{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/88997"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/88997","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Designing data center networks for high throughput","abstract":"Data centers with tens of thousands of servers now support popular Internet services, scientific research, as well as industrial applications. The network is the foundation of such facilities, giving the large server pool the ability to work together on these applications. The network needs to provide high throughput between servers to ensure that computations are not slowed down by network bottlenecks, with servers waiting on data from other servers. This work address two broad, related questions about high-throughput data center network design: (a) how do we measure and benchmark various network designs for throughput? and (b) how do we design such networks for near-optimal throughput? The problem of designing high-throughput networks has received a lot of attention, with multiple interesting architectures being proposed every year. However, there is no clarity on how one should benchmark these networks and how they compare to each other. In fact, this work shows that commonly used measurement approaches, in particular, cut-metrics like bisection bandwidth, do not predict throughput accurately. In contrast, we directly evaluate the throughput of networks on both uniform and (heretofore unknown) nearly-worst-case traffic matrices, and include here a comparison of 10 networks using this approach. Further, prior work has not addressed a fundamental question: how far are we from throughput-optimal design? In this work, we propose the first upper bound on network throughput for any topology with identical switches. Although designing optimal topologies is infeasible, we demonstrate that random graphs achieve throughput surprisingly close to this bound -- within a few percent at the scale of a few thousand servers for uniform traffic. Our approach also addresses important practical concerns in the design of data center networks, such as incremental expansion and heterogeneous design – as more and varied equipment is added to a data center over the years in response to evolving needs, how do we best accommodate such equipment? Our networks can achieve the same incremental growth at 40% of the expense such growth would incur with past techniques for Clos networks. Further, our approach to designing heterogeneous topologies (i.e., where all the network switches are not identical) achieves 43% higher throughput than a comparable VL2 topology, a heterogeneous network already deployed in Microsoft’s data centers. We acknowledge that the use of random graphs also poses challenges, particularly with regards to efficient routing and physical cabling. We thus present here high-efficiency routing and cabling schemes for such networks as well.","abstract_html":"Data centers with tens of thousands of servers now support popular Internet services, scientific research, as well as industrial applications. The network is the foundation of such facilities, giving the large server pool the ability to work together on these applications. The network needs to provide high throughput between servers to ensure that computations are not slowed down by network bottlenecks, with servers waiting on data from other servers. This work address two broad, related questions about high-throughput data center network design: (a) how do we measure and benchmark various network designs for throughput? and (b) how do we design such networks for near-optimal throughput? The problem of designing high-throughput networks has received a lot of attention, with multiple interesting architectures being proposed every year. However, there is no clarity on how one should benchmark these networks and how they compare to each other. In fact, this work shows that commonly used measurement approaches, in particular, cut-metrics like bisection bandwidth, do not predict throughput accurately. In contrast, we directly evaluate the throughput of networks on both uniform and (heretofore unknown) nearly-worst-case traffic matrices, and include here a comparison of 10 networks using this approach. Further, prior work has not addressed a fundamental question: how far are we from throughput-optimal design? In this work, we propose the first upper bound on network throughput for any topology with identical switches. Although designing optimal topologies is infeasible, we demonstrate that random graphs achieve throughput surprisingly close to this bound -- within a few percent at the scale of a few thousand servers for uniform traffic. Our approach also addresses important practical concerns in the design of data center networks, such as incremental expansion and heterogeneous design – as more and varied equipment is added to a data center over the years in response to evolving needs, how do we best accommodate such equipment? Our networks can achieve the same incremental growth at 40% of the expense such growth would incur with past techniques for Clos networks. Further, our approach to designing heterogeneous topologies (i.e., where all the network switches are not identical) achieves 43% higher throughput than a comparable VL2 topology, a heterogeneous network already deployed in Microsoft’s data centers. We acknowledge that the use of random graphs also poses challenges, particularly with regards to efficient routing and physical cabling. We thus present here high-efficiency routing and cabling schemes for such networks as well.","abstract_has_math":false,"creators":["Singla, Ankit"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Godfrey, Philip B","Gupta, Indranil","Nahrstedt, Klara","Shenker, Scott"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2016,"date_issued":"2016-03-02T19:33:46Z","date_published":"2016-03-02T19:33:46Z","updated_at":"2026-07-22T22:26:32Z","subjects":["topology design","topology","network","random","throughput"],"languages":["en"],"rights":["Copyright 2015 Ankit Singla"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/88997","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Godfrey, Philip