alt text 

Stanford University Networking Seminar


Dave Taht ( Bufferbloat Project )
Inside Codel and Fq_codel and Derivatives in Delay Based active queue management

12:00pm, Thursday January 31, 2013
Gates 104

About the Talk

Kathleen Nichols and Van Jacobson spent 14 years developing a successor to RED, called “Codel”. Even though well described in journals such as ACM queue, and with commonly available source code, how the tightly intertwined drop strategy and RTT estimator actually work is not well understood. Furthermore the combination of various forms of Fair Queuing on top of any AQM is not well understood.

This talk goes into detail of the current ns2 and Linux based code, while discussing the design decisions and network traffic types we looked at while designing them, and their predecessor (SFQRED) as well as touring through a large selection of graphs and data from various real-world simulations. It will also look into the known flaws of both codel and fq_codel, and describe the ongoing research into improvements.

About the Speaker

Dave Täht is the co-founder of the bufferbloat project. He is also architect of the CeroWrt reference router project, which is exploring solutions to the bufferbloat and ipv6 deployment problems on consumer hardware. He is the original implementor of the codel algorithm in Linux, as well as maintainer of the ns2 and ns3 models of codel, and fq_codel. He has developed nfq_codel and has multiple upcoming enhancements and derivatives, under test. To enhance testing of bufferbloat related fixes, is also working on standardizing a “Realtime Response under Load” (RRUL) test suite.

Prior to tackling bufferbloat, he worked on wireless mesh networking, spacecraft, VOIP, and embedded Linux, most notably as “Member, Visionary staff” for MontaVista software. He has been working on Unix derived systems for 34 years.

He is the CTO of Teklibre, LLC, and associated with the LINCS lab in Paris, the Internet Systems Consortium (ISC), and his present work is sponsored through the Comcast Technology Research & Development Fund.