Distributed and Optimal RDMA Resource Scheduling in Shared Data Center Networks

Shen, Dian; Luo, Junzhou; Dong, Fang; Guo, Xiaolin; Wang, Kai; Lui, John C. S.

doi:10.1109/infocom41043.2020.9155533

Cited by 6 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RDMA Optimizations. As RDMA gains popularity, there is a body of recent work on RDMA scheduling [84,88] and scalability improvement [95,22,53,52]. Existing techniques focus on solving scalability problems when RDMA NICs are shared among multiple clients.…”

Section: Related Workmentioning

confidence: 99%

Canvas: Isolated and Adaptive Swapping for Multi-Applications on Remote Memory

Wang¹,

Qiao²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

Remote memory techniques for datacenter applications have recently gained a great deal of popularity. Existing remote memory techniques focus on the efficiency of a single application setting only. However, when multiple applications co-run on a remote-memory system, significant interference could occur, resulting in unexpected slowdowns even if the same amounts of physical resources are granted to each application. This slowdown stems from massive sharing in applications' swap data paths. Canvas is a redesigned swap system that fully isolates swap paths for remote-memory applications. Canvas allows each application to possess its dedicated swap partition, swap cache, prefetcher, and RDMA bandwidth. Swap isolation lays a foundation for adaptive optimization techniques based on each application's own access patterns and needs. We develop three such techniques: (1) adaptive swap entry allocation, (2) semanticsaware prefetching, and (3) two-dimensional RDMA scheduling. A thorough evaluation with a set of widely-deployed applications demonstrates that Canvas minimizes performance variation and dramatically reduces performance degradation.

show abstract

Section: Related Workmentioning

confidence: 99%

Canvas: Isolated and Adaptive Swapping for Multi-Applications on Remote Memory

Wang¹,

Qiao²,

Ma³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…When the network cluster is relatively small, RC-type communication mechanisms can meet the specific characteristics of network traffic in AI infrastructure [13]. However, as the scale of AI infrastructure grows, RDMA QP communication based on RC inevitably exhibits performance deficiencies [1,19]. Firstly, the number of QPs established by RC will increase rapidly as the scale expands, which will lead to a decrease in the performance of the network interface card (NIC).…”

Section: Introductionmentioning

confidence: 99%

An Optimized RDMA QP Communication Mechanism for Hyperscale AI Infrastructure

Wang,

Lin,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

The current artificial intelligence (AI) infrastructure widely employs remote direct memory access (RDMA) protocol for high-performance communication in networks, utilizing Reliable Connection (RC)-based Queue Pairs (QP) to ensure end-to-end correct and ordered data transmission. However, as the scale of AI infrastructure continues to expand, this RC-based QP communication mechanism faces deficiencies in scalability and is prone to congestion, resulting in degraded network transfer performance. In this paper, we propose an optimized RDMA QP communication mechanism to address scalability and congestion issues in hyper-scale AI infrastructure networks. Firstly, we replace RC-based QPs with Reliable Datagram (RD)-based QPs and propose a new reliable mechanism to address scalability problems, eliminating the need for repetitive QP establishment by AI processes during external communication. Additionally, to mitigate congestion caused by a single path, we implement multipath data transmission by introducing a new unordered reception method in the network software stack. Through experiments and simulation tests, the optimized RDMA QP communication in large-scale AI infrastructure exhibits exceptional scalability and significantly reduces the occurrence of congestion, resulting in an overall network performance improvement of over 15%.

show abstract