Optimal Representations of a Traffic Distribution in Switch Memories
Traffic splitting is a required functionality in networks, for example for load balancing over multiple paths or among different servers. The capacity of each server or path implies the distribution by which traffic should be split. A recent approach implements traffic splitting within the ternary c...
Gespeichert in:
Veröffentlicht in: | IEEE/ACM transactions on networking 2020-04, Vol.28 (2), p.930-943 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 943 |
---|---|
container_issue | 2 |
container_start_page | 930 |
container_title | IEEE/ACM transactions on networking |
container_volume | 28 |
creator | Sadeh, Yaniv Rottenstreich, Ori Barkan, Arye Kanizo, Yossi Kaplan, Haim |
description | Traffic splitting is a required functionality in networks, for example for load balancing over multiple paths or among different servers. The capacity of each server or path implies the distribution by which traffic should be split. A recent approach implements traffic splitting within the ternary content addressable memory (TCAM), which is often available in switches. It is important to reduce the amount of memory allocated for this task since TCAMs are power hungry and are often also required for other tasks such as classification and routing. For splitting a universe of 2^{W} addresses into k pieces of particular sizes, we give a simple algorithm that computes an optimal representation in O(Wk) time. Furthermore, we prove that a recently published load balancer, called Niagara, which runs in O(Wk\log k) time is in fact optimal. That is, both our algorithm and Niagara produce the smallest possible TCAM that splits the traffic exactly to the required pieces, where the only previously known algorithm for computing optimal exact representation has running time exponential in k . Finally, we use these optimal algorithms to experimentally study the number of TCAM rules required to split traffic in typical scenarios. |
doi_str_mv | 10.1109/TNET.2020.2977477 |
format | Article |
fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TNET_2020_2977477</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9032315</ieee_id><sourcerecordid>2391265915</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-f4ee27b74d3c36a1f7ebd4614d987e5097696ccbac1b6e53a7c48492ca74bc83</originalsourceid><addsrcrecordid>eNo9kFtLAzEQhYMoWKs_QHwJ-Lw192wepa0XqBZ030M2ncWUdndNUsR_7y4tPs3AnHOG8yF0S8mMUmIeqvdlNWOEkRkzWgutz9CESlkWTCp1PuxE8UIpwy7RVUpbQignTE3QYt3nsHc7_AF9hARtdjl0bcJdgx2uomua4PEipBxDfRhPOLT48ydk_4XfYN_FAOkaXTRul-DmNKeoelpW85ditX5-nT-uCs8Mz0UjAJiutdhwz5WjjYZ6IxQVG1NqkMRoZZT3tfO0ViC5016UwjDvtKh9yafo_hjbx-77ACnbbXeI7fDRMm4oU9JQOajoUeVjl1KExvZxaBh_LSV2ZGVHVnZkZU-sBs_d0RMA4F9vCGd8SPwDlOplfQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2391265915</pqid></control><display><type>article</type><title>Optimal Representations of a Traffic Distribution in Switch Memories</title><source>IEEE Electronic Library (IEL)</source><creator>Sadeh, Yaniv ; Rottenstreich, Ori ; Barkan, Arye ; Kanizo, Yossi ; Kaplan, Haim</creator><creatorcontrib>Sadeh, Yaniv ; Rottenstreich, Ori ; Barkan, Arye ; Kanizo, Yossi ; Kaplan, Haim</creatorcontrib><description><![CDATA[Traffic splitting is a required functionality in networks, for example for load balancing over multiple paths or among different servers. The capacity of each server or path implies the distribution by which traffic should be split. A recent approach implements traffic splitting within the ternary content addressable memory (TCAM), which is often available in switches. It is important to reduce the amount of memory allocated for this task since TCAMs are power hungry and are often also required for other tasks such as classification and routing. For splitting a universe of <inline-formula> <tex-math notation="LaTeX">2^{W} </tex-math></inline-formula> addresses into <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula> pieces of particular sizes, we give a simple algorithm that computes an optimal representation in <inline-formula> <tex-math notation="LaTeX">O(Wk) </tex-math></inline-formula> time. Furthermore, we prove that a recently published load balancer, called Niagara, which runs in <inline-formula> <tex-math notation="LaTeX">O(Wk\log k) </tex-math></inline-formula> time is in fact optimal. That is, both our algorithm and Niagara produce the smallest possible TCAM that splits the traffic exactly to the required pieces, where the only previously known algorithm for computing optimal exact representation has running time exponential in <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula>. Finally, we use these optimal algorithms to experimentally study the number of TCAM rules required to split traffic in typical scenarios.]]