Distributed and Optimal RDMA Resource Scheduling in Shared Data Center Networks

Remote Direct Memory Access (RDMA) suffers from unfairness issues and performance degradation when multiple applications share RDMA network resources. Hence, an efficient resource scheduling mechanism is urged to optimally allocates RDMA resources among applications. However, traditional Network Utility Maximization (NUM) based solutions are inadequate for RDMA due to three challenges: 1) The standard NUM-oriented algorithm cannot deal with coupling variables introduced by multiple dependent RDMA operations; 2) The stringent constraint of RDMA on-board resources complicates the standard NUM by bringing extra optimization dimensions; 3) Naively applying traditional algorithms for NUM suffers from scalability and convergence issues in solving a large-scale RDMA resource scheduling problem.

In this paper, we present distributed and optimal resource scheduling for RDMA networks to tackle the aforementioned challenges. First, we propose Distributed RDMA NUM (DRUM) to model the RDMA resource scheduling problem as a new variation of the NUM problem. Second, we present a distributed algorithm based on the alternating directional method of multipliers (ADMM), which has the property of convergence guarantee. Third, we implement our proposed algorithm in the real-world RDMA environment, and extensively evaluate it through large scale simulations and testbed experiments. Experimental results show that our method significantly improves applications' performance under resource contention, achieving 1.4 1.7⇥ higher throughput even under heavy background traffic, and 69.3% improvement in terms of network utility.