Re-Thinking System Availability in the World of Virtualization

September 10, 2008 - 0 Comments

So I have been a auto enthusiast for forever. For much of that time, I have been an adherent to the mantra”there is no replacement for displacement” (sorry Rob). What has changed over the years, however, is that car buying has evolved beyond looking for the biggest engine and lowest 0-60 times I could afford. Don’t get me wrong, I still optioned the larger engine in my last two rides (sorry again, Rob), but I finally figured out other things are as, if not more important. Opportunities to open the throttle up all the way are thrilling, but limited, and these days I actually have more fun hunting for tasty switchbacks on the backroads between my home and San Jose. Simply, the daily aspects of my current ride have define my overall on my experience with it.Back in February, I talked a bit about what makes the Nexus 7000 better than anything else on the market: the value of the switch does not hinge on how fast it goes, but on things that really matter to folks who have to live with these switches on a daily basis. One of these areas is the growing intolerance for system downtime. The current trends around consolidation and virtualization demand a different mindset and different expectations of infrastructure. While there are indisputable benefits to consolidation and virtualization, the flip side of this is that the size of a failure domain grows proportionally to the level of consolidation and virtualization. Every part of the data center needs to meet this higher bar. For example, VMware has its HA and DRS solutions. On the network side, one of the things we offer is a Zero Service Loss architecture on the Nexus 7000. Network World just took the Nexus 7000 though its paces and scored it 5/5 for availability. With all 256 10GbE ports forwarding traffic, the testers killed the OSPF process, upgraded and downgraded the software, and finally pulled 4 of the 5 the fabric modules from the switch. In all cases, the switch did not drop a packet.In fact, in a similar example, you can see how NX-OS and the Nexus 7000 handle things when you kill spanning tree while the switch is serving as the root bridge.I will have some other cool stuff to talk about next in the next couple of weeks, but in the interim, we have an At-A-Glance and whitepaper that dig into this a little further.

In an effort to keep conversations fresh, Cisco Blogs closes comments after 60 days. Please visit the Cisco Blogs hub page for the latest content.