Cisco Blogs


Cisco Blog > Data Center and Cloud

We Have a Winner

August 7, 2008 at 12:00 pm PST

So Brian Cantor won my little uptime contest. Brian dug up a C5K that has been up for over 3,450 days. Brian says

“I work for an insurance company and this particular switch serves as an access switch in one of our call centers. It has mostly end users but there are some printers and a couple of servers. As far as I can tell, this switch has been chugging away since before the new millennium.”

Congrats Brian--fleece en route.Omar

The Google Service Oriented Virtualized Cloud as a Service

This post is really a test of title/hype versus content. My personal bet is that because of this title coagulating every term that is riding the hype cycle at warp speed it will become my most clicked through post yet. Anyone taking that bet?As for some useful content- here are a few of our more commented posts or other things I liked that I saw recently…Virtualization 2.0 -- Data Center KnowledgeMy Thoughts on Where Cloud Computing May GoI also liked James and Sam’s discourse on What is a Cloud? Anyhow, I’ll post back up in a couple weeks and see if my guess is right….dg

More Like “The Color of Money”

In a recent post, Chris Mellor articulates what the impact of FCoE might be on the storage world. How storage switch manufacturers will have to retool their switches to support converged architectures and operating systems. How HBA vendors will have to now create a value proposition competing against entrenched Ethernet NIC vendors and especially how storage vendors will have to add native FCoE capability to their arrays and drives. And of course all this could have an impact to how iSCSI performs in the market as well.While I do agree with most of this assessment, I don’t agree with his conclusion. The fact is whenever there has been a battle between Ethernet and another network transport protocol, Ethernet has always won. Why should this time be any different? Fibre Channel is an excellent storage transport protocol but it is not ideal for a generalized transport of multiple data types. Ethernet has been doing this for some time and transporting storage will be the same as for any other upper layer application. Of course, Ethernet will have to evolve as it always has and Data Center Ethernet will offer the lossless and guaranteed delivery that Fibre Channel has today.Of course vendors like Cisco and QLogic are embracing FCoE as it delivers what customers have been asking for, a common transport for all of their of data. They realize that the data center is being virtualized and servers, storage, and networks have to work together to tackle the challenges that are in front of them.But these aren’t the only ones that see the opportunity of re-architecting the data center to support a virtualized infrastructure. Intel, Emulex, NetApp, and EMC are also supporting this effort as it allows them all to reach a much larger customer base than before.As our CEO likes to say, there’s an inflection point happening in the data center and those who are in front of it and ready to capitalize on it will definitely see “The Color of Money.”

Beijing Olympics 2008: Connecting the World

The Olympics gives the world two weeks to pause and marvel at athletes who shine brightly with their intense dedication to the pursuit of excellence, spurred by fierce competition. It’s worth taking a few minutes to note the results of equally intense dedication to televising the Games (also under intense and relentless market competition) with the most innovative technology, bringing the excitement, the drama, and the incredible achievement of the Olympics to as many people as possible. NBC Universal is making broadcasting history this week by presenting 3600 hours of coverage from Beijing, more than the combined hours of all previous summer Olympics Games. Viewers of the 2008 Olympic Games will be able to use their PCs and laptops to access 2,200 hours of video that they can play back on demand, as well as 3,000 hours of highlights, rewinds, and encores. People will also be able to watch video and view results on their smartphones.With all that video to transmit, NBC has selected Cisco to provide IP video network infrastructure and video encoding solutions to NBC during the network’s coverage of the 2008 Beijing Olympic Games, including one of Cisco’s Data Center technologies: Wide Area Application Services (WAAS). Rather than sending 400 video shot selectors and editors to Beijing, NBC will be using Cisco WAAS for WAN optimization and application acceleration between Beijing, New York and Los Angeles. By optimizing 35Mbps links into 140Mbps links, Cisco WAAS allows editors and shot selectors to access gigabyte-sized video files over the WAN with the same performance as if they were stored locally. This reduces operating costs of housing, air travel, transportation, and food. Avoiding 800 airplane trips also supports NBC’s green initiatives for the Olympic Games.To transmit video to its studios, NBC has deployed three 155Mbps OC-3 pipes between Beijing and New York. A Cisco 12004/4 Router collapses all three into one virtual pipe using equal cost load balancing. The types of traffic on the network range from video content and IP telephony to teleprompter content and event scoring. Cisco WAAS leverages rather than overwrites router QoS, giving NBC the confidence to dedicate 400Mbps to video, unlike tunnel-based architectures. So sit back, enjoy the Olympic Games this year wherever you happen to be at any given moment. Employers around the world are already anticipating lost productivity due to the video accessibility of the Games, and wondering how their internal networks are going to handle the increased load. I’ll be dutifully watching my favorite events, largely the track and field ones, while my friend Feng who wrote most/all of this posting goes for synchronized swimming and rhythmic gymnastics.

Slight Changes…

I wanted to append and slightly change my aforementioned theory on server disaggregation and network evolution. Previously it was basically something like this….”Whenever a network transport is faster than a server bus speed the peripheral connecting to that bus will go from a parallel connection to a serial one to a shared/packetized one.Printers, Hard Drives, CPU-CPU Interconnect, and potentially even memory will follow this theorem. Thus over time all of the elements necessary to process an IT workload will be not only interconnected by a common fabric, but more importantly connected with a layer of abstraction that will make any resource available to any workload at any time. “Now it still seems to be holding true (even 3-4 years after I made my first slide trying to explain this trend) but I realized in conversation with some sage reporters today that there is another axis to the graph. Network speed and capability increase. The faster and more capable the network the more disaggregated the server becomes. The faster and more capable a network is the more the network consolidates other network types. I need to sit down with a decent Cabernet and mull over if there is an end-state that is achieved. But if I had a data center that looked like a rack of CPU, a rack of memory, a rack of storage, a common network linking these physical assets and a network-enabled hypervisor running on top of this infrastructure providing a layer of abstraction between the physical elements and the operating system(s) this would be interesting. The faster I can reallocate resources against workload the less aggregate resources I need to support an increasingly sporadic workload profile. Also- couple with this witty comment #2 -- “The value of virtualization is compounded by the number of resources consolidated into the virtualized data center” and we have a scenario that drives branch consolidation, virtual desktop infrastructure, and other forms of resource consolidation into the data center.Now there are still some networking firms out there that are chasing a speeds/feeds game. Some that have not recognized the value of innovation. Some that still go for the largest routing table, CAM table, buffer pool, millions of packets per second measurement, or Gbps backplane speed comparison. Some hire third parties that were strong advocates of Gigabit Token Ring to champion their product marketing efforts and contrive tests to show how fast/great/cool/neat/geewhiz/wow/smart they are. Some wrap their products in a green flag and parade them through these ‘testing houses’ and declare victory. Some simply exist. Well my friends, the data center is a rapidly evolving part of the network. One that demands focus, innovation, and efficiency- not just existence. So to commemorate a great author who sadly passed away today-“Blow the dust off the clock. Your watches are behind the times. Throw open the heavy curtains which are so dear to you - you do not even suspect that the day has already dawned outside.”