The CoCo-Beholder: Enabling Comprehensive Evaluation of Congestion Control Algorithms

12/22/2019
by   Evgeniya Khasina, et al.
0

The recent endeavors of the research community to unite efforts on the design and evaluation of congestion control algorithms have created a growing collection of congestion control schemes called Pantheon. However, the virtual network emulator that comes with the collection has very limited capabilities: it can run flows of only one scheme at once, and the flows cannot have individual network settings, as the topology is point-to-point. This thesis addresses those limitations and presents CoCo-Beholder, a human-friendly emulator providing the popular dumbbell topology of any size, each link of which may have individual rate, delay, and queue size. The central link of the topology may also have a variable delay with optional jitter. Flows of different schemes may run between the halves of the topology at once, and for each flow, the direction and starting time can be chosen. CoCo-Beholder's reliability is ensured by testing schemes in the dumbbell topology of size one and comparing the results against those of Pantheon emulator. With CoCo-Beholder, the thesis successfully reproduces experiments from a recent paper that evaluated the fairness and RTT-fairness of schemes using a real hardware dumbbell testbed. Finally, the thesis explores the behavior of schemes under the square-wave delay using CoCo-Beholder's variable delay feature.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset

Sign in with Google

×

Use your Google Account to sign in to DeepAI

×

Consider DeepAI Pro