></description><identifier>ISSN: 1063-6692</identifier><identifier>EISSN: 1558-2566</identifier><identifier>DOI: 10.1109/TNET.2020.2977477</identifier><identifier>CODEN: IEANEP</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Associative memory ; Computer network management ; data structures ; Heuristic algorithms ; Law ; Memory management ; packet switching ; Partitioning algorithms ; Representations ; Run time (computers) ; Servers ; Splitting ; Switches ; Switching theory ; Task analysis ; Traffic capacity</subject><ispartof>IEEE/ACM transactions on networking, 2020-04, Vol.28 (2), p.930-943</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-f4ee27b74d3c36a1f7ebd4614d987e5097696ccbac1b6e53a7c48492ca74bc83</citedby><cites>FETCH-LOGICAL-c293t-f4ee27b74d3c36a1f7ebd4614d987e5097696ccbac1b6e53a7c48492ca74bc83</cites><orcidid>0000-0002-5712-1028 ; 0000-0002-4064-1238 ; 0000-0001-9586-8002</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9032315$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9032315$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sadeh, Yaniv</creatorcontrib><creatorcontrib>Rottenstreich, Ori</creatorcontrib><creatorcontrib>Barkan, Arye</creatorcontrib><creatorcontrib>Kanizo, Yossi</creatorcontrib><creatorcontrib>Kaplan, Haim</creatorcontrib><title>Optimal Representations of a Traffic Distribution in Switch Memories</title><title>IEEE/ACM transactions on networking</title><addtitle>TNET</addtitle><description><![CDATA[Traffic splitting is a required functionality in networks, for example for load balancing over multiple paths or among different servers. The capacity of each server or path implies the distribution by which traffic should be split. A recent approach implements traffic splitting within the ternary content addressable memory (TCAM), which is often available in switches. It is important to reduce the amount of memory allocated for this task since TCAMs are power hungry and are often also required for other tasks such as classification and routing. For splitting a universe of <inline-formula> <tex-math notation="LaTeX">2^{W} </tex-math></inline-formula> addresses into <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula> pieces of particular sizes, we give a simple algorithm that computes an optimal representation in <inline-formula> <tex-math notation="LaTeX">O(Wk) </tex-math></inline-formula> time. Furthermore, we prove that a recently published load balancer, called Niagara, which runs in <inline-formula> <tex-math notation="LaTeX">O(Wk\log k) </tex-math></inline-formula> time is in fact optimal. That is, both our algorithm and Niagara produce the smallest possible TCAM that splits the traffic exactly to the required pieces, where the only previously known algorithm for computing optimal exact representation has running time exponential in <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula>. Finally, we use these optimal algorithms to experimentally study the number of TCAM rules required to split traffic in typical scenarios.]]></description><subject>Algorithms</subject><subject>Associative memory</subject><subject>Computer network management</subject><subject>data structures</subject><subject>Heuristic algorithms</subject><subject>Law</subject><subject>Memory management</subject><subject>packet switching</subject><subject>Partitioning algorithms</subject><subject>Representations</subject><subject>Run time (computers)</subject><subject>Servers</subject><subject>Splitting</subject><subject>Switches</subject><subject>Switching theory</subject><subject>Task analysis</subject><subject>Traffic capacity</subject><issn>1063-6692</issn><issn>1558-2566</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kFtLAzEQhYMoWKs_QHwJ-Lw192wepa0XqBZ030M2ncWUdndNUsR_7y4tPs3AnHOG8yF0S8mMUmIeqvdlNWOEkRkzWgutz9CESlkWTCp1PuxE8UIpwy7RVUpbQignTE3QYt3nsHc7_AF9hARtdjl0bcJdgx2uomua4PEipBxDfRhPOLT48ydk_4XfYN_FAOkaXTRul-DmNKeoelpW85ditX5-nT-uCs8Mz0UjAJiutdhwz5WjjYZ6IxQVG1NqkMRoZZT3tfO0ViC5016UwjDvtKh9yafo_hjbx-77ACnbbXeI7fDRMm4oU9JQOajoUeVjl1KExvZxaBh_LSV2ZGVHVnZkZU-sBs_d0RMA4F9vCGd8SPwDlOplfQ</recordid><startdate>20200401</startdate><enddate>20200401</enddate><creator>Sadeh, Yaniv</creator><creator>Rottenstreich, Ori</creator><creator>Barkan, Arye</creator><creator>Kanizo, Yossi</creator><creator>Kaplan, Haim</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-5712-1028</orcidid><orcidid>https://orcid.org/0000-0002-4064-1238</orcidid><orcidid>https://orcid.org/0000-0001-9586-8002</orcidid></search><sort><creationdate>20200401</creationdate><title>Optimal Representations of a Traffic Distribution in Switch Memories</title><author>Sadeh, Yaniv ; Rottenstreich, Ori ; Barkan, Arye ; Kanizo, Yossi ; Kaplan, Haim</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-f4ee27b74d3c36a1f7ebd4614d987e5097696ccbac1b6e53a7c48492ca74bc83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Associative memory</topic><topic>Computer network management</topic><topic>data structures</topic><topic>Heuristic algorithms</topic><topic>Law</topic><topic>Memory management</topic><topic>packet switching</topic><topic>Partitioning algorithms</topic><topic>Representations</topic><topic>Run time (computers)</topic><topic>Servers</topic><topic>Splitting</topic><topic>Switches</topic><topic>Switching theory</topic><topic>Task analysis</topic><topic>Traffic capacity</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Sadeh, Yaniv</creatorcontrib><creatorcontrib>Rottenstreich, Ori</creatorcontrib><creatorcontrib>Barkan, Arye</creatorcontrib><creatorcontrib>Kanizo, Yossi</creatorcontrib><creatorcontrib>Kaplan, Haim</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><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE/ACM transactions on networking</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sadeh, Yaniv</au><au>Rottenstreich, Ori</au><au>Barkan, Arye</au><au>Kanizo, Yossi</au><au>Kaplan, Haim</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Optimal Representations of a Traffic Distribution in Switch Memories</atitle><jtitle>IEEE/ACM transactions on networking</jtitle><stitle>TNET</stitle><date>2020-04-01</date><risdate>2020</risdate><volume>28</volume><issue>2</issue><spage>930</spage><epage>943</epage><pages>930-943</pages><issn>1063-6692</issn><eissn>1558-2566</eissn><coden>IEANEP</coden><abstract><![CDATA[Traffic splitting is a required functionality in networks, for example for load balancing over multiple paths or among different servers. The capacity of each server or path implies the distribution by which traffic should be split. A recent approach implements traffic splitting within the ternary content addressable memory (TCAM), which is often available in switches. It is important to reduce the amount of memory allocated for this task since TCAMs are power hungry and are often also required for other tasks such as classification and routing. For splitting a universe of <inline-formula> <tex-math notation="LaTeX">2^{W} </tex-math></inline-formula> addresses into <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula> pieces of particular sizes, we give a simple algorithm that computes an optimal representation in <inline-formula> <tex-math notation="LaTeX">O(Wk) </tex-math></inline-formula> time. Furthermore, we prove that a recently published load balancer, called Niagara, which runs in <inline-formula> <tex-math notation="LaTeX">O(Wk\log k) </tex-math></inline-formula> time is in fact optimal. That is, both our algorithm and Niagara produce the smallest possible TCAM that splits the traffic exactly to the required pieces, where the only previously known algorithm for computing optimal exact representation has running time exponential in <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula>. Finally, we use these optimal algorithms to experimentally study the number of TCAM rules required to split traffic in typical scenarios.]]></abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TNET.2020.2977477</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0002-5712-1028</orcidid><orcidid>https://orcid.org/0000-0002-4064-1238</orcidid><orcidid>https://orcid.org/0000-0001-9586-8002</orcidid></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | ISSN: 1063-6692 |
ispartof | IEEE/ACM transactions on networking, 2020-04, Vol.28 (2), p.930-943 |
issn | 1063-6692 1558-2566 |
language | eng |
recordid | cdi_crossref_primary_10_1109_TNET_2020_2977477 |
source | IEEE Electronic Library (IEL) |
subjects | Algorithms Associative memory Computer network management data structures Heuristic algorithms Law Memory management packet switching Partitioning algorithms Representations Run time (computers) Servers Splitting Switches Switching theory Task analysis Traffic capacity |
title | Optimal Representations of a Traffic Distribution in Switch Memories |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T02%3A23%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Optimal%20Representations%20of%20a%20Traffic%20Distribution%20in%20Switch%20Memories&rft.jtitle=IEEE/ACM%20transactions%20on%20networking&rft.au=Sadeh,%20Yaniv&rft.date=2020-04-01&rft.volume=28&rft.issue=2&rft.spage=930&rft.epage=943&rft.pages=930-943&rft.issn=1063-6692&rft.eissn=1558-2566&rft.coden=IEANEP&rft_id=info:doi/10.1109/TNET.2020.2977477&rft_dat=%3Cproquest_RIE%3E2391265915%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2391265915&rft_id=info:pmid/&rft_ieee_id=9032315&rfr_iscdi=true |