Year: 2005

?Customers investing in 64-bit technology will be pleased with SWsoft?s commitment to computing and performance advances,? said Serguei Beloussov, CEO, SWsoft. ?Virtuozzo is the first server virtualization solution to use the maximum computing power of Intel and AMD. Virtuozzo?s architecture is better able to take advantage of underlying hardware and software and doesn?t have to recreate technology to recognize full potential.?

“Worldwide revenues for virtual environment software, the aggregate market containing virtual machine software, grew nearly 25% between 2003 and 2004,” said Dan Kusnetzky, IDC’s VP of system software research. “Virtualized environments supported on high-volume, powerful, and yet, relatively low cost 32- and 64-bit hardware can help organizations reduce costs in some important areas while still allowing them to implement IT-based solutions offering real business value.”

Unmatched Server Virtualization Extended
Virtuozzo server virtualization for Linux and Windows creates multiple isolated Virtual Private Servers (VPSs) on a single physical server enabling each VPS to perform and execute exactly like a stand-alone server. Unlike other hardware emulation approaches to virtualization, Virtuozzo provides Operating System (OS) level virtualization.

The core benefits of Virtuozzo include:

– High Performance
?Thin? technology that adds no system calls or overhead

– Expansive Hardware and Software Support
Interacts with existing OS and hardware; fully supports native 32 and 64-bit, SMP, 16-CPU and 64 GB RAM

– High Scalability
Interacts A single physical server can house tens or hundreds of VPSs

– Complete Isolation
Each VPS is completely isolated using a Kernel Abstraction Layer and Virtuozzo File System

– Robust Resource Management
Complete control over CPU, memory, disk and network I/O

– Powerful Management Tools
Easily manage large and potentially remote groups of servers and VPSs with a full set of administrative and VPS owner tools

Sam Greenblatt, a senior vice president at Computer Associates International Inc., in Islandia, N.Y., said that while the kernel is evolving for the desktop, server and embedded markets, more and more technology is being included, and the kernel is “getting fatter. We are not interested in the game drivers and music drivers that are being added to the kernel. We are interested in a more stable kernel.”

Andrew Morton, the current maintainer of the Linux 2.6 kernel, who works for Open Source Development Labs Inc., in Beaverton, Ore., said there is no formal road map for an enterprise Linux feature set since the development of those technologies rests largely with vendors such as Red Hat Inc., IBM, Novell Inc. and CA.

“We are pumping feature changes into the kernel at an enormous rate,” said Morton.

Still, Morton took issue with Greenblatt’s contention, saying that most new features are optional and that their use is at the discretion of organizations compiling their builds of the kernel.

Morton said new features should continue to be added to the stable 2.6 tree rather than forming a new 2.7 development tree.

Critics of the development process point to growing competition among vendors to get code for new features accepted. But Morton maintains that the competition is healthy because it helps top-level kernel developers understand what subfeatures are required and what other users need.

On the enterprise front, Morton said he expects to merge code from Cambridge University’s Computer Laboratories’ Xen virtualization technology into the Linux kernel within the next few months. Xen “does the right thing technically,” unlike other technologies, which are mainly workarounds for the fact that the operating system is not appropriately licensed, Morton said.

But CA’s Greenblatt disagreed, saying that other virtualization technologies, such as one from VMware Inc., in Palo Alto, Calif., currently fill the virtualization role.

“We would be happy to see a true hypervisor [an application that allows multiple operating systems to run concurrently on the same physical server]. We think [Xen] is great innovation, but its concept of virtualization is still not to the point that we want to see in there,” Greenblatt said.

Ian Pratt, a Xen project leader at Cambridge University, in England, said that Xen is indeed a true hypervisor.

“It runs on the bare metal and provides protected virtual environments for guest operating systems running on top of it,” Pratt said. “Because of the paravirtualized approach, where we make some modifications to the guest operating systems, we’ve been able to allow the hypervisor and Linux to work in a more cooperative fashion.”

On the issue of adding more clustering technology to the kernel, Morton said he hopes that clustering teams are working on factoring out common components for a merge into the mainline kernel.

InfiniBand, a channel-based, switch-fabric architecture from Topspin Communications Inc., in Mountain View, Calif., which was acquired last week by Cisco Systems Inc. , has already been moved into the kernel, Morton said, adding that the other InfiniBand stakeholders “seemed fine” with that decision.

This acquisition strengthens Cisco’s ability to provide customers with specialized networking technology and services to allow them to build their data centers in a flexible, grid-like fashion. The Topspin product line will extend Cisco’s data center switching solutions to include InfiniBand-based server switching and will complement Cisco’s existing network switching and storage switching solutions including its Ethernet-based Catalyst switching platform for internet/intranet infrastructure and its multiprotocol (Fibre Channel, FCIP, iSCSI and FICON) MDS switches for storage area networks.

