Virtualization.com

News and insights from the vibrant world of virtualization and cloud computing

Video interview with George Kurian, Vice President and General Manager of the Application Delivery Business Unit at Cisco (Part 2/2)

by 1 Comment

In this second part of our interview with George Kurian, he explains about the capabilities of VFrame; being Cisco’s system’s management and provisioning that is aimed at the virtualized network and helps to put the virtual puzzle together.

Cisco recognizes the data center as a heterogeneous multivendor environment and plans to supports 3rd party technologies in the future. Cisco sees the notion of what a computer is today, getting truly blended closely with the network as interconnect speeds go up dramatically over the next two to three years.

Despite a fast moving environment Virtualization also offers IT professionals a significant career opportunity.

What is most important in the virtualization world is to not to think about your data center as traditional silos of storage, server, network, firewall, application…we need to bring virtualization into the network…we talked about both the Catalyst switches as well as the Nexus family and recently, our entire application delivery portfolio; application switching LAN acceleration techniques have got virtualization technology integrated into them. The second is …to bring networking intelligence into the virtual machine environment itself. So the ability to provide failover, traffic management, switching securities, and load balancing, those technologies that historically sat at the physical interface between the server and the network. The port now moved into the virtual machine and that’s really the technology roadmap for the next twelve months…

At Virtualization.com we are curious, if Cisco is going to make related products announcements at VMworld 2008.

Read the full transcript below or return to the first part.

0:05 Cisco has also announced VFrame? What type of capabilities does that offer?

George Kurian: VFrame which a system’s management and provisioning tool which we announced at Cisco Live a year ago, really helps to put together the virtualized network that compliments the virtual server environment. As we talked about to make virtualization real and operationally efficient, you need to have a virtualized network to compliment the virtual server and one of the things that our data center customers were telling us about is: ‘what’s most important in the virtualization world is to not to think about your data center as traditional silos of storage, server, network, firewall, application’. What they really are looking for is the service, which is putting all these virtual elements together. Now, VFrame especially with the VFrame 1.2 release, which we announced at Cisco Live this week, really completes putting together the virtual network environment. It’s got support for virtual LANs as well as virtual firewalls and recently, virtual load balancers as well as virtual storage. That really gives you a complete networking environment and then…

1:21 And also how to manage that?

Kurian: Yes.

1:23 Is that policy-based management?

Kurian: Policy-based provisioning tools and template-based provisioning models and what’s also interesting in the VFrame 1.2 release is we married that capability also now with the virtual server environment where VFrame 1.2 has tight integration with the VMware control center that allows you now to use the same policy-based provisioning model for VMware ESX servers.

1:49 Right. Are you trying to support other hypervisor, Xen, Hyper-V?

Kurian: Yeah. We absolutely recognized that the data center is a heterogenous multivendor environment. So, we’ll support other technologies in the future.

2:02 You just talked about the classic silos that are breaking up and do you see that the network manager and operator need broader skills to match all those new fields ? It is no longer just about the server and the firewalls and securities, storage. It’s all merging into the network.

Kurian: Absolutely. We see that virtualization offers all IT professionals a significant career opportunity to advance their own careers, and for the networking professionals themselves, we see that virtualization if you take advantage of the trend allows you to advance your career.

2:45 Do you have a role there? Could you help them or are you planning to…?

Kurian: Absolutely. Yes. At Ciscowe recognized to make virtualization work and be successful, our networking professionals need a much deeper understanding of the server storage and even application environments so that they can break through these silos. One of the things that we announced at Cisco Live this week was an augmentation to both our CCIE certification for our networking professionals that allows them to take advantage of new training and tools and get themselves data center CCIE certified. So in essence, they move from being a device and element management professional to actually a data center architect. The second was a series of programs for our channel partners so that they can also take advantage of these opportunities to be able to position themselves from being networking solution providers to really data center architects and solution providers. So, it’s called the data center network infrastructure program that we’ve made available now to our channel partners.

4:00 What about security evolutions, because today many organizations use VLANs to manage LAN security between the virtual machines, how do you see this evolve?

