Reviewer: Ben Wun
Date: 9-29-2005
What is the consensus rating for this paper? bottom 50%
How confident are you that the consensus judgement treats the paper fairly? reasonably confident
How would you rate the overall review process for this paper? thorough
How did the disagreements among the reviewers get resolved? Or if you were unable to reach consensus, what were the main sticking points?
While most reviewers originally put the paper somewhere in the top 50%, most seemed to change their mind after the discussion. There were several concerns discussed which the authors of the paper did not address effectively, or at all.
The authors claim that VCP's slowness to converge to a fair distribution of bandwidth is not a problem because TCP also performs poorly in this area, but they do not do a direct comparision, and failed to convince us that VCP is no worse than TCP in this respect.
Another point not addressed in the paper is how VCP would interact with other types of protocols, or what would happen if a misbehaving connection were to interfere. All their experiments were performed under the ideal and unlikely scenario of a network containing only well behaved VCP flows.
It was pointed out that the authors may have been too aggressive in their target network utilization. A tradeoff for better fairness while maintaining a lower, but still good, link utilization may be better. While VCP can probably be tuned for this, the authors did not look into it at all.
The consensus seems to be that the paper does not make a strong enough case that VCP is indeed an acceptable solution for fair and efficient allocation of bandwidth on high BDP networks. The authors did not give enough support for all of their assertions, and did not examine behavior of their protocol in a realistic enviroment.