SFC: Near-Source Congestion Signaling and Flow Control

State-of-the-art congestion control algorithms for data centers alone do not cope well with transient congestion and high traffic bursts. To help with these, we revisit the concept of direct \emph{backward} feedback from switches and propose Back-to-Sender (BTS) signaling to many concurrent incast s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Le, Yanfang, Lee, Jeongkeun, Blendin, Jeremias, Chen, Jiayi, Nikolaidis, Georgios, Pan, Rong, Soule, Robert, Akella, Aditya, Segura, Pedro Yebenes, singhvi, Arjun, Li, Yuliang, Meng, Qingkai, Kim, Changhoon, Arslan, Serhat
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Le, Yanfang
Lee, Jeongkeun
Blendin, Jeremias
Chen, Jiayi
Nikolaidis, Georgios
Pan, Rong
Soule, Robert
Akella, Aditya
Segura, Pedro Yebenes
singhvi, Arjun
Li, Yuliang
Meng, Qingkai
Kim, Changhoon
Arslan, Serhat
description State-of-the-art congestion control algorithms for data centers alone do not cope well with transient congestion and high traffic bursts. To help with these, we revisit the concept of direct \emph{backward} feedback from switches and propose Back-to-Sender (BTS) signaling to many concurrent incast senders. Combining it with our novel approach to in-network caching, we achieve near-source sub-RTT congestion signaling. Source Flow Control (SFC) combines these two simple signaling mechanisms to instantly pause traffic sources, hence avoiding the head-of-line blocking problem of conventional hop-by-hop flow control. Our prototype system and scale simulations demonstrate that near-source signaling can significantly reduce the message completion time of various workloads in the presence of incast, complementing existing congestion control algorithms. Our results show that SFC can reduce the $99^{th}$-percentile flow completion times by $1.2-6\times$ and the peak switch buffer usage by $2-3\times$ compared to the recent incast solutions.
doi_str_mv 10.48550/arxiv.2305.00538
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2305_00538</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2305_00538</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-d170d7e1fbbf0d294b0e56a64cba5511cd89248260594c467b2952c5100a79bb3</originalsourceid><addsrcrecordid>eNotj7tOwzAYRr0woMIDMOEXSPjt-PeFDUUEkKoypHvkWyJLwUZuub09amE6wycdfYeQGwat0IhwZ-t3-mx5B9gCYKcviRyH_p7uoq3NWD6qj7QveYmHYyqZjmnJdk15oTYHOqzl67Qea1mvyMVs10O8_ueG7IfHff_cbF-fXvqHbWOl0k1gCoKKbHZuhsCNcBBRWim8s4iM-aANF5pLQCO8kMpxg9wjA7DKONdtyO2f9nx8eq_pzdaf6RQwnQO6Xz-3PqM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>SFC: Near-Source Congestion Signaling and Flow Control</title><source>arXiv.org</source><creator>Le, Yanfang ; Lee, Jeongkeun ; Blendin, Jeremias ; Chen, Jiayi ; Nikolaidis, Georgios ; Pan, Rong ; Soule, Robert ; Akella, Aditya ; Segura, Pedro Yebenes ; singhvi, Arjun ; Li, Yuliang ; Meng, Qingkai ; Kim, Changhoon ; Arslan, Serhat</creator><creatorcontrib>Le, Yanfang ; Lee, Jeongkeun ; Blendin, Jeremias ; Chen, Jiayi ; Nikolaidis, Georgios ; Pan, Rong ; Soule, Robert ; Akella, Aditya ; Segura, Pedro Yebenes ; singhvi, Arjun ; Li, Yuliang ; Meng, Qingkai ; Kim, Changhoon ; Arslan, Serhat</creatorcontrib><description>State-of-the-art congestion control algorithms for data centers alone do not cope well with transient congestion and high traffic bursts. To help with these, we revisit the concept of direct \emph{backward} feedback from switches and propose Back-to-Sender (BTS) signaling to many concurrent incast senders. Combining it with our novel approach to in-network caching, we achieve near-source sub-RTT