Kurian: There’re two aspects of what we see. I think the first is, as we talked about it, we need to bring into the switches and routers and security devices, the ingredients of virtualization. So, we need to bring virtualization into the network that phase is well underway. As we talked about both the Catalyst switches as well as the Nexus family and recently, our entire application delivery portfolio; application switching LAN, acceleration techniques have got virtualization technology integrated into them. The second is the phase that we are embarking upon and where we make very significant announcements over the next twelve months is to bring now networking intelligence into the virtual machine environment itself. So the ability to provide failover, traffic management, switching securities, and load balancing, those technologies that historically sat at the physical interface between the server and the network. The port now moved into the virtual machine and that’s really the technology roadmap for the next twelve months. So, stay posted for a lot of exciting announcements.

5:25 I think anything that will help the people in managing infrastructure is going to be curious from which management software is really going to be able to control all of these new features.

Kurian: Yeah. I think what we see, architecturally is a unified policy management model where you can implement policy for your physical servers and also extend that into the virtual domain and then from the product construct, you really see software extensions to our switching platforms.

5:59 How do you see the future of virtualization evolve? Where would you think is ahead of them in this field?

Kurian: I’d only think what we see are a couple of important things. I think the first is if you think about networking speeds and latency getting faster and faster and lower and lower respectively, you can, in essence, really extend virtualization to all aspects of IT systems. So, we do see down the road the opportunity to drive things like processor virtualization, memory virtualization, as interconnect speeds and latencies go up dramatically over the next two to three years. So, really the notion of what the computer gets truly blended closely with the network. In addition, I think when we see virtualization, we also see it extended into the application domain because today what we see is the IT infrastructures virtualize but on top of that, you’re having relatively monolithic and static applications, but what we see down the road there is that you can literally have any application be delivered to any device across any network.

7:15 George, thanks a lot for your insights and all the things you’ve told us about virtualization here at Cisco and we look forward to all those product announcements over the next few months.

Kurian: Keep posted. It’s an exciting time.

Video interview with George Kurian, Vice President and General Manager of the Application Delivery Business Unit at Cisco (Part 1/2)

by Leave a Comment

In this first part of our interview with George Kurian at Cisco’s headquarters we get to know how Cisco looks at Virtualization in the datacenter from three different sets of product capabilities: pervasive networking platforms, services and VFrame (provisioning and orchestration tools).


From his position as the vice president and general manager of the Application Delivery Business Unit at Cisco, he sees the need for server virtualization to be complemented with virtualization capabilities in the network and explains how his teams are engineering the network to be a facilitator for all the virtues Virtualization brings. The goal for George’s data center technology group is to make the network aware of the new atomic unit in the data center: the Virtual Machine and no longer the physical server or port. He goes on pointing to the Nexus series and new introductions for the Catalyst series with capabilities to support some of these (r)evolutionary trends in the data center. In essence Cisco is reducing the number of connections that the server has to have from roughly eight today to only two, thus simplifying power, cooling, cabling, the whole series of transformations in the data center and then from an operational standpoint, providing a single network that you need to manage.

Read the full transcript below or go to the second part.

0:04 George, welcome to Virtualization.com. Could you tell a little bit more about yourself and what you’re doing here at Cisco?

George Kurian: Hi Toon. I’m George Kurian and I’m the vice president and general manager of the Application Delivery Business Unit. We’re part of the engineering organization at Cisco and within Cisco’s engineering team, we are part of the data center technology group, the group that builds all our switching and so services platforms for the data center.

0:30 Okay and how does Cisco think about the data center and virtualization in particular?

Kurian: First of all, in terms of the data center itself, we looked at the data center from the lines of three different sets of capabilities, product capabilities. The first are pervasive networking interconnect platforms such as our Catalyst 6500 platforms that provide LAN to server connections. Platforms such as our MDS platforms which are for storage interconnects, InfiniBand which provide inter process or cluster communication interconnects, and in addition that recently introduced, the Nexus 5000 family, that provides access interconnects for servers to the network. So in essence of range of interconnect platforms, layered on top of that are services such as security services, load balancing application delivery services, WAN acceleration services that drives the performance of applications from the data center to the remote branches, and then putting all of that together is a layer of provisioning and orchestration tools that we call VFrame. So networking platforms, services and provisioning tools.

1:52 Okay. Let’s start off on how one can capture all the benefits like one of the major benefits of virtual machines that you can relocate, just put a lot of strain on the network? How did you deal with that?

