作者: T.J. Hacker , B.D. Athey , B. Noble
DOI: 10.1109/IPDPS.2002.1015527
关键词:
摘要: This paper examines the effects of using parallel TCP flows to improve end-to-end network performance for distributed data intensive applications. A series transmission experiments were conducted over a wide-area assess how throughput, and understand number necessary throughput while avoiding congestion. An empirical expression based on experimental is presented, guidelines use are discussed.