Accelerating Packet Processing in Container Overlay Networks via Packet-level Parallelism

Jiaxin Lei, Manish Munikar, Hui Lu, Rao Jia

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Overlay networks serve as the de facto network virtualization technique for providing connectivity among distributed containers. Despite the flexibility in building customized private container networks, overlay networks incur significant performance loss compared to physical networks (i.e., the native). The culprit lies in the inclusion of multiple network processing stages in overlay networks, which prolongs the network processing path and overloads CPU cores. In this paper, we propose mFlow, a novel packet steering approach to parallelize the in-kernel data path of network flows. mFlow exploits packet-level parallelism in the kernel network stack by splitting the packets of the same flow into multiple micro-flows, which can be processed in parallel on multiple cores. mFlow devises new, generic mechanisms for flow splitting while preserving in-order packet delivery with little overhead. Our evaluation with both micro-benchmarks and real-world applications demonstrates the effectiveness of mFlow, with significantly improved performance - e.g., by 81% in TCP throughput and 139% in UDP compared to vanilla overlay networks. mFlow even achieved higher TCP throughput than the native (e.g., 29.8 vs. 26.6 Gbps).

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages79-89
Number of pages11
ISBN (Electronic)9798350337662
DOIs
StatePublished - 2023
Event37th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023 - St. Petersburg, United States
Duration: 15 May 202319 May 2023

Publication series

NameProceedings - 2023 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023

Conference

Conference37th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2023
Country/TerritoryUnited States
CitySt. Petersburg
Period15/05/2319/05/23

Keywords

  • Container Overlay Networks
  • Kernel Network Stack
  • Packet Processing

Fingerprint

Dive into the research topics of 'Accelerating Packet Processing in Container Overlay Networks via Packet-level Parallelism'. Together they form a unique fingerprint.

Cite this