Kurian: In essence, we believe, Toon, that virtualization of the server environment needs to be complimented with virtualization capabilities in the network. Because to be able to get the benefits of efficiency plus flexibility in that server virtualization tries to create, you need to have the network be a facilitator of all of that. So, specifically, some of the benefits that virtual machine motion has as well as different fail over scenarios that customers are used to around the physical machine environment bringing that to the virtual machine environment needs the network to be virtual machine aware so that you can have what we call transparent virtualization, and so a lot of work we’re doing in the data center technology group is to make the network aware now of the new atomic unit in the data center which is no longer the physical server and what we forever call the port but really now the virtual machine itself.

3:12 That’s also a big change if you look at like the Catalyst series as well as the jack-of-all trades where you would just plug in a firewall, routing device or whatever; whereas now, we’re moving to a whole new situation because some people call it the flat layered two-domain mess that is being created by virtual machines and hypervisors. How do you cope with that?

Kurian: The Nexus series of products as well as the Catalyst have important new introductions of capabilities to support some of the evolutionary trends that you see in a data center, right? The first one, which is still the most used by customers, is what we call server consolidation and standardization. This is the movement from a variety of distributed computing environments to a few standardized X86 environments in the data center. What consolidation especially with the movement of multiprocessor CPUs does is it drives a much higher density and bandwidth per slot. So the Catalyst as well as the Nexus 7000 series for example are much more dense platforms. In addition, what we see is the movement from more client to server-oriented applications to some of the more server-to-server communication paradigms introduced by Web 2.0 and other types of new applications. It drives a lot of what we call cross-sectional bandwidth and so there are new innovations both by the Nexus 5000 and 7000 series that take advantage of those new types of platforms.

Now, one of the new trends that we are seeing as part of what we announced, which we call the unified fabric, is the consolidation of a variety of currently heterogenous networking environments in the data center into a single unified networking fabric. The most important of the networking environments in the data center classically the LAN, which is an Ethernet environment, and then storage, which has historically been a Fiber Channel environment. What we announced in the end of January is what we call the unified fabric and what the unified fabric essentially does is bring some of the best elements of Ethernet simplicity, scalability, and cost efficiency together with the needs of fiber channel, for example, lossless transport, lower latency, and so on. And so we see that really transforming the next generation data center. In essence, reducing the number of connections that the server has to have from roughly eight today to two simplifying power, cooling, cabling, the whole series of transformations in the data center and then from an operational standpoint, providing a single network that you need to manage.

6:12 Okay. Are you working on standardization, an industry standards, to do this?

Kurian: Yes. We’re working with a combination of an industry partner ecosystem with players like the Intel and IBM and others as well as the ITF and some standardization bodies…We try to standardize some of these key technologies such as Fiber Channel over Ethernet.

6:36 What of type of bandwidth do you see within the Fiber Channels over Ethernet? We’re at 10 gigabyte today.

Kurian: Right.

6:41 How would that evolve? What timing do you think we’ll be able to do this?

Kurian: There’s certainly a movement in the Fiber Channel work to bring out 8 Gigabyte Fiber Channel on the Ethernet side. The two next levels of performance are 40 Gb and 100 Gb Ethernets. There’s a standard work in both of those performance levels that are in process.

7:08 Okay. When we talked about the virtualization capabilities that you want to build into the network, could you maybe tell a little bit about the differences there between the Nexus architecture and the Catalyst architecture?

Kurian: In essence, the benefits of Nexus and the Catalyst are roughly similar when you consider the interactions between the server and the network, right? I think what the Nexus certainly does is take density and per slot performance to a whole new level as well as what we see in the Nexus is the increased intelligence on the port basis because what we see in the Nexus world where we really have built that to be the platform of the next ten to fifteen years of data center. The physical NIC on server has now a lot more traffic behind and a lot more application environments hosted behind it so we brought a lot more per-port intelligence for example into the Nexus. We will see that intelligence also coming into upcoming versions of the Catalyst as well but that’s one of the hallmarks that we bring.

8:15 Today, that it really one of the bottlenecks in virtualization, all the I/O virtualization, going on?
Kurian: That’s right. In essence, you want to have quality of service now at the NIC itself right, because you’ve got this disparate application environment sitting behind that single physical interface.

