Tuesday, July 24, 2012

Why Network Latency Matters for Virtualized Applications

My colleague Russell Skingsley has an interesting take on the effects of latency on virtualized application performance. The purpose of virtualization is to optimize resource utilization. As Russell pointed out it isn’t just an academic conversation. For the cloud hosting provider it’s about revenue maximization. Network latency has a direct impact on virtualized application performance and therefore revenue for the service provider. Your choice of network infrastructure will impact your business, but it can be difficult to see how investing in high performance networking solutions will improve your business. I will try to connect the dots.

Don't Sell it Just Once
It’s a service provider axiom that you don’t want to waste your valuable assets by selling them to a single customer, even at a premium. Take dark fiber for instance, every SP has come to learn that selling a fiber to a single customer will never bring scalable revenues. Making the move to adding DWDM to the service mix allows you to scale up the number of customers and is an improvement over selling dark fiber, but is limited by the number of lamdas that can fit in the spectrum on a single fiber. The scaling is linear. A similar situation exists for shared cloud computing resources.

Sunday, July 22, 2012

Is There a Real Use Case for LISP, The Locator/ID Separation Protocol?

LISP is a protocol that pops back in the news just when you might have forgot that it existed. It happened again in June when Cisco re-launched LISP for fast mobility at their annual user conference, complete with an on stage demo and much fanfare. While the demo’s are impressive, the history of LISP makes me wonder what is going on behind the curtain. This isn’t the first time that Cisco has proposed LISP for a new use case. In 2011, Cisco positioned LISP as a solution for IPv6 transition and virtual machine mobility, along with VXLAN and OTV, creating a triumvirate of proprietary protocols to further pioneering use cases. But is there real value in LISP?

What is LISP? 
LISP is a protocol and an addressing architecture originally discussed at the IETF in 2006 to help contain the growth of the route tables in core routers. The LISP proposal which was submitted in 2010 is still under development as an experimental draft in the IETF, see link.  As far as I have see there is not much consensus regarding the usefulness of LISP, and it has several open issues in the areas of security, service migration and deployability. Because the cost and risk associated with LISP are significant, network operators have scaled their routing systems using other techniques such as by deploying routers with sufficient FIB capacity, and by deploying NAT.