Under the terms of the agreement, Cisco will pay approximately $250 million in cash and options for Topspin. The acquisition is subject to various standard closing conditions, including applicable regulatory approvals, and is expected to close in the fourth quarter of Cisco’s fiscal year 2005 ending July 30, 2005.

“The widespread adoption of server architectures such as blades, grid computing, and clustered applications is driving an emerging market opportunity within the data center. As our customers build out these new computing environments, it is important that we deliver server networking technologies to fit their needs. By adding Topspin’s server fabric switches and virtualization software, alongside our industry leading portfolio of Ethernet and SAN switches we are able to offer our customers compelling end-to-end data center switching capabilities,” said Luca Cafiero, Senior Vice President, Data Center, Switching and Wireless Technology Group, Cisco Systems.

Topspin products are targeted at data centers where customers are deploying high performance grid and utility computing, clustered enterprise applications, and/or server virtualization. These customers include enterprises, service providers, research institutions, and universities, with mission critical applications that are computational and data intensive and require high availability and manageability from the underlying infrastructure. Topspin’s technology delivers a compelling return to its customers on their IT investment dollars by improving price/performance, promoting resource flexibility, and dramatically reducing equipment and management costs.

This acquisition and the introduction of InfiniBand technology into Cisco’s portfolio offers customers another way to meet their application networking needs. Several major server vendors have announced support for InfiniBand technology as part of their clustering and/or grid solutions for both their standard and blade server solutions. Specifically, Dell, HP, IBM, NEC and Sun have all announced relationships with Topspin to provide InfiniBand-based server fabric switching as part of their portfolios.

To perform this study, AMD supplied VeriTest with one HP ProLiant DL585 AMD Opteron processor-based server and one IBM xSeries 445 Intel Xeon processor-based server. These servers were chosen because they were considered to be near-equivalent platforms from a configuration perspective. Both servers had quad-processor configurations, 16 GB of RAM, and four Intel 82543 Gigabit Ethernet Adapters. See Appendix A for additional server specifications details.

Surgient packaged applications leverage VMware virtual infrastructure?s scalability, manageability; security and efficiency to cost effectively automate delivery of enterprise applications on-demand.

?Companies like Documentum and Starwood are realizing the strong benefits that Surgient can provide by orchestrating virtual resources to deliver applications which solve real problems?, said Sameer Jagtap, Surgient Director of Product Management. ?We are pleased to leverage the very latest advances in virtual infrastructure technology from VMware.?

?Surgient applications are an excellent example of how VMware virtual infrastructure can be utilized to deliver applications that automate and enhance business processes?, said Brian Byun, Vice President of Alliances for VMware.

After that, the system started evolving to include other features. It ended being transformed to a system that deploys Virtual Machines for users based on a newly developed concept of templates. To run this infrastructure, you?ll need just an IIS Web Server, .NET Framework 1.1 and Virtual Server installed. No extra hardware or software is required.

The user interface is clean and simple, providing power to the user and reducing the learning curve to use the infrastructure. Some knowledge of Web browsing and minimum knowledge of the hardware you need for your VM and type of machine is enough to create your own Virtual Machines on it with simple.

The system also includes a client-side system service which runs inside the Virtual Machine. It is used to pass information from VSDM to the Virtual Machine and perform maintenance tasks, like renaming the machine. This a very important task because if you create Virtual Machines based from some image and they startup, Windows network will crash because another name already exists on the network. The VSDM Client prevents that by keeping the virtual machine name in sync with the VSDM database, avoiding network name collisions.

CW: To what extent will virtualization capabilities be built into the operating system?
JA: I hope everyone understands that virtualization is sort of a native part of an operating system from ground zero. We’ve virtualized the CPU to give processing. That’s what we do. And we’ve virtualized memory. That’s what virtual memory comes from. So all that’s happening now is, as the hardware progresses with more capability for virtualization, the OS is going to take advantage of it. Today we have stuff for products that are there because the hardware really doesn’t do everything we need it to do. But as the hardware does do it, it’s just a natural for the OS to support it.
On our current path, [there’s] some isolation that we do in Longhorn. Virtualization is not planned for Longhorn; well, that’s not true — some parts of it we are considering. But we won’t make it because the hardware won’t be ready. For example, virtualizing the I/O, it’s not there from the hardware, and that’s something that we would really like. So we will progressively extend the virtualization in the OS to take advantage of the hardware virtualization that’s there.

CW: Will you take features from your Virtual Server product and fold them into the operating system?
JA: What we want to do is take more advantage of the hardware as we move ahead.