Video interview with Nick Van Der Zweep, Virtualization Director at HP (Part 4/4)

by 1 Comment

In this fourth and final part of our interview with Nick Van Der Zweep we got some numbers that Virtualization at HP has grown over 80% last year and the claim that HP is

‘growing with VMware faster than VMware is growing in any industry’.

Also because HP has about half of the Blade market and Nick adds that:

‘the connect rate of virtualization to Blade Servers is much heavier than just Standalone Rack Servers. Blades are just an absolute natural fit for virtualization’.

With iVirtualization (not aimed at Apple), HP is adding backward compatible ‘integrated virtualization’ to its Proliant Server range. Another unique feature to the HP iVirtualization is the virtual console which can handle several environments (e.g. VMware, Citrix.) each with their multiple virtual machines. The standard I/O integrated lights out remote console management will automatically connects into the overall console or down right into each of the different VMs within the machine.

Read the full transcript below or return to the previous part

0:11 Could you give us some number on how important virtualization is to HP?

Nick Van Der Zweep: To our business, it’s absolutely critically important and we’re seeing the numbers rolling in from a connect rate perspective.. A few numbers that I know of: integrity systems with the software per virtualization on our Integrity servers grew at about 120% in the last year so that’s a pretty strong growth. VMware numbers I think are public as to how VMware has grown somewhere in the eighty to some percent range which is very good. Our VMware connect rates on our X86 servers have grown beyond that. So we’re growing with VMware faster than VMware is growing in any industry.

Other areas that might be of interest in virtualization space are Blades. The connect rate of virtualization to Blades is much, much heavier than just Standalone Rack Servers. Blades are just an absolute natural fit for virtualization. It was something that we focused on when we designed our C class Blades systems and we’re doing well in the industry because we focused so much on enabling virtualization with that platform. Close to 50% market share in the industry which is outstanding to say the least and then part of what we put in there was HP Virtual Connect in order to make this really work well together, and that was the main product of year for us by a couple of different institutions. It’s really facilitating growth within HP with our management software, Blades, infrastructure virtualization and we’re taking more and more steps with our inside software management and VSC products as well.

2:03 Are we going to see a white ProLiant server soon, because HP launched iVirtualization and I think Apple will be curious to know what that would exactly look like?

Van Der Zweep: Well, actually, we will custom-paint any our infrastructure to match the decor that you want to put it into. So we can comply with whatever color codes that you want to have within your data center.

2:27 I think Steve Jobs is going to be very jealous of that. We can order pink Proliants now ?

Van Der Zweep: Right. If you want it, we can make it. iVirtualization definitely is a key point to us and that goes back to your partnership with VMware, Citrix, and Microsoft. Right out of the box, we get a ProLiant server and instead of saying boot from disc or boot from the network, its boot up the hypervisor, built right into this.

2:55 You’re actually shipping in with an extra flash card where these are precharged?

Van Der Zweep: Exactly and the interesting thing is even before we announced the integrated iVirtualization, we had that ability to add those flash cards. We have the USB capability built into our previous models, so we can upgrade existing models to an integrated virtualization as well. So, what’s inside exactly is that it’s got a USB key with the either ESXI software or for instance Citrix server or that type of software in virtualization.

3:29 From a logistical point of view that sounds like quite a challenge, because you’re shipping from factory… how do you keep close to the release cycles of the hypervisors to make sure you got the latest available version along with the hardware and ship this to the customers?

Van Der Zweep: Yeah because there’re flash drives, we can upgrade them and flash them back into the field as well as if they need upgrades. I think the more important thing is we’re not just putting a flash drive and some VMware, Citrix or such software within the machine, we add value around that as well. So, for instance, we introduced iVirtualization with a virtual console so that when you’re running, for instance, a Citrix environment and you set up multiple virtual machines, our standard I/O integrated lights out remote console management automatically connects into the overall console or down right into each of the different VMs within the machine and that’s again unique in the industry. We’re working so closely with our partners and adding value on top of it instead of just putting a CD in a box.

4:34 What about the virtualization services HP is offering because this technology is so disruptive that many departments seek help to get there?

Van Der Zweep: Yeah. The services that we offer range in spectrum, everything from macro view of data center consolidation and data center transformation services to architect, the physical data centers to look at how to consolidate, how to go from eighty data centers to six similar to some of the initiatives we’ve had even at HP, how to deal with the technology. If you did not touch virtualization technology before, we can train you to be able to implement that, to do capacity planning kinds of initiatives, support you after the facts. So, we’ve got a full range of services that can help you from design all the way through the execution.

