Farouk Salem
Lecturer Assistant, Computer Science Department, Faculty of Computers and Artificial Intelligence
5 Dr. Ahmed Zewail Street, Faculty of Computers and Information, Postal Code: 12613, Orman, Giza, Egypt (email)
Improving the throughput of a scalable FLESnet using the Data-Flow Scheduler
- Citation:
- Salem, F., F. Schintke, T. Schütt, and A. Reinefeld, "Improving the throughput of a scalable FLESnet using the Data-Flow Scheduler", CBM Progress Report 2018, pp. 149 – 150, 2019.
Abstract:
Minimizing the latency is essential for FLESnet to achieve good aggregated bandwidth and we already improved the throughput and lowered the latency with our Data-Flow Scheduler. However, there is still a gap between the achieved and the maximally achievable bandwidth. For timeslice building, we found that FLESnet performs two RDMA writes for each contribution. This congests the network unnecessarily and increases the latency, especially in large deployments. We, therefore, optimized FLESnet to need only one RDMA request per contribution. We show how the aggregated bandwidth is increased when the scheduler is used. We also discuss the performance of the scheduler on an Infiniband cluster.
Notes:
n/a