Understanding TCP Incast and Its Implications for Big Data Workloads

TCP incast is a recently identified network transport pathology that affects many-to-one communication patterns in datacenters. It is caused by a complex interplay between datacenter applications, the underlying switches, network topology, and TCP, which was originally designed for wide area networks. We seek to understand how incast impacts the emerging class of big data workloads. We develop and validate a quantitative model that accurately predicts the onset of incast and TCP behavior both before and after. We also investigate how incast affects the Apache Hadoop implementation of MapReduce, an important example of a big data application. We further reflect on some technology and data analysis trends surrounding big data, speculate on how these trends interact with incast, and make recommendations for datacenter operators.