RDMA Communciation Patterns

Author:

Ziegler TobiasORCID,Leis Viktor,Binnig Carsten

Abstract

AbstractRemote Direct Memory Access (RDMA) is a networking protocol that provides high bandwidth and low latency accesses to a remote node’s main memory. Although there has been much work around RDMA, such as building libraries on top of RDMA or even applications leveraging RDMA, it remains a hard problem to identify the most suitable RDMA primitives and their combination for a given problem. While there have been some initial studies included in papers that aim to investigate selected performance characteristics of particular design choices, there has not been a systematic study to evaluate the communication patterns of scale-out systems. In this paper, we address this issue by systematically investigating how to efficiently use RDMA for building scale-out systems.

Funder

Technische Universität Darmstadt

Publisher

Springer Science and Business Media LLC

Subject

General Earth and Planetary Sciences,General Environmental Science

Reference26 articles.

1. Alonso G, Binnig C, Pandis I, Salem K, Skrzypczak J, Stutsman R, Thostrup L, Wang T, Wang Z, Ziegler T (2019) DPI: the data processing interface for modern networks. In: CIDR 2019, 9th Biennial Conference on Innovative Data Systems Research Asilomar, 13.01.–16.01. (Online Proceedings. www.cidrdb.org (2019). http://cidrdb.org/cidr2019/papers/p11-alonso-cidr19.pdf)

2. Barthels C, Alonso G, Hoefler T (2017) Designing databases for future high-performance networks. IEEE Data Eng Bull 40(1):15–26 (http://sites.computer.org/debull/A17mar/p15.pdf)

3. Barthels C, Alonso G, Hoefler T, Schneider T, Müller I (2017) Distributed join algorithms on thousands of cores. Proc VLDB Endow 10(5):517–528. https://doi.org/10.14778/3055540.3055545 (http://www.vldb.org/pvldb/vol10/p517-barthels.pdf)

4. Barthels C, Loesing S, Alonso G, Kossmann D (2015) Rack-scale in-memory join processing using RDMA. In: Sellis TK, Davidson SB, Ives ZG (eds) Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data Melbourne, 31.05.–4.06. Association for Computing Machinery, New York, pp 1463–1475 https://doi.org/10.1145/2723372.2750547

5. Binnig C, Crotty A, Galakatos A, Kraska T, Zamanian E (2016) The end of slow networks: It’s time for a redesign. Proc VLDB Endow 9(7):528–539. https://doi.org/10.14778/2904483.2904485

Cited by 10 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Virtual Try-On Application leveraging RoCE in Low-latency Edge Computing Networks;2024 24th International Conference on Transparent Optical Networks (ICTON);2024-07-14

2. Seamless: Transparent Storage Access Through Smart Switches;Proceedings of the 20th International Workshop on Data Management on New Hardware;2024-06-09

3. Why Files If You Have a DBMS?;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13

4. RDMA-Based Deterministic Communication Architecture for Autonomous Driving;2023 IEEE 29th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA);2023-08-30

5. Zero-sided RDMA: Network-driven Data Shuffling;Proceedings of the 19th International Workshop on Data Management on New Hardware;2023-06-18

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3