Scaling Up Memory Disaggregated Applications with SMART
Feng Ren, Mingxing Zhang, Kang Chen, Huaxia Xia, Zuoning Chen, Yongwei Wu
Abstract
Recent developments in RDMA networks are leading to the trend of memory disaggregation. However, the performance of each compute node is still limited by the network, especially when it needs to perform a large number of concurrent fine-grained remote accesses. According to our evaluations, existing IOPS-bound disaggregated applications do not scale well beyond 32 cores, and therefore do not take full advantage of today's many-core machines.
Topics & Concepts
Remote direct memory accessComputer scienceNode (physics)ScalingDistributed computingSupercomputerParallel computingComputer architectureComputer networkEngineeringMathematicsGeometryStructural engineeringCloud Computing and Resource ManagementAdvanced Data Storage TechnologiesDistributed and Parallel Computing Systems