5:28 Okay. Nick Van Der Zweep, thanks a lot for the time that you’ve give us and I hope to see you soon.

Van Der Zweep: You’re quite welcome.

Video interview with Nick Van Der Zweep, Virtualization Director at HP (Part 3/4)

by 2 Comments

In this third part of our video interview with Nick Van Der Zweep, Director for Virtualization at HP, he predicts Desktop Virtualization to be the next big tipping point in our industry. He adds this is one of the areas were HP is differentiating itself from IBM with a full desktop-to-data-center strategy.

“People like IBM are still struggling to catch up to that because they’ve got management systems for every platform that they have and trying to pull that together.  That’s critically important to be able to see holistic view of the entire data center…”

But also when it comes to flexible and usage-based data center pricing models and cloud computing, Nick claims HP is a pioneer with clients such as Dreamworks, rendering their movies on HP’s excess infrastructure.

The Opsware acquisition is referred to often in this interview when it comes to HP offering the full broad enterprise management software and configuration management with server automation. Nick also hints at their current investments in Virtualization related security offerings.

The interview was recorded at the HP headquarters in Cupertino, where Nick is often asked by financial analysts: ‘Is virtualization bad for your business?”. His clear answer is “NO”, as it unlocks the potential for businesses to do more and enables HP to sell a lot more robust configurations with a larger amount of condensed CPUs, much more memory, more I/O capability, etc.

Nick also shines a light on the future of virtualization, which will have (mostly free) hypervisors as a commodity. What really unlocks virtualization however is the management software and related automation capabilities. This is why HP bought and integrated a company like Opsware.

Read the full transcript below or read the previous part here or move on to the last episode.

So, we differentiate ourselves from IBM today by covering this desktop to data center that got out off the whole desktop space and this is going to explode.  Desktop virtualization is absolutely going to explode and that’s the next kind of big tipping point that we’re seeing. Integrated and we’re not afraid to take our technology off of our high-end systems, our nonstop UNIX systems.  We’re not afraid to put it on X86 and we put it there early and fast because that’s where the market needs it.  And so we’re proactively pushing that there.  For instance with our latest release, we took a whole bunch of technology that was only on Integrity and UNIX and brought it to Windows and X86.  So, desktop to data center, fully integrated stack up our management software, systems insight manager for a number of years has been able to manage across our entire portfolio of Integrity, Proliant, et cetera.  People like IBM are still struggling to catch up to that because they’ve got management systems for every platform that they have and trying to pull that together.  That’s critically important to be able to see holistic view of the entire data center.

1:19:  Virtualizations is actually also enabling cloud computing and  grid computing and all of these which are no longer coming from expensive mainframe hardware but virtual power through G4 X86 type of servers, and this brings us to usage-based pricing  models.  HP has been in there.  Did you have plans on offering infrastructure as a service or data center as a service?

Van Der Zweep:  So today, we already do sets of infrastructure service.  Data center has its service capabilities.  We certainly offer our Integrity servers on a usage basis where you buy the capacity almost like a prepaid mobile card where you buy 30 CPU days, and as you use it, it takes down in 30 minute increments. We also have adaptive infrastructure as a service.  We’re taking all of our capabilities of virtualization, automation, etcetera, in helping customers move to what we call an adaptive infrastructure and next generation data center.  And we’ve implemented that ourselves and provide that as a service to our customers.  This goes back to many years ago, four or five years ago for instance with DreamWorks, where DreamWorks wants this kind of environment where to render films, they’ve got a certain amount of capacity themselves but there’s peak times when they really need to get busy and so, we’ve got a whole set of technology, a whole set of data centers that can handle excess capacity, excess requirements from them to render films.  So we worked with DreamWorks and others to render films, do this in the manufacturing industry and others.  And it’s all paid by the direct kind of pricing.

3:09:  Okay.  What about HP server automation technology?  I know you’re a Virtualization Director.  How easy is it for all those administrators to use that and to deploy everything?

