on the weekends or your trusty sedan that you go to work in every day! They both have their purpose but one may be better suited for the task at hand.
A recent survey conducted by Gabriel Consulting Group highlighted some interesting x86 server purchasing trends. The largest market for x86 servers is still the 2-socket based servers, with almost 40% of the respondents saying they are planning on purchasing “more” or “many more” systems in the coming year. But, the survey also reflected an increasing interest in 4-socket servers with 33% of the respondents saying they intend to purchase these systems in greater volumes.
A key driver in this trend towards larger servers is virtualization. When it comes to virtualization, there are compelling advantages to be realized in implementing 4-socket or even 8-socket systems;
- Reduced hardware footprint. Particularly important for data centers that are space constrained and want to use fewer numbers of larger servers to consolidate both infrastructure and business application workloads.
- More cores. There is evidence that 2P servers can adequately support a large number of virtual machines running very light workloads where each virtual machine uses one or at most two virtual CPUs to get the job done.
- o However, for more demanding workloads, the more virtual CPUs you can assign to each VM (in other words, the more cores you have available) the better each workload will run. It should be noted that VMware’s recently introduced vSphere product has increased capabilities to support up to 8 virtual CPUs per VM, anticipating the continued migration of more demanding, production-level applications to virtualized environments.
- o A good example of this is seen in a paper highlighting the best practices for deploying Citrix XenApp with XenServer for HP ProLiant servers, where scalability is shown to degrade if you assign more virtual CPUs than there are physical CPU cores.
- Larger memory footprint. The amount of memory available is particularly important for resource intensive workloads that process large amounts of information or stream data to many concurrent user sessions as is the case with a virtual desktop infrastructure. AMD OpteronTM processor-based 4-socket servers like the HP Proliant DL585 G5 and the Dell PowerEdge R905 can handle up to 256GB of memory per server while the HP Proliant DL785 and Sun Fire X4600 can handle up to 512GB of memory while 2-socket servers can only provide up to 144GB of memory.
- Additional headroom for peak workloads. Often more demanding workloads like transaction-based business applications have less predictable workloads that peak with high demand. The additional cores, memory, and I/O capabilities of 4-socket servers give you this scalability edge to handle these bursts.
- Consolidation of larger numbers of applications. While theoretically possible, most IT shops are currently not running hundreds of virtual machines on a single server. But, optimal virtual machine density is still a goal of many organizations implementing virtualization today. Four-socket servers provide a reliable and highly efficient platform for consolidation particularly for data intensive or more heavily utilized workload.
No discussion on the benefits of virtualization and 4-socket servers would be complete without addressing the aspect of ROI. There is a fantastic article recently posted by Collin MacMillan that shows Shanghai Refresh Delivers ROI in 2-months using Intel’s ROI calculations for a Nehalem server replacement that yields an ROI in eight months. Collin also references an Intel/IDC white paper that concludes, “Systems based on 4P platforms provide better consolidation ratios and scalability than 2P platforms.”
In the end it’s all about having the right balance of resources – CPU, memory, network and storage. As system utilization increases to 50% or more through virtualization, there is an increased demand for balanced systems with the potential for providing higher levels of CPU and memory resources.
One thing is for sure, there is no one-size-fits-all when it comes to virtualization. Customers are finding more and more workloads that are suitable for virtualization due to technology improvements like you see with AMD Opteron multi-core processors with AMD-VTM technology. So which one is going to get you to your destination, the convertible or the SUV?
Tim Mueting is a Product Marketing Manager at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
Virtual Machines on the Move
Posted by Margaret Lewis in 5:15 AM
As you can imagine, migrating virtual machines without downtime is considered a core technology for building flexible and highly availability virtualized environments. So there were many questions around whether a hypervisor could gain widespread acceptance if it did not offer live migration capabilities. Fast forward to Spring 2009, and it is clear that Hyper-V has made a significant impact on the market.
