On capacity provisioning in datacenter networks for full bandwidth communication

On capacity provisioning in datacenter networks for full bandwidth communication

Recent advances in datacenter network design have enabled full bandwidth communication based on the notion of Valiant load balancing. In this paper, we study from the link capacity viewpoint how such communication paradigm can be supported in the context of link failures, the study of which is curre...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wenda Ni, Changcheng Huang, Jing Wu
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Resource management
Topology
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 67
container_issue
container_start_page 62
container_title
container_volume
creator Wenda Ni
Changcheng Huang
Jing Wu
description Recent advances in datacenter network design have enabled full bandwidth communication based on the notion of Valiant load balancing. In this paper, we study from the link capacity viewpoint how such communication paradigm can be supported in the context of link failures, the study of which is currently absent. In particular, we target full bandwidth communication among all the servers, for all valid traffic patterns, and under k arbitrary link failures. We derive the minimum link capacity required on two typical datacenter topologies-VL2 and fat-tree. Our main finding is that given the same server scale, fat-tree requires less total link capacity than VL2 for 1 ≤ k ≤ n/4, where n denotes the port count of homogeneous switches used in fat-tree. For k > n/4, there exists a turning point from which VL2 becomes more capacity-efficient.
doi_str_mv 10.1109/HPSR.2013.6602291
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6602291</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6602291</ieee_id><sourcerecordid>6602291</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-bb1bfa1f7c4730e3dc334e7593066c8b1cb22c15c9e75196bc81417426a8f0633</originalsourceid><addsrcrecordid>eNotkN9KwzAchSMoOGYfQLzJC7TmlzRJcylDnTDY8M_1SNJEo21a0syxt7fgrg4c-A58B6FbIBUAUffr3dtrRQmwSghCqYILVCjZQC0kqwUl8hItKKO85JzTa1RM0zchBKQQTKgF2m0jtnrUNuQTHtPwG6YwxBA_cYi41VlbF7NLOLp8HNLPhP2QsD90HTY6tsfQ5i9sh74_xGB1ntEbdOV1N7ninEv08fT4vlqXm-3zy-phUwaQPJfGgPEavLS1ZMSx1jJWO8kVI0LYxoA1lFrgVs0lKGHsrASypkI3ngjGlujufzc45_ZjCr1Op_35A_YH3kZQqw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>On capacity provisioning in datacenter networks for full bandwidth communication</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Wenda Ni ; Changcheng Huang ; Jing Wu</creator><creatorcontrib>Wenda Ni ; Changcheng Huang ; Jing Wu</creatorcontrib><description>Recent advances in datacenter network design have enabled full bandwidth communication based on the notion of Valiant load balancing. In this paper, we study from the link capacity viewpoint how such communication paradigm can be supported in the context of link failures, the study of which is currently absent. In particular, we target full bandwidth communication among all the servers, for all valid traffic patterns, and under k arbitrary link failures. We derive the minimum link capacity required on two typical datacenter topologies-VL2 and fat-tree. Our main finding is that given the same server scale, fat-tree requires less total link capacity than VL2 for 1 ≤ k ≤ n/4, where n denotes the port count of homogeneous switches used in fat-tree. For k &gt; n/4, there exists a turning point from which VL2 becomes more capacity-efficient.</description><identifier>ISSN: 2325-5552</identifier><identifier>EISBN: 9781467346207</identifier><identifier>EISBN: 1467346209</identifier><identifier>DOI: 10.1109/HPSR.2013.6602291</identifier><language>eng</language><publisher>IEEE</publisher><subject>Resource management ; Topology</subject><ispartof>2013 IEEE 14th International Conference on High Performance Switching and Routing (HPSR), 2013, p.62-67</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6602291$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6602291$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Wenda Ni</creatorcontrib><creatorcontrib>Changcheng Huang</creatorcontrib><creatorcontrib>Jing Wu</creatorcontrib><title>On capacity provisioning in datacenter networks for full bandwidth communication</title><title>2013 IEEE 14th International Conference on High Performance Switching and Routing (HPSR)</title><addtitle>HPSR</addtitle><description>Recent advances in datacenter network design have enabled full bandwidth communication based on