Van Der Zweep:  It was a very strategic acquisition for us to get into the whole infrastructure automation space, server automation, with the Opsware products and tying right back into server automation and configuration management.  Our infrastructure is very much the best infrastructure in the industry in providing management software there to advantage the infrastructure and some of that I’ve been describing.  But these all plugs in to our full broad enterprise management software and configuration management, and server automation as well.  The nice thing about teaming this together, you’ve got the ability to very quickly change your infrastructure but with the server automation, very quickly be able to change your applications, commission or decommission web servers and application servers quickly, and then with our infrastructure be able to redeploy those assets.  So, you have to do those two things in conjunction with each other.  It makes a lot of sense to put that on portfolio.

4:26:  Up to now, we talked a lot about the good new things virtualization can bring, but these new relationships between guest and host systems also popped up a lot of security issues.  It’s still very new although it’s been there for a few years.  It’s still quite a new technology.  How do you think virtualization security issues can be addressed?

Van Der Zweep:  Well, I think that’s evolving.  We’ve definitely been working with the vendors, the VMwares, the Citrix, our own technologies to make sure that the software is very hardened.  We’re looking at trusted computing models that can work in this industry as well.  Certainly, we’ve had those working bare-metal physical machines to get that working more so in the virtualization space.  So, I think that’s evolving over time.  We’ve got many offerings today to be able to help in this space but that’s another area of investment for us.

Video interview with Nick Van Der Zweep, Virtualization Director at HP (Part 2/4)

by 2 Comments

In this second part of our lengthy video interview with Nick Van Der Zweep, Director for Virtualization at HP, we get further introduced to how HP defines virtualization and how it differentiates from its competitors.

Nick also shares what typical Virtualization problems his clients are grappling with and what skill set is needed in IT departments to overcome the pitfalls.

Read the full transcript below, return to part 1 or go ahead to part 3

0:12 HP has one of the most complete virtualization solutions offerings. How are these portfolios integrated?
Nick Van Der Zweep:  That’s really where we started with some of our management software as I mentioned in the Integrity space back in 1999-2000.We had high availability and partitioning and pay-as-you-go and instant capacity in management software and we glued it all together so that we produce one-user interspace to that environment.  Just recently, we announced and started shipping last month Inside Dynamics which takes that software, makes it available to go to Integrity, ProLiant, X86.  One management footprints Systems Inside Manager which is known across the industry as one management software for ProLiant, Integrity, Discovery, fault management and from there it manages all the hypervisors up there, we can…

