Efficient Memory Disaggregation with INFINISWAP

Abstract

Memory-intensive applications suffer large performance loss when their working sets do not fully fit in memory. Yet, they cannot leverage otherwise unused remote memory when paging out to disks even in the presence of large imbalance in memory utilizations across a cluster. Existing proposals for memory disaggregation call for new architectures, new hardware designs, and/or new programming models, making them infeasible. This paper describes the design and implementation of INFINISWAP, a remote memory paging system designed specifically for an RDMA network. INFINISWAP opportunistically harvests and transparently exposes unused memory to unmodified applications by dividing the swap space of each machine into many slabs and distributing them across many machines' remote memory. Because one-sided RDMA operations bypass remote CPUs, INFINISWAP leverages the power of many choices to perform decentralized slab placements and evictions. We have implemented and deployed INFINISWAP on an RDMA cluster without any modifications to user applications or the OS and evaluated its effectiveness using multiple workloads running on unmodified VoltDB, Memcached, PowerGraph, GraphX, and Apache Spark. Using INFINISWAP, throughputs of these applications improve between 4 x (0.9 4 x) to 1 5.4 x (7.8 x) over disk (Mellanox nbdX), and median and tail latencies between 5.4 x (2 x) and 6 1 x (2.3 x). INFINISWAP achieves these with negligible remote CPU usage, whereas nbdX becomes CPU-bound. INFINISWAP increases the overall memory utilization of a cluster and works well at scale.