Practical and Scalable RDMA Connection Sharing for HPC Workload
Yuejie Wang, Tuo Fang, Biyu Peng, Yang Cheng, Xin Sun, Chengchao Xu, Yuchen Tang, Yuxin Ren, Ning Jia, Xinwei Hu, Yunfei Du, Guyue (Grace) Liu
Abstract
RDMA is a fundamental communication infrastructure in high-performance computing (HPC). However, as the number of RDMA connections increases, system performance rapidly declines and memory consumption increases sharply. Previous research demonstrates that sharing RDMA connections among processes is necessary and effective to address the scalability problem. Unfortunately, previous work shares connections in software, thus incurring substantial overhead to each packet operation, and fails to comprehensively explore control policies to achieve superior sharing decisions.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get 3aa717d7-9d9b-4a0a-a4d8-6ab11ed2d190Related papers
- Birds of a Feather Flock Together: Scaling RDMA RPCs with FlockSumit Kumar Monga, Sanidhya Kashyap, Changwoo MinSOSP 2021 · 34 citations
- Scalable RDMA Transport with Efficient Connection SharingJian Tang, Xiaoliang Wang, Huichen DaiINFOCOM 2023 · 13 citations
- Maximizing the Benefit of RDMA at End HostsXiaoliang Wang, Hexiang Song, Cam-Tu Nguyen, Dongxu Cheng et al.INFOCOM 2021 · 8 citations
- Network Load Balancing with In-network Reordering Support for RDMACha Hwan Song, Xin Zhe Khooi, Raj Joshi, Inho Choi et al.SIGCOMM 2023 · 110 citations
- Scalable RDMA-accelerated Distributed Locks with Shared Stream AbstractionMiao Cai, Junru Shen, Xiaojian Liao, Rong Gu et al.EuroSys 2026
