Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control
This paper develops a technique to detect whether the cross traffic competing with a flow is elastic or not, and shows how to use the elasticity detector to improve congestion control. If the cross traffic is elastic, i.e., made up of buffer-filling flows like Cubic or Reno, then one should use a sc...
Main Authors: | , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
ACM
2021
|
Online Access: | https://hdl.handle.net/1721.1/137381 |
_version_ | 1811084664984567808 |
---|---|
author | Goyal, Prateesh Narayan, Akshay Cangialosi, Frank Raghavan, Deepti Narayana, Srinivas Alizadeh, Mohammad Balakrishnan, Hari |
author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Goyal, Prateesh Narayan, Akshay Cangialosi, Frank Raghavan, Deepti Narayana, Srinivas Alizadeh, Mohammad Balakrishnan, Hari |
author_sort | Goyal, Prateesh |
collection | MIT |
description | This paper develops a technique to detect whether the cross traffic competing with a flow is elastic or not, and shows how to use the elasticity detector to improve congestion control. If the cross traffic is elastic, i.e., made up of buffer-filling flows like Cubic or Reno, then one should use a scheme that competes well with such traffic. Such a scheme will not be able to control delays because the cross traffic will not cooperate. If, however, cross traffic is inelastic, then one can use a suitable delay-sensitive congestion control algorithm, which can control delays, but which would have obtained dismal throughput when run concurrently with a buffer-filling algorithm.
We use the elasticity detector to demonstrate a congestion control framework that always achieves high utilization, but which can also achieve low delays when cross traffic permits it. The technique uses an asymmetric sinusoidal pulse patternand estimates elasticity by computing the frequency response(FFT) of the cross traffic estimate; we have measured its accuracy to be over 90%. We have developed Nimbus, a protocol that explicitly switches between TCP-competitive and delay-sensitive modes using the elasticity detector. Our results on emulated and real-world paths show that Nimbus achieves throughput comparable to or better than Cubic always, but with delays that are much lower when cross traffic is inelastic. Unlike BBR, Nimbus is fair to Cubic, and has significantly lower delay in all cases; for example, on real-world paths, Nimbus has 11% lower throughput but at 40-50 ms lower packet delay. |
first_indexed | 2024-09-23T12:55:07Z |
format | Article |
id | mit-1721.1/137381 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T12:55:07Z |
publishDate | 2021 |
publisher | ACM |
record_format | dspace |
spelling | mit-1721.1/1373812023-04-10T13:05:31Z Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control Goyal, Prateesh Narayan, Akshay Cangialosi, Frank Raghavan, Deepti Narayana, Srinivas Alizadeh, Mohammad Balakrishnan, Hari Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory This paper develops a technique to detect whether the cross traffic competing with a flow is elastic or not, and shows how to use the elasticity detector to improve congestion control. If the cross traffic is elastic, i.e., made up of buffer-filling flows like Cubic or Reno, then one should use a scheme that competes well with such traffic. Such a scheme will not be able to control delays because the cross traffic will not cooperate. If, however, cross traffic is inelastic, then one can use a suitable delay-sensitive congestion control algorithm, which can control delays, but which would have obtained dismal throughput when run concurrently with a buffer-filling algorithm. We use the elasticity detector to demonstrate a congestion control framework that always achieves high utilization, but which can also achieve low delays when cross traffic permits it. The technique uses an asymmetric sinusoidal pulse patternand estimates elasticity by computing the frequency response(FFT) of the cross traffic estimate; we have measured its accuracy to be over 90%. We have developed Nimbus, a protocol that explicitly switches between TCP-competitive and delay-sensitive modes using the elasticity detector. Our results on emulated and real-world paths show that Nimbus achieves throughput comparable to or better than Cubic always, but with delays that are much lower when cross traffic is inelastic. Unlike BBR, Nimbus is fair to Cubic, and has significantly lower delay in all cases; for example, on real-world paths, Nimbus has 11% lower throughput but at 40-50 ms lower packet delay. 2021-11-04T17:57:11Z 2021-11-04T17:57:11Z 2018-07-16 2019-05-02T16:21:23Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/137381 Goyal, Prateesh, Narayan, Akshay, Cangialosi, Frank, Raghavan, Deepti, Narayana, Srinivas et al. 2018. "Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control." en 10.1145/3232755.3232772 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf ACM MIT web domain |
spellingShingle | Goyal, Prateesh Narayan, Akshay Cangialosi, Frank Raghavan, Deepti Narayana, Srinivas Alizadeh, Mohammad Balakrishnan, Hari Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control |
title | Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control |
title_full | Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control |
title_fullStr | Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control |
title_full_unstemmed | Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control |
title_short | Elasticity Detection: A Building Block for Delay-Sensitive Congestion Control |
title_sort | elasticity detection a building block for delay sensitive congestion control |
url | https://hdl.handle.net/1721.1/137381 |
work_keys_str_mv | AT goyalprateesh elasticitydetectionabuildingblockfordelaysensitivecongestioncontrol AT narayanakshay elasticitydetectionabuildingblockfordelaysensitivecongestioncontrol AT cangialosifrank elasticitydetectionabuildingblockfordelaysensitivecongestioncontrol AT raghavandeepti elasticitydetectionabuildingblockfordelaysensitivecongestioncontrol AT narayanasrinivas elasticitydetectionabuildingblockfordelaysensitivecongestioncontrol AT alizadehmohammad elasticitydetectionabuildingblockfordelaysensitivecongestioncontrol AT balakrishnanhari elasticitydetectionabuildingblockfordelaysensitivecongestioncontrol |