Abstract | ||
---|---|---|
Because of small NIC on-chip memory, the massive connection states maintained on Remote Direct Memory Access (RDMA) NIC (RNIC) significantly limit its scalability. When the number of concurrent connections grows, RNICs have to frequently fetch connection states from host memory, leading to dramatic performance degradation. In this paper, we propose StaR, which fundamentally solves this scalability issue by making RNIC stateless. Leveraging the asymmetric communication pattern in data center applications, the StaR RNIC stores zero connection-related states by moving all the connection states to the other end. Through careful design, StaR RNICs can maintain unchanged RDMA semantics and avoid security issues even when processing traffic statelessly. Preliminary simulation results show that StaR can improve the aggregate throughput by more than 160x (stress test) and 4x (application) compared to original RNICs.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3343180.3343183 | Proceedings of the 3rd Asia-Pacific Workshop on Networking 2019 |
Keywords | DocType | ISSN |
Data Center Networks, RDMA, Scalability, Stateless RNIC | Conference | 978-1-4503-7635-8 |
ISBN | Citations | PageRank |
978-1-4503-7635-8 | 0 | 0.34 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pulin Pan | 1 | 0 | 0.34 |
Guo Chen | 2 | 11 | 3.96 |
Xizheng Wang | 3 | 0 | 0.68 |
Dai Huichen | 4 | 268 | 19.51 |
Bojie Li | 5 | 63 | 5.85 |
Binzhang Fu | 6 | 2 | 1.72 |
Kun Tan | 7 | 1350 | 98.64 |