congestion signaling. Source Flow Control (SFC) combines these two simple signaling mechanisms to instantly pause traffic sources, hence avoiding the head-of-line blocking problem of conventional hop-by-hop flow control. Our prototype system and scale simulations demonstrate that near-source signaling can significantly reduce the message completion time of various workloads in the presence of incast, complementing existing congestion control algorithms. Our results show that SFC can reduce the $99^{th}$-percentile flow completion times by $1.2-6\times$ and the peak switch buffer usage by $2-3\times$ compared to the recent incast solutions.</description><identifier>DOI: 10.48550/arxiv.2305.00538</identifier><language>eng</language><subject>Computer Science - Networking and Internet Architecture</subject><creationdate>2023-04</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2305.00538$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2305.00538$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Le, Yanfang</creatorcontrib><creatorcontrib>Lee, Jeongkeun</creatorcontrib><creatorcontrib>Blendin, Jeremias</creatorcontrib><creatorcontrib>Chen, Jiayi</creatorcontrib><creatorcontrib>Nikolaidis, Georgios</creatorcontrib><creatorcontrib>Pan, Rong</creatorcontrib><creatorcontrib>Soule, Robert</creatorcontrib><creatorcontrib>Akella, Aditya</creatorcontrib><creatorcontrib>Segura, Pedro Yebenes</creatorcontrib><creatorcontrib>singhvi, Arjun</creatorcontrib><creatorcontrib>Li, Yuliang</creatorcontrib><creatorcontrib>Meng, Qingkai</creatorcontrib><creatorcontrib>Kim, Changhoon</creatorcontrib><creatorcontrib>Arslan, Serhat</creatorcontrib><title>SFC: Near-Source Congestion Signaling and Flow Control</title><description>State-of-the-art congestion control algorithms for data centers alone do not cope well with transient congestion and high traffic bursts. To help with these, we revisit the concept of direct \emph{backward} feedback from switches and propose Back-to-Sender (BTS) signaling to many concurrent incast senders. Combining it with our novel approach to in-network caching, we achieve near-source sub-RTT congestion signaling. Source Flow Control (SFC) combines these two simple signaling mechanisms to instantly pause traffic sources, hence avoiding the head-of-line blocking problem of conventional hop-by-hop flow control. Our prototype system and scale simulations demonstrate that near-source signaling can significantly reduce the message completion time of various workloads in the presence of incast, complementing existing congestion control algorithms. Our results show that SFC can reduce the $99^{th}$-percentile flow completion times by $1.2-6\times$ and the peak switch buffer usage by $2-3\times$ compared to the recent incast solutions.</description><subject>Computer Science - Networking and Internet Architecture</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tOwzAYRr0woMIDMOEXSPjt-PeFDUUEkKoypHvkWyJLwUZuub09amE6wycdfYeQGwat0IhwZ-t3-mx5B9gCYKcviRyH_p7uoq3NWD6qj7QveYmHYyqZjmnJdk15oTYHOqzl67Qea1mvyMVs10O8_ueG7IfHff_cbF-fXvqHbWOl0k1gCoKKbHZuhsCNcBBRWim8s4iM-aANF5pLQCO8kMpxg9wjA7DKONdtyO2f9nx8eq_pzdaf6RQwnQO6Xz-3PqM</recordid><startdate>20230430</startdate><enddate>20230430</enddate><creator>Le, Yanfang</creator><creator>Lee, Jeongkeun</creator><creator>Blendin, Jeremias</creator><creator>Chen, Jiayi</creator><creator>Nikolaidis, Georgios</creator><creator>Pan, Rong</creator><creator>Soule, Robert</creator><creator>Akella, Aditya</creator><creator>Segura, Pedro