Never Miss a Beat: Get a snapshot of the issues affecting the IT industry straight to your inbox.
July 15, 2011
4 Min Read
Cisco announced enhancements to its Unified Computing System and Fabric Interconnects for both data centers and cloud computing during its Cisco Live user group conference in Las Vegas, July 10-14.
UCS was Cisco's entry, in 2009, into the x86-blade market, with a design optimized for hosting virtual machines. It included a close alliance with VMware for managing the hypervisor's software switch, as well as a memory expansion technique that allowed a large amount of RAM to be installed on the blade.
And while Cisco faces increasing competition in its core switch and router business, it is showing competitiveness in the x86 blade business. Over the past two years, it's become "a top tier" blade supplier, in terms of market share, Cisco executives said at Cisco Live.
According to IDC's figures for the first quarter 2011 server market, Cisco holds 9.4% of the x86-blade server market based on revenue from factory units shipped, placing it ahead of Dell at 8.4%. HP was in the number one spot with 50% of revenue; while IBM was number two at 20.2% revenue share. They were the top four vendors in the blade market.
Blades are a new market for Cisco and it's important that the firm pick up market share, given its investment in UCS. It now has 5,400 UCS customers. Sales of blades are also growing faster than the server market as a whole; they now represent 20.5% of all x86 server sales, thanks to public and private cloud architectures frequently based on blades, and account for $1.8 billion in server revenue. That growth is at a rate that is about twice as fast as the general server market.
"Blades represent a higher-value sale for server vendors, being increasingly deployed in converged systems to support virtual environments," said Jed Scaramella, an enterprise server research manager at IDC. Converged systems, including Cisco's UCS, combine storage and communications traffic generated by virtual machines into a single I/O stream that is offloaded into the networking fabric. "After several years of being a highly consolidated market where the top three vendors accounted for over 80% of blade revenue, the recent entry of Cisco has introduced a viable new competitor to the market," he concluded.
Cisco officials told its Las Vegas user group meeting that its UCS blades have a new Virtual Interface Card 1280, which extends the amount of traffic that a heavily virtualized host server can handle. The card can provide up to 256 virtual adapters and interfaces, each of which may be linked back to a virtual machine on the server and provide an outlet for either Ethernet communications or Fibre Channel Over Ethernet storage traffic.
The card implements Cisco VM-FEX (fabric extender) technology, which maps a virtual network over the physical infrastructure and allows a network manager to generate a path from a switch in the external network fabric through the card and back to the virtual machine on a host UCS server. The path can carry both communications and storage traffic at "near bare-metal performance" in UCS systems, Cisco's July 13 announcement said.
Cisco also introduced VMware vCenter for Cisco UCS. VCenter is VMware's management software for managing a group of virtualized host servers. VCenter for Cisco UCS will provide a virtualization management platform that allows IT staffs to provision and configure a virtualized environment either in the data center or in branch offices, the announcement said. In some cases, customers will use Cisco's UCS Express on Cisco Integrated Services Routers, an embedded system in the router, to establish virtual environments in remote offices.
Cisco also said it was enhancing its Wide Area Application Service (WAAS) product line to improve the performance of an application that's offered as software as a service, or applications offered in other high-performance settings. It has added "the industry's first" context-aware redundancy elimination. Cisco's WAAS checks to see if information already exists at a branch office or other remote location before moving data from the data center to the branch. The feature can improve application response times and conserve network bandwidth.
WAAS includes a new Central Manager which can view and manage up to 2,000 WAAS instances, with application performance management metrics that allow a network administrator to see how individual applications are performing and execute root-cause analysis if a performance issue develops.
Data centers face increased resource demands and flat budgets. In this report, we show you steps you can take today to squeeze more from what you have, and also provide guidance on building a next-generation data center. Download it now.
About the Author(s)
Editor at Large, Cloud
Charles Babcock is an editor-at-large for InformationWeek and author of Management Strategies for the Cloud Revolution, a McGraw-Hill book. He is the former editor-in-chief of Digital News, former software editor of Computerworld and former technology editor of Interactive Week. He is a graduate of Syracuse University where he obtained a bachelor's degree in journalism. He joined the publication in 2003.
You May Also Like