Improving Data Center Network Utilization Using Near-Optimal Traffic Engineering
Equal cost multiple path (ECMP) forwarding is the most prevalent multipath routing used in data center (DC) networks today. However, it fails to exploit increased path diversity that can be provided by traffic engineering techniques through the assignment of nonuniform link weights to optimize netwo...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on parallel and distributed systems 2013-06, Vol.24 (6), p.1139-1148 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 1148 |
---|---|
container_issue | 6 |
container_start_page | 1139 |
container_title | IEEE transactions on parallel and distributed systems |
container_volume | 24 |
creator | Fung Po Tso Pezaros, D. P. |
description | Equal cost multiple path (ECMP) forwarding is the most prevalent multipath routing used in data center (DC) networks today. However, it fails to exploit increased path diversity that can be provided by traffic engineering techniques through the assignment of nonuniform link weights to optimize network resource usage. To this extent, constructing a routing algorithm that provides path diversity over nonuniform link weights (i.e., unequal cost links), simplicity in path discovery and optimality in minimizing maximum link utilization (MLU) is nontrivial. In this paper, we have implemented and evaluated the Penalizing Exponential Flow-spliTing (PEFT) algorithm in a cloud DC environment based on two dominant topologies, canonical and fat tree. In addition, we have proposed a new cloud DC topology which, with only a marginal modification of the current canonical tree DC architecture, can further reduce MLU and increase overall network capacity utilization through PEFT routing. |
doi_str_mv | 10.1109/TPDS.2012.343 |
format | Article |
fullrecord | <record><control><sourceid>crossref_RIE</sourceid><recordid>TN_cdi_ieee_primary_6392830</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6392830</ieee_id><sourcerecordid>10_1109_TPDS_2012_343</sourcerecordid><originalsourceid>FETCH-LOGICAL-c323t-5d80552eb20476d2709b050fee6219f2ad1197c0a43b63ce98c4c01b946f0cc3</originalsourceid><addsrcrecordid>eNo9kE1LAzEURYMoWKtLV27yB1JfvqaTpbRVC6UtOF0PmcxLibYzJRMU_fXOUHF17-JwuRxC7jlMOAfzWGznbxMBXEykkhdkxLXOmeC5vOw7KM2M4Oaa3HTdOwBXGtSIbJfHU2w_Q7Onc5ssnWGTMNI1pq82ftBdCofwY1NoG7rrBmqNNrLNKYWjPdAiWu-Do4tmHxrE2AO35MrbQ4d3fzkmxfOimL2y1eZlOXtaMSeFTEzXOWgtsBKgplktpmAq0OARs_6kF7bm3EwdWCWrTDo0uVMOeGVU5sE5OSbsPOti23URfXmK_aX4XXIoBxvlYKMcbJS9jZ5_OPMBEf_ZTBqRS5C_BqdbYQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Improving Data Center Network Utilization Using Near-Optimal Traffic Engineering</title><source>IEEE Electronic Library (IEL)</source><creator>Fung Po Tso ; Pezaros, D. P.</creator><creatorcontrib>Fung Po Tso ; Pezaros, D. P.</creatorcontrib><description>Equal cost multiple path (ECMP) forwarding is the most prevalent multipath routing used in data center (DC) networks today. However, it fails to exploit increased path diversity that can be provided by traffic engineering techniques through the assignment of nonuniform link weights to optimize network resource usage. To this extent, constructing a routing algorithm that provides path diversity over nonuniform link weights (i.e., unequal cost links), simplicity in path discovery and optimality in minimizing maximum link utilization (MLU) is nontrivial. In this paper, we have implemented and evaluated the Penalizing Exponential Flow-spliTing (PEFT) algorithm in a cloud DC environment based on two dominant topologies, canonical and fat tree. In addition, we have proposed a new cloud DC topology which, with only a marginal modification of the current canonical tree DC architecture, can further reduce MLU and increase overall network capacity utilization through PEFT routing.</description><identifier>ISSN: 1045-9219</identifier><identifier>EISSN: 1558-2183</identifier><identifier>DOI: 10.1109/TPDS.2012.343</identifier><identifier>CODEN: ITDSEO</identifier><language>eng</language><publisher>IEEE</publisher><subject>cloud computing ; Data center routing ; data center topology ; load balancing ; Mathematical model ; multipath routing ; Network topology ; Optimization ; Protocols ; Routing ; Servers ; Topology ; traffic engineering</subject><ispartof>IEEE transactions on parallel and distributed systems, 2013-06, Vol.24 (6), p.1139-1148</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c323t-5d80552eb20476d2709b050fee6219f2ad1197c0a43b63ce98c4c01b946f0cc3</citedby><cites>FETCH-LOGICAL-c323t-5d80552eb20476d2709b050fee6219f2ad1197c0a43b63ce98c4c01b946f0cc3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6392830$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,781,785,797,27928,27929,54762</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6392830$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Fung Po Tso</creatorcontrib><creatorcontrib>Pezaros, D. P.