1:08  Does it do deployment automatically?
Van Der Zweep:  So, we’ve got deployment built in to it so through a WRAP Deployment Packet of deployed into bare-metal and they’re deployed to virtual machines. We support Citrix, VMware, Microsoft and so we took that software that higher level of management software Inside Dynamic VSC which represent VSC in the integrity space and really glued it together. What’s really interesting right now is that we can provide hypervisor-like capabilities even to bare metal machines and that interface brings that all together.  You can’t even tell if you’re working on bare-metal machine versus a VMware hypervisor. You can do moves from moving application from place to place within the infrastructure and whether be bare metal or its using VMware behind the scenes so definitely heavy integrated.
2:05  I’m very interested to know how HP views its competitive landscape in the virtualization industry?
Van Der Zweep:  I think, we are extremely well positioned in the industry to be able to help our customers in the whole virtualization space and then also help HP and our shareholders as well. And because we’ve got the capabilities of covering this from desktop to the data center, we have a huge what we call a personal systems group where we sell desktops, Thin clients, Blade PCs, virtual desktop environments. So we are heavily invested in that side of the technology as well as the server side technology as well.  Storage virtualization, server virtualization, we have a huge multi-billion dollar software organization within HP to deliver infrastructure management, our Opsware/Mercury capabilities are layered on top of that as well.  So, we’ve got a technological portfolio that I think is a number one bar in the industry that anybody looks at.  And then the services portfolio to be able to help customers, architectural data centers, to data center transformations, look at everything from power cooling environmental pieces of the puzzle because that’s comes in to virtualization very quickly as well as you know because we can design the data centers, and as well help people and customers to do installation support and ITIL practice because as you go into a shared environment and now your employees are sharing resources.  Well you better standardize the jobs across the data centers. So the people who are doing server administration are all doing it the same way, not doing it one way for SAP environment and another way for their Exchange environment, because it’s all shared infrastructure.
3:59 Do you think we need a new skill set out there? Now their tasks are merging: for the networking people and security people and storage people. They’re really now have to talk together?
Van Der Zweep:  They absolutely do.  So, there are two things that happen that we focus on that.  I think it’s really happening to the industry. One is standardizing their roles and responsibilities so that and their interlocks so that they can talk to each other.  But then again we do things that simplify the processes, automate the processes.  If you look at the likes of Opsware or even our Blade environment, we added something called virtual connect to our Blade environment putting in a virtual fabric, a virtual back plain.  Now, what we’re able to do with Virtual Connect Blades and Inside Dynamics is move a Microsoft Exchange environment running on one blade through a point and click, move it to another Blade in another enclosure. If you try to do that today within a typical datacenter, you’ve got to call up the server guy to install that on the new Blade.  You have to call the network guy up and have them move the VLAN information from that node to that node and you have to call up the SAN storage guy to say “I’m going to reroute all the SAN in order to make that movement happen”.  Whether or not you have hypervisors or not, you got to set all of these up three people which means a week worth of work.  We can do it point and click everything is automated.  All the steps happened and it’s done.  So, it’s a matter of working better together from a people perspective but also delivering technologies that bust through the processes of the past and automate them as well.
5:43  What are the typical issues that your customers are grappling with today?
Van Der Zweep:  The typical issues that they grapple with today certainly is out of macro level cost, how do we drive down cost agility, how do I be more responsive to the business so that when they say, “Hey I’m one of deploy infrastructure or new application or scale up I want to do that today.  I don’t want to do that in a month,” and then service levels.  People are constantly saying I’m moving towards more of an environment where instead of that it’s just one mission critical system on that one server that keeps the business running, everything is kind of connected together with the applications that we have today, services oriented architectures and such where you’ve got ten or hundreds of pieces of infrastructure that are working in concept which each other and you have to have a high availability to everything and so they are want to get that built in without complex clustering.
6:45  What about the greener side of ITs, there is also a lot of buzz around the green data centers, do you find that your customers –due to boosting energy costs- are looking for for cheap electricity bills and renewable energy sources and are they actually looking at what is this server consuming and if that’s being underutilized to have like lesser power  being consumed?
Van Der Zweep:  Absolutely.  So, we have customers especially in the enterprise based that have data centers that within the next what three, four, five years they do not have enough power to handle the growth where is that they’re having within that environment.  Well, they’d have to build an entire new data centers and that’s cost thing. And they don’t feel good about it from an environmental perspective and the cost that they pay to the utilities.  So they’re concerned about that. So virtualization can help there with the software that I described with Inside Dynamics, what we built into this release is that we’ve put in  the ability to do consolidation and it will automatically come back to you with scenarios. Here is your current scenario, and this is exactly how many kilowatts you’re using per month and you enter into it.  You tell what your rates are, so it says you’re paying three hundred and fifty dollars a month for these systems for energy. And then it comes back and says, “Well here is the new environment consolidated using virtualization.”  And we can actually tell you its hundred fifteen dollars a month is your exact energy cost that you would be paying versus today versus option A or maybe option B or C that was exciting when we were in Barcelona demonstrating this and we had four people deep and four people wide sitting in front of one screen looking at this and one person is going I need you to put in my rates for Sweden and share this because I got to bring this home.  It’s a hot area.

University of Toronto Announces Snowflock

by Leave a Comment

Andres Lagar-Cavilla wrote in to announce the news that he and his team have just released Snowflock.

Snowflock lets you clone Xen VMs into dozens of identical replicas running in different hosts. Snowflock can do this in less than a second and with very low runtime overhead. With Snowflock you can, for example,  perform parallel computations on the fly by scaling “instantaneously” your computing footprint in a shared cluster. Snowflock is a research prototype, hence the 0.1 major-minor. A minimum degree of experience with Xen and Linux is necessary to use the system.

Snowflock is the joined work of researchers at both the the Department of Computer Science, University of Toronto and at Carnegie Mellon University. Snowflock has been released in a binary and source release, under the GNU General Public License (GPL). The release is available at http://compbio.cs.toronto.edu/snowflock

Snowflock was presented earlier this year at the Xen Summit North America 2008. A more complete description of the implementation and functionality of Snowflock is available in this technical report.