130 likes | 140 Views
Learn about BubbleStorm, a practical solution for calculating the sum in peer-to-peer networks, and its improvements in terms of round switching, message loss compensation, and bandwidth saving. Discover the challenges and open problems related to the Push-Sum algorithm, including vulnerability to attacks.
E N D
Brief Announcement:Practical Summation via Gossip Wesley W. Terpstra, Christof Leng, Alejandro P. Buchmann Databases and Distributed Systems Group Technische Universität Darmstadt Germany
Sum calculation in peer-to-peer • Input: every peer has a value • Output: (at least) one peer knows • Useful in computing many global statistics: • Network size • Average utilization • Load balance (standard deviation) • Churn (rate of peer replacement) • Size of stored data For our system, BubbleStorm, we compute degi(p)
Build on an existing solution • Approaches can be compared by • Message rounds (latency) • Total messages (bandwidth) • Parameters: system size (n), accuracy () • We improve the Push-Sum algorithm for practical use
Stationary Distribution (Steady State) Equilibrium: edges carry the same water and fish in both directions peers have water and fish proportional to degree and clock Perturbations of equilibrium do not affect water/fish ratio
Other improvements • Round switching • Once the result is accurate “enough”, restart • Provides a running estimate on network statistics • Compensate for message loss • Prevent adding two of the most aggressive fish • Save bandwidth for multiple measurements
Synchrony • Kempe et al. prove correctness with synchronous model, but conjecture that it works asynchronously • We validate this claim by simulation • 1 million peers, 5s gossip interval, find network size:
Open Problem • Push-Sum is very vulnerable to attack • Any peer can completely change the result • This is largely due to the problem statement (sum!) • Simplistic prevention (bounds) easily defeated • Introduce too few of the largest fish type too large • Switch rounds prematurely too small & unstable • What is a useful adversary model for summation?