More Web Proxy on the site http://driver.im/

research-article

Free access

FEC Killed The Cut-Through Switch

Authors:

Andrew W. Moore,

Noa ZilbermanAuthors Info & Claims

NEAT '18: Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies

Pages 15 - 20

https://doi.org/10.1145/3229574.3229577

Published: 07 August 2018 Publication History

Abstract

Latency penalty in Ethernet links beyond 10Gb/s is due to forward error correction (FEC) blocks. In the worst case a single-hop penalty approaches the latency of an entire cut-through switch. Latency jitter is also introduced, making latency prediction harder, with large peak to peak variance. These factors stretch the tail of latency distribution in Rack-scale systems and Data Centers, which in turn degrades performance of distributed applications. We analyse the underlying mechanisms, calculate lower bounds and propose a different approach that would reduce the penalty, allow control over latency and feedback for application level optimisation.

Supplementary Material

Original paper (p15-sella_v1.pdf)

Published on August 20, 2018 in the ACM Digital Library. Replaced on August 23, with approval of the program chairs. A figure was omitted in error.

Download
11.38 MB

References

[1]

Mohammad Al-Fares, Alexander Loukissas, and Amin Vahdat. 2008. A scalable, commodity data center network architecture. In ACM SIGCOMM Computer Communication Review, Vol. 38. ACM, 63--74.

Digital Library

[2]

Mohammad Alizadeh, Abdul Kabbani, Tom Edsall, Balaji Prabhakar, Amin Vahdat, and Masato Yasuda. 2012. Less is more: trading a little bandwidth for ultra-low latency in the data center. In Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation. USENIX Association, 19--19.

Digital Library

[3]

Luiz Barroso, Mike Marty, David Patterson, and Parthasarathy Ranganathan. 2017. Attack of the killer microseconds. Commun. ACM 60, 4 (2017), 48--54.

Digital Library

[4]

Richard E Blahut. 2003. Algebraic codes for data transmission. Cambridge university press.

[5]

Broadcom. 2017. Broadcom Tomahawk 3. (2017). https://www.broadcom.com/blog/broadcom-s-tomahawk-3-ethernet\-switch-chip-delivers-12--8-tbps-of-speed-in-a-single-16-nm-device

[6]

Stuart Cheshire. 1996. It's the Latency, Stupid. (1996). http://www.stuartcheshire.org/rants/latency.html

[7]

Roy Cideciyan and John Ewen. 2011. Transcoding/FEC Options and Trade-offs for 100 Gb/s Backplane and Copper Cable. (2011). http://www.ieee802.org/3/bj/public/nov11/cideciyan_01a_1111.pdf

[8]

Paul T Congdon, Prasant Mohapatra, Matthew Farrens, and Venkatesh Akella. 2014. Simultaneously reducing latency and power consumption in openflow switches. IEEE/ACM Transactions on Networking (TON) 22, 3 (2014), 1007--1020.

Digital Library

[9]

Exablaze. 2017. Exalink Fusion. https://exablaze.com/downloads/pdf/ExaLINK_Fusion_Brochure.pdf.

[10]

G David Forney. 1973. The viterbi algorithm. Proc. IEEE 61, 3 (1973), 268--278.

[11]

Mark Handley, Costin Raiciu, Alexandru Agache, Andrei Voinescu, Andrew W Moore, Gianni Antichi, and Marcin Wójcik. 2017. Re-architecting datacenter networks and stacks for low latency and high performance. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication. ACM, 29--42.

Digital Library

[12]

IEEE. 2014. IEEE Standard for Ethernet Amendment 2: Physical Layer Specifications and Management Parameters for 100 Gb/s Operation Over Backplanes and Copper Cables. (2014).

[13]

IEEE. 2016. 802.3by-2016 - IEEE Standard for Ethernet - Amendment 2: Media Access Control Parameters, Physical Layers, and Management Parameters for 25 Gb/s Operation. (2016). http://ieeexplore.ieee.org/servlet/opac?punumber=7526269

[14]

IEEE. 2018. P802.3cd/D3.1, Feb 2018 - IEEE Draft Standard for Ethernet Amendment: Media Access Control Parameters for 50 Gb/s and Physical Layers and Management Parameters for 50 Gb/s, 100 Gb/s, and 200 Gb/s Operation. (2018). http://ieeexplore.ieee.org/servlet/opac?punumber=8288802

[15]

Ryan J Marcotte and Edwin Olson. 2016. Adaptive forward error correction with adjustable-latency QoS for robotic networks. In Robotics and Automation (ICRA), 2016 IEEE International Conference on. IEEE, 5283--5288.

[16]

Mellanox. 2017. Spectrum2. (2017). http://www.mellanox.com/page/products_dyn?product_family=277&mtag=spectrum2_ic

[17]

Micron. 2017. Why CAS latency isn't an accurate measure of memory performance. (2017). http://uk.crucial.com/gbr/en/memory-performance-speed-latency

[18]

Daniel Molka, Daniel Hackenberg, and Robert Schöne. 2014. Main memory and cache performance of Intel Sandy Bridge and AMD Bulldozer. In Proceedings of the workshop on Memory Systems Performance and Correctness. ACM, 4.

Digital Library

[19]

Todd K Moon. 2005. Error correction coding. Mathematical Methods and Algorithms. Jhon Wiley and Son (2005).

Digital Library

[20]

David A Patterson. 2005. Latency Lags Bandwidth. In ICCD. 3--6.

Digital Library

[21]

Jonathan Perry, Amy Ousterhout, Hari Balakrishnan, Devavrat Shah, and Hans Fugal. 2015. Fastpass: A centralized zero-queue datacenter network. ACM SIGCOMM Computer Communication Review 44, 4 (2015), 307--318.

