PortLand: Scaling Data Center Networks to 100,000 Ports and Beyond

(November 18, 2009) Amin Vahdat, a professor of Computer Science and Engineering at the University of California-San Diego, discusses PortLand, a scalable, fault tolerant layer 2 routing and forwarding protocol for data centers, and places the work in the context of his larger efforts in data center networking.

Stanford University:
http://www.stanford.edu/

Stanford Engineering Everywhere:
http://see.stanford.edu/

Stanford Center for Professional Development:
http://scpd.stanford.edu/

Stanford University Channel on YouTube:
http://www.youtube.com/stanford/

Category:

Education

Tags:

• science
• technology
• electrical engineering
• computers
• data center
• network
• cloud computing
• routing
• port
• forwarding protocol
• design
• hosts
• scaling
• bandwidth
• database
• top of rack switch
• multi-rooted tree
• layer 2
• layer 3
• small

[grunder20]

Can you believe they statistically surveyed all of those boats?

Impressive to the bones.

[pzmtuthcvpvl]

remarkable - demo on 300 nodes scaling to 100,000 ? study of commercial data-centers in operation running across 100 million cores could reveal robust Map Reduction approaches over bandwith limited apps