</creatorcontrib><title>Improving Data Center Network Utilization Using Near-Optimal Traffic Engineering</title><title>IEEE transactions on parallel and distributed systems</title><addtitle>TPDS</addtitle><description>Equal cost multiple path (ECMP) forwarding is the most prevalent multipath routing used in data center (DC) networks today. However, it fails to exploit increased path diversity that can be provided by traffic engineering techniques through the assignment of nonuniform link weights to optimize network resource usage. To this extent, constructing a routing algorithm that provides path diversity over nonuniform link weights (i.e., unequal cost links), simplicity in path discovery and optimality in minimizing maximum link utilization (MLU) is nontrivial. In this paper, we have implemented and evaluated the Penalizing Exponential Flow-spliTing (PEFT) algorithm in a cloud DC environment based on two dominant topologies, canonical and fat tree. In addition, we have proposed a new cloud DC topology which, with only a marginal modification of the current canonical tree DC architecture, can further reduce MLU and increase overall network capacity utilization through PEFT routing.</description><subject>cloud computing</subject><subject>Data center routing</subject><subject>data center topology</subject><subject>load balancing</subject><subject>Mathematical model</subject><subject>multipath routing</subject><subject>Network topology</subject><subject>Optimization</subject><subject>Protocols</subject><subject>Routing</subject><subject>Servers</subject><subject>Topology</subject><subject>traffic engineering</subject><issn>1045-9219</issn><issn>1558-2183</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kE1LAzEURYMoWKtLV27yB1JfvqaTpbRVC6UtOF0PmcxLibYzJRMU_fXOUHF17-JwuRxC7jlMOAfzWGznbxMBXEykkhdkxLXOmeC5vOw7KM2M4Oaa3HTdOwBXGtSIbJfHU2w_Q7Onc5ssnWGTMNI1pq82ftBdCofwY1NoG7rrBmqNNrLNKYWjPdAiWu-Do4tmHxrE2AO35MrbQ4d3fzkmxfOimL2y1eZlOXtaMSeFTEzXOWgtsBKgplktpmAq0OARs_6kF7bm3EwdWCWrTDo0uVMOeGVU5sE5OSbsPOti23URfXmK_aX4XXIoBxvlYKMcbJS9jZ5_OPMBEf_ZTBqRS5C_BqdbYQ</recordid><startdate>20130601</startdate><enddate>20130601</enddate><creator>Fung Po Tso</creator><creator>Pezaros, D. P.</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20130601</creationdate><title>Improving Data Center Network Utilization Using Near-Optimal Traffic Engineering</title><author>Fung Po Tso ; Pezaros, D. P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c323t-5d80552eb20476d2709b050fee6219f2ad1197c0a43b63ce98c4c01b946f0cc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>cloud computing</topic><topic>Data center routing</topic><topic>data center topology</topic><topic>load balancing</topic><topic>Mathematical model</topic><topic>multipath routing</topic><topic>Network topology</topic><topic>Optimization</topic><topic>Protocols</topic><topic>Routing</topic><topic>Servers</topic><topic>Topology</topic><topic>traffic engineering</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Fung Po Tso</creatorcontrib><creatorcontrib>Pezaros, D. P.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><jtitle>IEEE transactions on parallel and distributed systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Fung Po Tso</au><au>Pezaros, D. P.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving Data Center Network Utilization Using Near-Optimal Traffic Engineering</atitle><jtitle>IEEE transactions on parallel and distributed systems</jtitle><stitle>TPDS</stitle><date>2013-06-01</date><risdate>2013</risdate><volume>24</volume><issue>6</issue><spage>1139</spage><epage>1148</epage><pages>1139-1148</pages><issn>1045-9219</issn><eissn>1558-2183</eissn><coden>ITDSEO</coden><abstract>Equal cost multiple path (ECMP) forwarding is the most prevalent multipath routing used in data center (DC) networks today. However, it fails to exploit increased path diversity that can be provided by traffic engineering techniques through the assignment of nonuniform link weights to optimize network resource usage. To this extent, constructing a routing algorithm that provides path diversity over nonuniform link weights (i.e., unequal cost links), simplicity in path discovery and optimality in minimizing maximum link utilization (MLU) is nontrivial. In this paper, we have implemented and evaluated the Penalizing Exponential Flow-spliTing (PEFT) algorithm in a cloud DC environment based on two dominant topologies, canonical and fat tree. In addition, we have proposed a new cloud DC topology which, with only a marginal modification of the current canonical tree DC architecture, can further reduce MLU and increase overall network capacity utilization through PEFT routing.</abstract><pub>IEEE</pub><doi>10.1109/TPDS.2012.343</doi><tpages>10</tpages></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1045-9219 |
ispartof | IEEE transactions on parallel and distributed systems, 2013-06, Vol.24 (6), p.1139-1148 |
issn | 1045-9219 1558-2183 |
language | eng |
recordid | cdi_ieee_primary_6392830 |
source | IEEE Electronic Library (IEL) |
subjects | cloud computing Data center routing data center topology load balancing Mathematical model multipath routing Network topology Optimization Protocols Routing Servers Topology traffic engineering |
title | Improving Data Center Network Utilization Using Near-Optimal Traffic Engineering |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T02%3A23%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improving%20Data%20Center%20Network%20Utilization%20Using%20Near-Optimal%20Traffic%20Engineering&rft.jtitle=IEEE%20transactions%20on%20parallel%20and%20distributed%20systems&rft.au=Fung%20Po%20Tso&rft.date=2013-06-01&rft.volume=24&rft.issue=6&rft.spage=1139&rft.epage=1148&rft.pages=1139-1148&rft.issn=1045-9219&rft.eissn=1558-2183&rft.coden=ITDSEO&rft_id=info:doi/10.1109/TPDS.2012.343&rft_dat=%3Ccrossref_RIE%3E10_1109_TPDS_2012_343%3C/crossref_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6392830&rfr_iscdi=true |