Digital Library

[22]

Diana Andreea Popescu, Noa Zilberman, and Andrew William Moore. 2017. Characterizing the impact of network latency on cloud-based applications' performance. (2017).

[23]

Irving S Reed and Gustave Solomon. 1960. Polynomial codes over certain finite fields. Journal of the society for industrial and applied mathematics 8, 2 (1960), 300--304.

[24]

Stephen M Rumble, Diego Ongaro, Ryan Stutsman, Mendel Rosenblum, and John K Ousterhout. 2011. It's Time for Low Latency. In HotOS, Vol. 13. 11--11.

Digital Library

[25]

Mellanox Technologies. 2017. Mellanox Spectrum-2 Ethernet Switch. http://www.mellanox.com/related-docs/prod_silicon/PB_Spectrum-2.pdf.

[26]

Zhongfeng Wang and Chung-Jue Chen. 2011. Feasibility Of 100G-KR FEC. (2011). http://www.ieee802.org/3/100GCU/public/may11/wang_01_0511.pdf

[27]

Noa Zilberman, Matthew Grosvenor, Diana Andreea Popescu, Neelakandan Manihatty-Bojan, Gianni Antichi, Marcin Wójcik, and Andrew W Moore. 2017. Where has my time gone?. In International Conference on Passive and Active Network Measurement. Springer, 201--214.

Cited By

Feng YMa K(2024)Switch-Less Dragonfly on Wafers: A Scalable Interconnection Architecture based on Wafer-Scale IntegrationProceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis10.1109/SC41406.2024.00102(1-17)Online publication date: 17-Nov-2024
https://dl.acm.org/doi/10.1109/SC41406.2024.00102
Joshi RSong CKhooi XBudhdev NMishra AChan MLeong BSchulzrinne HKohler EMaltz DMisra V(2023)Masking Corruption Packet Losses in Datacenter Networks with Link-local RetransmissionProceedings of the ACM SIGCOMM 2023 Conference10.1145/3603269.3604853(288-304)Online publication date: 10-Sep-2023
https://dl.acm.org/doi/10.1145/3603269.3604853
Gallenmüller SScholz DStubbe HCarle GCarle GOtt J(2021)The pos frameworkProceedings of the 17th International Conference on emerging Networking EXperiments and Technologies10.1145/3485983.3494841(259-266)Online publication date: 2-Dec-2021
https://dl.acm.org/doi/10.1145/3485983.3494841
Show More Cited By

Index Terms

FEC Killed The Cut-Through Switch
1. Networks

Recommendations

Bounded-Reorder Packet Scheduling in Optical Cut-Through Switch
The recently proposed optical cut-through (OpCut) switch holds a great potential in achieving high energy efficiency, as it allows optical packets to cut through the switch in optical domain whenever possible, which avoids power-hungry O/E/O conversion. ...
The Knockout Switch: A Simple, Modular Architecture for High-Performance Packet Switching

A new, high-performance packet-switching architecture, called the Knockout Switch, is proposed. The Knockout Switch uses a fully interconnected switch fabric topology (i.e., each input has a direct path to every output) so that no switch blocking occurs ...
The Switch Reordering Contagion: Preventing a Few Late Packets from Ruining the Whole Party

Packet reordering has now become one of the most significant bottlenecks in next-generation switch designs. A switch practically experiences a reordering delay contagion, such that a few late packets may affect a disproportionate number of other ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

NEAT '18: Proceedings of the 2018 Workshop on Networking for Emerging Applications and Technologies

August 2018

63 pages

ISBN:9781450359078

DOI:10.1145/3229574

Copyright © 2018 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGCOMM: ACM Special Interest Group on Data Communication

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 August 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article
Research
Refereed limited

Conference

SIGCOMM '18

Sponsor:

SIGCOMM

SIGCOMM '18: ACM SIGCOMM 2018 Conference

August 20, 2018

Budapest, Hungary

Acceptance Rates

Overall Acceptance Rate 8 of 18 submissions, 44%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
877
Total Downloads

Downloads (Last 12 months)151
Downloads (Last 6 weeks)20

Reflects downloads up to 11 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Feng YMa K(2024)Switch-Less Dragonfly on Wafers: A Scalable Interconnection Architecture based on Wafer-Scale IntegrationProceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis10.1109/SC41406.2024.00102(1-17)Online publication date: 17-Nov-2024
https://dl.acm.org/doi/10.1109/SC41406.2024.00102
Joshi RSong CKhooi XBudhdev NMishra AChan MLeong BSchulzrinne HKohler EMaltz DMisra V(2023)Masking Corruption Packet Losses in Datacenter Networks with Link-local RetransmissionProceedings of the ACM SIGCOMM 2023 Conference10.1145/3603269.3604853(288-304)Online publication date: 10-Sep-2023
https://dl.acm.org/doi/10.1145/3603269.3604853
Gallenmüller SScholz DStubbe HCarle GCarle GOtt J(2021)The pos frameworkProceedings of the 17th International Conference on emerging Networking EXperiments and Technologies10.1145/3485983.3494841(259-266)Online publication date: 2-Dec-2021
https://dl.acm.org/doi/10.1145/3485983.3494841
Xiang ZGabriel FUrbano ENguyen GReisslein MFitzek F(2019)Reducing Latency in Virtual Machines: Enabling Tactile Internet for Human-Machine Co-WorkingIEEE Journal on Selected Areas in Communications10.1109/JSAC.2019.290678837:5(1098-1116)Online publication date: May-2019
https://doi.org/10.1109/JSAC.2019.2906788

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents