Proportionally Fair approach for Tor's Circuits Scheduling

TL;DR

This paper introduces two scheduling methods for Tor's circuit resource allocation that improve fairness and throughput, with one optimizing for fairness and the other balancing fairness and latency.

Contribution

It proposes two novel scheduling approaches for Tor that ensure proportional fairness among circuits, enhancing performance and user experience.

Findings

Average-rate scheduler achieves optimal fairness and higher throughput.

Optimization-based scheduler balances fairness with reduced latency.

Both methods improve Tor network performance.

Abstract

The number of users adopting Tor to protect their online privacy is increasing rapidly. With a limited number of volunteered relays in the network, the number of clients' connections sharing the same relays is increasing to the extent that it is starting to affect the performance. Recently, Tor's resource allocation among circuits has been studied as one cause of poor Tor network performance. In this paper, we propose two scheduling approaches that guarantee proportional fairness between circuits that are sharing the same connection. In our evaluation, we show that the average-rate-base scheduler allocates Tor's resources in an optimal fair scheme, increasing the total throughput achieved by Tor's relays. However, our second proposed approach, an optimization-based scheduler, maintains acceptable fairness while reducing the latency experienced by Tor's clients.