CLEO: Machine learning for ECMP

Heesang Jin, Minkoo Kang, Gyeongsik Yang, Chuck Yoo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose CLEO, which is a machine learning approach to equal-cost multipath routing (ECMP) schemes to distribute and balance traffic. ECMP-based traffic load-balancing is widely practiced by datacenters, but hash collision resulting from skewed ECMP hashing makes it difficult to achieve the desired throughputs over paths. Various solutions have been proposed to overcome the performance degradation caused by hash collision, but most of these solutions require modifying packet headers or replacing switches. To solve this problem, CLEO builds a neural-network model that characterizes the ECMP scheme of a switch. The proof-of-concept evaluation shows that CLEO improves the root mean square error fourfold between the desired and real path throughputs.

Original languageEnglish
Title of host publicationCoNEXT 2019 Companion - Proceedings of the 15th International Conference on Emerging Networking EXperiments and Technologies, Part of CoNEXT 2019
PublisherAssociation for Computing Machinery, Inc
Pages1-3
Number of pages3
ISBN (Electronic)9781450370066
DOIs
Publication statusPublished - 2019 Dec 9
Event15th International Conference on Emerging Networking EXperiments and Technologies, CoNEXT 2019 - Part of CoNEXT 2019 - Orlando, United States
Duration: 2019 Dec 92019 Dec 12

Publication series

NameCoNEXT 2019 Companion - Proceedings of the 15th International Conference on Emerging Networking EXperiments and Technologies, Part of CoNEXT 2019

Conference

Conference15th International Conference on Emerging Networking EXperiments and Technologies, CoNEXT 2019 - Part of CoNEXT 2019
CountryUnited States
CityOrlando
Period19/12/919/12/12

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'CLEO: Machine learning for ECMP'. Together they form a unique fingerprint.

  • Cite this

    Jin, H., Kang, M., Yang, G., & Yoo, C. (2019). CLEO: Machine learning for ECMP. In CoNEXT 2019 Companion - Proceedings of the 15th International Conference on Emerging Networking EXperiments and Technologies, Part of CoNEXT 2019 (pp. 1-3). (CoNEXT 2019 Companion - Proceedings of the 15th International Conference on Emerging Networking EXperiments and Technologies, Part of CoNEXT 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3360468.3366768