Swing: Providing Long-Range Lossless RDMA via PFC-Relay
Swing: Providing Long-Range Lossless RDMA via PFC-Relay
复制标题
DOI：
10.1109/tpds.2022.3215517
复制
发表时间：
2023-01
影响因子：
5.3
通讯作者：
Yanqing Chen;Chen Tian;Jiaqing Dong;Song Feng;Xu Zhang;Chang-Long Liu;Peiwen Yu;Nai Xia;Wanchun Dou;Guihai Chen
中科院分区：
文献类型：
--
作者：
Yanqing Chen;Chen Tian;Jiaqing Dong;Song Feng;Xu Zhang;Chang-Long Liu;Peiwen Yu;Nai Xia;Wanchun Dou;Guihai Chen
远程直接内存访问（RDMA）因其高性能而被广泛部署在数据中心中。构建在地理分布的数据中心上的大规模高性能云服务需要远程 RDMA 来满足性能要求。然而，现有的RDMA解决方案很难满足新兴的基于地理分布式数据中心的大规模高性能云服务在吞吐量和延迟方面的严格要求。一方面，无损 RDMA 由于对优先流控制 (PFC) 消息的延迟响应而受到深度缓冲区和数据中心间流量潜在的次优吞吐量的影响。另一方面，当具有不同往返时间 (RTT) 的多个流在跨数据中心场景中共存时，具有选择性重传的有损 RDMA 性能较差。本文提出Swing，通过PFC-Relay将高性能无损RDMA扩展到长距离链路。 Swing 确保长距离链路的吞吐量，同时最大限度地减少长距离 RDMA 的缓冲区要求。它支持远程 RDMA，无需对现有数据中心网络进行任何修改。评估表明，Swing在多种流量场景下可以将平均流量完成时间（FCT）降低14%-66%。
Remote Direct Memory Access (RDMA) has been widely deployed in datacenters for its high performance. Large-scale high performance cloud services built on geographically distributed datacenters require long-range RDMA for performance requirements. However, existing RDMA solutions can hardly satisfy the stringent requirements of the emerging large-scale high-performance cloud services built on geo-distributed datacenters in terms of throughput and delay. On the one hand, lossless RDMA suffers from a deep buffer and potential suboptimal throughput for inter-datacenter traffic due to delayed response to Priority Flow Control (PFC) messages. On the other hand, lossy RDMA with selective retransmissions suffers from poor performance when multiple flows with different round-trip times (RTTs) coexist in cross-datacenter scenarios. This article proposes Swing, which expands the high-performance lossless RDMA to long-distance links through PFC-Relay. Swing ensures the throughput of long-distance links while minimizing the buffer requirement for long-range RDMA. It enables long-range RDMA without making any modifications to existing in-datacenter networks. The evaluation shows that Swing can reduce the average flow completion time (FCT) by 14%-66% in a variety of traffic scenarios.