the notion of Valiant load balancing. In this paper, we study from the link capacity viewpoint how such communication paradigm can be supported in the context of link failures, the study of which is currently absent. In particular, we target full bandwidth communication among all the servers, for all valid traffic patterns, and under k arbitrary link failures. We derive the minimum link capacity required on two typical datacenter topologies-VL2 and fat-tree. Our main finding is that given the same server scale, fat-tree requires less total link capacity than VL2 for 1 ≤ k ≤ n/4, where n denotes the port count of homogeneous switches used in fat-tree. For k &gt; n/4, there exists a turning point from which VL2 becomes more capacity-efficient.</description><subject>Resource management</subject><subject>Topology</subject><issn>2325-5552</issn><isbn>9781467346207</isbn><isbn>1467346209</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotkN9KwzAchSMoOGYfQLzJC7TmlzRJcylDnTDY8M_1SNJEo21a0syxt7fgrg4c-A58B6FbIBUAUffr3dtrRQmwSghCqYILVCjZQC0kqwUl8hItKKO85JzTa1RM0zchBKQQTKgF2m0jtnrUNuQTHtPwG6YwxBA_cYi41VlbF7NLOLp8HNLPhP2QsD90HTY6tsfQ5i9sh74_xGB1ntEbdOV1N7ninEv08fT4vlqXm-3zy-phUwaQPJfGgPEavLS1ZMSx1jJWO8kVI0LYxoA1lFrgVs0lKGHsrASypkI3ngjGlujufzc45_ZjCr1Op_35A_YH3kZQqw</recordid><startdate>201307</startdate><enddate>201307</enddate><creator>Wenda Ni</creator><creator>Changcheng Huang</creator><creator>Jing Wu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201307</creationdate><title>On capacity provisioning in datacenter networks for full bandwidth communication</title><author>Wenda Ni ; Changcheng Huang ; Jing Wu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-bb1bfa1f7c4730e3dc334e7593066c8b1cb22c15c9e75196bc81417426a8f0633</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Resource management</topic><topic>Topology</topic><toplevel>online_resources</toplevel><creatorcontrib>Wenda Ni</creatorcontrib><creatorcontrib>Changcheng Huang</creatorcontrib><creatorcontrib>Jing Wu</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wenda Ni</au><au>Changcheng Huang</au><au>Jing Wu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>On capacity provisioning in datacenter networks for full bandwidth communication</atitle><btitle>2013 IEEE 14th International Conference on High Performance Switching and Routing (HPSR)</btitle><stitle>HPSR</stitle><date>2013-07</date><risdate>2013</risdate><spage>62</spage><epage>67</epage><pages>62-67</pages><issn>2325-5552</issn><eisbn>9781467346207</eisbn><eisbn>1467346209</eisbn><abstract>Recent advances in datacenter network design have enabled full bandwidth communication based on the notion of Valiant load balancing. In this paper, we study from the link capacity viewpoint how such communication paradigm can be supported in the context of link failures, the study of which is currently absent. In particular, we target full bandwidth communication among all the servers, for all valid traffic patterns, and under k arbitrary link failures. We derive the minimum link capacity required on two typical datacenter topologies-VL2 and fat-tree. Our main finding is that given the same server scale, fat-tree requires less total link capacity than VL2 for 1 ≤ k ≤ n/4, where n denotes the port count of homogeneous switches used in fat-tree. For k &gt; n/4, there exists a turning point from which VL2 becomes more capacity-efficient.</abstract><pub>IEEE</pub><doi>10.1109/HPSR.2013.6602291</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2325-5552
ispartof 2013 IEEE 14th International Conference on High Performance Switching and Routing (HPSR), 2013, p.62-67
issn 2325-5552
language eng
recordid cdi_ieee_primary_6602291
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Resource management
Topology
title On capacity provisioning in datacenter networks for full bandwidth communication
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T23%3A49%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=On%20capacity%20provisioning%20in%20datacenter%20networks%20for%20full%20bandwidth%20communication&rft.btitle=2013%20IEEE%2014th%20International%20Conference%20on%20High%20Performance%20Switching%20and%20Routing%20(HPSR)&rft.au=Wenda%20Ni&rft.date=2013-07&rft.spage=62&rft.epage=67&rft.pages=62-67&rft.issn=2325-5552&rft_id=info:doi/10.1109/HPSR.2013.6602291&rft_dat=%3Cieee_6IE%3E6602291%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467346207&rft.eisbn_list=1467346209&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6602291&rfr_iscdi=true