摘要: Data-intensive distributed applications can increase their performance by running on a cluster of hosts connected via high-bandwidth interconnections. However, there is no effective method to find such bandwidth-constrained in decentralized fashion. Our work inspired prior that treats Internet bandwidth as an approximate tree metric space. This paper presents decentralized, accurate, and efficient hosts, given the desired size minimum interconnection bandwidth. We describe centralized polynomial time algorithm for space, along with proof correctness. then provide version algorithm. Simulation experiments two real-world datasets confirm our clustering approach achieves high accuracy scalability. also discuss costs decentralization how treeness dataset affects accuracy.