Why did dinosaurs become extinct? I'm no paleontologist but allow me to provide an over-simplified explanation: When the environment went through radical alterations, dinosaurs couldn't adequately adapt to these changes. In a binary, "adapt or die" world, the dinosaurs died.
A similar binary situation is developing with data center networks. On the one hand, the environment is going through some radical changes. According to ESG Research:
- 63% of enterprise organizations are consolidating or have already consolidated data centers. On average, these firms will eliminate 25% to 50% of their data centers. Nearly half of organizations will consolidate data centers belonging to independent business units into multi-tenant facilities.
- About 40% of organizations are extending applications or moving virtual servers across geographically dispersed data centers. In other words, web applications and server virtualization are creating a virtual data center platform across multiple physical facilities.
- Almost all enterprises are using server virtualization today with aggressive future plans for more VM workloads, more VMs per physical server, etc.
- Large organizations anticipate steady growth in the number of physical/virtual devices per data center, the number of VLANs per data center, and the number of IP subnets per data center.
Clearly the data center environment is changing, which begs the question: Are data center networks adapting? Yes, but the ESG data indicates that the slow pace of change is causing some major problems. When asked to identify network operations challenges, large organizations pointed to things like too many manual processes, time consuming network provisioning and configuration, and organizational problems between the networking team and other functional IT groups. Network security is a mess and network performance is a constantly moving target. Yikes!
The data center networking dinosaur is adapting but we are rapidly approaching a breaking point. Yes, the networking industry is working diligently to bridge this gap, the ESG data points to an inevitable inflection point coming sooner than you think.
I will continue to blog about the ESG data center networking research as the report will be published quite soon. A few parting thoughts here:
- Expect changes in every aspect of data center network: NIC cards, cabling, virtual switches, data center fabrics, etc. Networking vendors must realize that these are a lot of simultaneous change that even the most sophisticated IT shops will have difficulty understanding.
- If anyone was still unclear about why Cisco went into the server business, my first point should solve this riddle. The ESG data also indicates that Cisco is succeeding but more on this later.
- While the jury is still out on OpenFlow, there is no question that the future of provisioning, management, and control planes will be software-based. The network must become a virtual platform a la VMware, Xen, KVM, etc. It is likely that SDN, OpenFlow, and vendor support from companies like BigSwitch, Brocade, HP, IBM, Juniper, and NEC will get a lot of attention in 2012.
- If you believe #3, Arista's strategy looks increasingly intelligent.
- While pure-play cloud computing initiatives are still rare, many enterprise organizations are extending applications, moving workloads, and using global load balancing across multiple data centers. Seems like the on-ramp to cloud computing to me. Once again, the network must adapt to location-independence - or die.
You can read Jon's other blog entries at Insecure About Security.