Boosting scalable data analytics with modern programmable networks
Marcel Blöcher, Tobias Ziegler, Carsten Binnig, Patrick Th. Eugster · 2018
Data center networks lie at the core of distributed data analytics frameworks running in large scale environments. Recent research seek to improve the system performance by optimizing the end-host network usage, e.g., optimally use RDMA [2] or zero copy I/O frameworks [5] for distributed data analytics frameworks. Such approaches allow these systems to leverage the high network-bandwidth at end-hosts, however, keep the network itself untouched which does not solve contention and scalability issues.