Cisco Blogs


Cisco Blog > Data Center and Cloud

Making the Jump to Light Speed

April 7, 2010 at 12:00 pm PST

by Harris Sussman,  Cisco Data Center Solutions -- Unified Computing System

 

Many of you will likely recall the following dialog from the original Star Wars film (1977), where the Millennium Falcon (Han’s Solo’s space ship) is speeding away from the Death Star:

Obi-Wan: How long before you can make the jump to light speed?
Han Solo: It’ll take a few moments to get the coordinates from the navi-computer. 
Luke: Are you kidding? At the rate they’re gaining?
Han Solo: Traveling through hyperspace ain’t like dusting crops, boy!

 Well, sorry I’ve dated those that remember, and for those having no idea what I’m talking about, check out the movie. I refer to this movie and scene in particular, because it reminds me about how advanced this film was at the time. In fact, the film was so progressive, the term “jump to light speed” is regularly used in peoples daily vernacular.

 When I look back and realize Cisco just announced the Unified Computing System a year ago, and ponder the test results gleaned from our new Intel Xeon 5600 and 7500 Series based blade server and rack server products, the term “make the jump to light speed” certainly seems fitting.

 Three weeks ago, Cisco announced historical results with our new Intel Xeon 5600 Series based blade server and rack server products captured in the table below.

Additionally, Cisco recently delivered test results demonstrating the scalability of our unique Extended Memory product, the B250 M2 using the Xeon Series 5600 processor. The following graph highlights how optimized the UCS B Series is for virtualization consolidation using a Microsoft SQL Server 2008 workload.

In a Cisco UCS B250 M2 Extended Memory Blade Server with vSphere, the Intel Xeon Processor X5680, and 384 GB of RAM handled 15 more virtual machines (VMs) than did the Cisco UCS B200 M2 Blade Server with vSphere, the Intel Xeon Processor X5680, and 96 GB of RAM, for a total of 115.38 percent more VMs. Please review detailed results at the Unified Computing System at Work page.

Just last week, Cisco announced 2 new Intel Xeon Series 7500 Processor based, 4-socket Blade and Rack Server products, the UCS B440 M1 and UCS C460 M1. The new Xeon 7500 Series boasts the biggest performance jump in Xeon history with new scalable performance, flexible virtualization and advanced reliability.

Read More »

Introducing the Second Generation Cisco UCS

April 6, 2010 at 12:00 pm PST

 

July will mark the three year anniversary of our Data Center 3.0 vision and in the intervening time, like clockwork, we have released products and technologies that have helped turn the vision into reality for our customers.  Today, we have a number of announcements that continue the trend.  While there are a number of cool new products including new members of the Nexus 1000 and Nexus 2000 family and new products from Tidal (which I will cover in subsequent blogs), today, I am going to start of with the next iteration of our UCS platform.

Last week, I blogged about the compelling innovation that Intel is bringing to market and the need to both build upon that innovation and deliver a balanced system design.  Our second generation UCS represents both of those goals by taking advantage of Intel’s newest offerings and adding our own special in the areas of I/O and management.

In a nutshell, the second generation UCS delivers

  • 4 times the compute capacity in the same footprint with 4-socket servers or 50% more cores in our 2-socket servers
  • Up to 160Gb/s bandwidth per blade this year with no chassis change
  • Doubling upstream Fibre Channel bandwidth 8Gb FC uplinks
  • 30% greater I/O performance with the Cisco VIC

With the latest generation of the UCS, we feel it is the logical choice for most if not all of you workloads, virtual or physical. To that end, we have over 15,000 applications certified via our certification and integration partners and we have developed and released Cisco Validated Designs for key applications such as Microsoft Exchange and SQL Server, Oracle RAC, and SAP.

Read More »

Intel’s Xeon 7500 Reinforces the Need for Balanced System Design

March 31, 2010 at 12:00 pm PST

 

So, I was lucky enough to go to the launch event for the new Intel Xeon processors yesterday.  There is plenty of more better more informed coverage out that there on the processor itself, so I am not going to try and re-create it here, but there are a couple of thoughts I did want to share.