Yebenes</creator><creator>singhvi, Arjun</creator><creator>Li, Yuliang</creator><creator>Meng, Qingkai</creator><creator>Kim, Changhoon</creator><creator>Arslan, Serhat</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230430</creationdate><title>SFC: Near-Source Congestion Signaling and Flow Control</title><author>Le, Yanfang ; Lee, Jeongkeun ; Blendin, Jeremias ; Chen, Jiayi ; Nikolaidis, Georgios ; Pan, Rong ; Soule, Robert ; Akella, Aditya ; Segura, Pedro Yebenes ; singhvi, Arjun ; Li, Yuliang ; Meng, Qingkai ; Kim, Changhoon ; Arslan, Serhat</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-d170d7e1fbbf0d294b0e56a64cba5511cd89248260594c467b2952c5100a79bb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Networking and Internet Architecture</topic><toplevel>online_resources</toplevel><creatorcontrib>Le, Yanfang</creatorcontrib><creatorcontrib>Lee, Jeongkeun</creatorcontrib><creatorcontrib>Blendin, Jeremias</creatorcontrib><creatorcontrib>Chen, Jiayi</creatorcontrib><creatorcontrib>Nikolaidis, Georgios</creatorcontrib><creatorcontrib>Pan, Rong</creatorcontrib><creatorcontrib>Soule, Robert</creatorcontrib><creatorcontrib>Akella, Aditya</creatorcontrib><creatorcontrib>Segura, Pedro Yebenes</creatorcontrib><creatorcontrib>singhvi, Arjun</creatorcontrib><creatorcontrib>Li, Yuliang</creatorcontrib><creatorcontrib>Meng, Qingkai</creatorcontrib><creatorcontrib>Kim, Changhoon</creatorcontrib><creatorcontrib>Arslan, Serhat</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Le, Yanfang</au><au>Lee, Jeongkeun</au><au>Blendin, Jeremias</au><au>Chen, Jiayi</au><au>Nikolaidis, Georgios</au><au>Pan, Rong</au><au>Soule, Robert</au><au>Akella, Aditya</au><au>Segura, Pedro Yebenes</au><au>singhvi, Arjun</au><au>Li, Yuliang</au><au>Meng, Qingkai</au><au>Kim, Changhoon</au><au>Arslan, Serhat</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SFC: Near-Source Congestion Signaling and Flow Control</atitle><date>2023-04-30</date><risdate>2023</risdate><abstract>State-of-the-art congestion control algorithms for data centers alone do not cope well with transient congestion and high traffic bursts. To help with these, we revisit the concept of direct \emph{backward} feedback from switches and propose Back-to-Sender (BTS) signaling to many concurrent incast senders. Combining it with our novel approach to in-network caching, we achieve near-source sub-RTT congestion signaling. Source Flow Control (SFC) combines these two simple signaling mechanisms to instantly pause traffic sources, hence avoiding the head-of-line blocking problem of conventional hop-by-hop flow control. Our prototype system and scale simulations demonstrate that near-source signaling can significantly reduce the message completion time of various workloads in the presence of incast, complementing existing congestion control algorithms. Our results show that SFC can reduce the $99^{th}$-percentile flow completion times by $1.2-6\times$ and the peak switch buffer usage by $2-3\times$ compared to the recent incast solutions.</abstract><doi>10.48550/arxiv.2305.00538</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2305.00538
ispartof
issn
language eng
recordid cdi_arxiv_primary_2305_00538
source arXiv.org
subjects Computer Science - Networking and Internet Architecture
title SFC: Near-Source Congestion Signaling and Flow Control
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T19%3A08%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SFC:%20Near-Source%20Congestion%20Signaling%20and%20Flow%20Control&rft.au=Le,%20Yanfang&rft.date=2023-04-30&rft_id=info:doi/10.48550/arxiv.2305.00538&rft_dat=%3Carxiv_GOX%3E2305_00538%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true