In fact, a March article by Stephen Sowyer of Virtualization Review, highlights research by industry analyst firm, Gartner, who reported within the next five years “Microsoft and VMware will vie for bragging rights in the server virtualization infrastructure segment.” This builds on the October 2008 Worldwide Quarterly Server Virtualization Tracker from industry analyst firm, IDC, which concluded, “In its first quarter of general availability Microsoft Hyper-V delivered a strong showing, and when combined with Virtual Server 2005, Microsoft’s market share is 23% of new shipments.” These findings are truly significant given Microsoft entered the world of virtualization less than a year ago.
With today’s release of Hyper-V Server 2008 R2, Microsoft will offer live migration capabilities, enabling users to virtualize their IT environment in the most cost effective manner while having full access to enterprise-class features.
Now, a lot of folks new to virtualization don’t quite understand all the factors involved in making live migration a reality (in fact, I’m sure some of you are wondering why we keep blogging on the topic). To perform live migration with Hyper-V 2008 R2, you are required to have the failover clustering role added and configured on the servers running Hyper-V. Failover clustering requires shared storage for the servers in the cluster nodes so that all virtual machines can be stored in the shared storage area and running virtual machine state can be managed by one of the nodes (check out this great step-by-step guide on TechNet here).
An advantage for folks with a data center full of Quad-Core AMD Opteron processors—even various generations—is our stable platform approach enables folks to do live migration between the processor family (“Barcelona” to “Shangahi” to our upcoming six-core “Istanbul” processors) without losing any functionality—see for yourself as we migrate across all three generations with Hyper-V 2008 here.
This stable platform approach is something we also use for power efficiency. You may have seen that we recently announced our new low power (EE) processors which provide the same level of functionality as other versions but with a lower power envelope.
As you can imagine, I’m very excited about the live migration demonstration with Microsoft and its upcoming Hyper-V 2008 R2 technology. Working with the virtualization team over there has been a rewarding experience and I’m impressed with the inroads they have made on the virtualization market since the release of Hyper-V. I look forward to continuing to working with the team to push us all towards the “holy grail” of virtualization as it is a technology that truly enables a powerful and dynamic virtualization experience for customers.
Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.
Interoperable Management for Cloud Computing
Posted by Julie Lass in 2:54 PM
Today the DMTF (Distributed Management Task Force) announced it created a new group called the Open Cloud Standards Incubator to work on defining standards to help enable interoperable management of clouds. Many of the key leaders in the cloud computing space committed to collaborating in the Incubator to create standards that will be supported by the industry. You can read more about the announcement here.
This promising development in the cloud computing community helps address end-user concerns about cloud computing. Collaboration among cloud computing leaders can lead to easier management of cloud resources and improve interoperability between disparate private and public clouds.
DMTF is an industry standards group that brings the IT industry together to collaborate on the development, validation and promotion of systems management standards. Companies in the DMTF collaborate on management standards because our customers—IT customers—demand that we make our products easier to manage when they are deployed together in their environments. IT administrators do not want to be forced to use separate management tools and processes for each vendor’s product. That’s too complex and expensive.
The need for interoperable management is no different for a cloud computing environment. There are still multiple resources to manage from hardware systems and virtualized platforms to software and applications. In addition, clouds both within an enterprise and publicly available need to interoperate and, to some degree, be managed holistically. In order to make cloud computing easier to adopt and maintain, standards that simplify the management of these resources distributed among different clouds are needed.
Finally, I think the goal in the industry is to make cloud computing more cost effective, reliable and easier to maintain. We can help achieve this goal by putting good standards in place that we all support to simplify managing this complex environment. This standardization can help our customers significantly realize the full benefits of the cloud computing paradigm.
If you are attending Microsoft Management Summit this week you can stop by the DMTF booth (#437) and find out more about the organization and its standards. You can also visit AMD in booth #517 where we’ll be showing you some real-life examples of interoperable management with DMTF DASH.
Valerie K. Kane (@valeriekane) is a senior marketing manager at AMD and VP of Marketing for the DMTF. Her postings are her own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.






(12 votes, average: 4.67 out of 5)
