RDMAbox : Optimizing RDMA for Memory Intensive Workloads

Abstract

We present RDMAbox, a set of low level RDMA optimizations that provide better performance than previous approaches. The optimizations are packaged in easy-to-use kernel and userspace libraries and presented through simple node level abstractions. We demonstrate the flexibility and effectiveness of RDMAbox by implementing a kernel remote paging system and a userspace file system using RDMAbox. RDMAbox employs two optimization techniques. First, we suggest Load-aware Batching to further reduce the total number of I/O operations to the RDMA NIC beyond existing doorbell batching. The I/O merge queue at the same time functions as a traffic regulator to enforce admission control and avoid overloading the NIC. Second, we propose Adaptive Polling to achieve higher efficiency of polling Work Completion than existing busy polling while maintaining the low CPU overhead of event trigger. Our implementation of a remote paging system with RDMAbox outperforms existing representative solutions with up to 6.48× throughput improvement and up to 83% decrease in average tail latency in bigdata workloads, and up to 83% reduction in completion time in machine learning workloads. Our implementation of a userspace file system based on RDMAbox achieves up to 6× higher throughput over existing representative solutions.