The Xeon 7500 is certainly a significant accomplishment.  A couple of the soundbites that stuck with me was the 20:1 consolidation capability for existing Xeon servers with a predicted payback of 8 months including significantly reduced energy costs.  One of the interesting points Kirk Skaugen made was that, if you are so inclined, you can now deliver 20X more compute capability in the existing thermal/power envelope of your data center. Beyond the raw performance, there were some equally important enhancements around scalability, support for virtualization, and system reliability.  Intel’s point was that the Xeon has the wherewithal to be your primary processor for all your workloads--and I have to admit they make a pretty good case.

But, this is IT and there is no free lunch, so what is the impact of plopping these big honking processors down in the middle of your data center?  

 

Read More »

What is the Biggest Intangible Benefit of WAN optimization?

WAN optimization technologies have many benefits, some easily measured and others that are intangible. The latter might be more important to the organization. Many customers tell us that they realize both tangible and intangible benefits from deploying Cisco WAAS. Tangible benefits include reduced or avoided bandwidth costs, reductions in branch office servers and a reduced branch office equipment footprint. These cost savings are realized since Cisco WAAS eliminates duplicate data transmission, enables branch office server consolidation and integrates with the Cisco ISR router. These tangible benefits can be fairly easy to measure as we shall see. Intangible benefits can be more difficult to measure, but they can often be more compelling. Let’s look at an example of a customer who has experienced both types of benefits.

Recently a customer told us that they expect to save $400,000 per year by deploying Cisco WAAS. Brisbane Australia based mining and heavy equipment supplier Hastings Deering says they achieved a rapid ROI with their WAN optimization project that connects their data center and remote office locations.  The Hastings Deering Group sells and supports Caterpillar heavy equipment used in the mining and construction industries across Queensland, the Northern Territory and the South Pacific region, including Papua New Guinea. With a network of 65 nodes connecting to corporate applications in Brisbane, CIO John Birch says there was a constant battle to keep branch response times low for all its applications. “About 18 months ago we decided to take a look at network options other than just increasing bandwidth and we started exploring WAN optimization products”

Read More »

Riding the Innovation Wave…or Just Treading Water?

March 29, 2010 at 12:00 pm PST

I was getting caught up with my reading this weekend and was reminded of the John F Kennedy quote about a rising tide lifting all boats.  Intel has once again done their magic and released their Xeon 5600 CPU (aka Westmere) sporting a couple of more cores, a larger L3 cache and some other neat tidbits.  The newest Intel processor becomes a platform upon which we build some interesting things by layering on our own innovations.  However, as I worked my through another article, I began to wonder if we were the only ones thinking that way.  In this interesting InfoWorld article, Paul Venezia reviews three of the latest blade server offerings based on the Westmere processor (Cisco UCS was not one of the systems reviewed).  The interesting thing was the at the end of the day, Paul concluded “[t]here is no significant difference in blade performance in similarly equipped blades from any of these vendors.”  So, while it seems Intel has done their part, it also seems very little was added by the vendors in the test. 

 

Paul continues that meaningful differentiation came down to features such as options, management, etc. As I mentioned, our UCS was not part of this test, Paul recently completed a thorough evaluation of the system, where he concluded that the UCS was “a more manageable, more scalable, and essentially superior blade server system.”  So, all things being equal, I think UCS had a good chance at taking top honors in a direct comparison (the UCS out-scored the systems in the recent test, although I am not sure its appropriate to compare scores across articles). That being said..all things are not equal…we have some significant innovations to bring to the party beyond Intel’s efforts, including our extended memory technology and our FEX technology, which I think translate to meaningful and tangible benefits for our customers.  As examples, we just released results on our latest app testing including a new record on the VMware VMmark (with a 42% improvement over the previous 2-socket record), and Oracle just announced a new record on the SPECjAppServer2004 benchmark, which measures application server performance.

Read More »