B","Gupta, Indranil","Nahrstedt, Klara","Shenker, Scott"]},{"key":"dc:creator","label":"Author","values":["Singla, Ankit"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2016-03-02T19:33:46Z","2015-11-20","2015-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["topology design","topology","network","random","throughput"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2015 Ankit Singla"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/88997"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Data centers with tens of thousands of servers now support popular Internet services, scientific research, as well as industrial applications. The network is the foundation of such facilities, giving the large server pool the ability to work together on these applications. The network needs to provide high throughput between servers to ensure that computations are not slowed down by network bottlenecks, with servers waiting on data from other servers. This work address two broad, related questions about high-throughput data center network design: (a) how do we measure and benchmark various network designs for throughput? and (b) how do we design such networks for near-optimal throughput? The problem of designing high-throughput networks has received a lot of attention, with multiple interesting architectures being proposed every year. However, there is no clarity on how one should benchmark these networks and how they compare to each other. In fact, this work shows that commonly used measurement approaches, in particular, cut-metrics like bisection bandwidth, do not predict throughput accurately. In contrast, we directly evaluate the throughput of networks on both uniform and (heretofore unknown) nearly-worst-case traffic matrices, and include here a comparison of 10 networks using this approach. Further, prior work has not addressed a fundamental question: how far are we from throughput-optimal design? In this work, we propose the first upper bound on network throughput for any topology with identical switches. Although designing optimal topologies is infeasible, we demonstrate that random graphs achieve throughput surprisingly close to this bound -- within a few percent at the scale of a few thousand servers for uniform traffic. Our approach also addresses important practical concerns in the design of data center networks, such as incremental expansion and heterogeneous design – as more and varied equipment is added to a data center over the years in response to evolving needs, how do we best accommodate such equipment? Our networks can achieve the same incremental growth at 40% of the expense such growth would incur with past techniques for Clos networks. Further, our approach to designing heterogeneous topologies (i.e., where all the network switches are not identical) achieves 43% higher throughput than a comparable VL2 topology, a heterogeneous network already deployed in Microsoft’s data centers. We acknowledge that the use of random graphs also poses challenges, particularly with regards to efficient routing and physical cabling. We thus present here high-efficiency routing and cabling schemes for such networks as well.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-03-02 without embargo terms","The student, Ankit Singla, accepted the attached license on 2015-11-19 at 05:12.","The student, Ankit Singla, submitted this Dissertation for approval on 2015-11-19 at 05:22.","This Dissertation was approved for publication on 2015-11-20 at 08:44.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8805 on 2016-03-02 at 12:50:15","Made available in DSpace on 2016-03-02T19:33:46Z (GMT). No. of bitstreams: 2 SINGLA-DISSERTATION-2015.pdf: 2205747 bytes, checksum: 37f87f236b44f545883f93db5b0efe71 (MD5) LICENSE.txt: 4209 bytes, checksum: fdbd7c50e82f7720525e793d0707dd85 (MD5) Previous issue date: 2015-11-20"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Designing data center networks for high throughput"]}]}],"canonical_facts":{"dc:contributor":["Godfrey, Philip B","Gupta, Indranil","Nahrstedt, Klara","Shenker, Scott"],"dc:creator":["Singla, Ankit"],"dc:date":["2016-03-02T19:33:46Z","2015-11-20","2015-12"],"dc:description":["Data centers with tens of thousands of servers now support popular Internet services, scientific research, as well as industrial applications. The network is the foundation of such facilities, giving the large server pool the ability to work together on these applications. The network needs to provide high throughput between servers to ensure that computations are not slowed down by network bottlenecks, with servers waiting on data from other servers. This work address two broad, related questions about high-throughput data center network design: (a) how do we measure and benchmark various network designs for throughput? and (b) how do we design such networks for near-optimal throughput? The problem of designing high-throughput networks has received a lot of attention, with multiple interesting architectures being proposed every year. However, there is no clarity on how one should benchmark these networks and how they compare to each other. In fact, this work shows that commonly used measurement approaches, in particular, cut-metrics like bisection bandwidth, do not predict throughput accurately. In contrast, we directly evaluate the throughput of networks on both uniform and (heretofore unknown) nearly-worst-case traffic matrices, and include here a comparison of 10 networks using this approach. Further, prior work has not addressed a fundamental question: how far are we from throughput-optimal design? In this work, we propose the first upper bound on network throughput for any topology with identical switches. Although designing optimal topologies is infeasible, we demonstrate that random graphs achieve throughput surprisingly close to this bound -- within a few percent at the scale of a few thousand servers for uniform traffic. Our approach also addresses important practical concerns in the design of data center networks, such as incremental expansion and heterogeneous design – as more and varied equipment is added to a data center over the years in response to evolving needs, how do we best accommodate such equipment? Our networks can achieve the same incremental growth at 40% of the expense such growth would incur with past techniques for Clos networks. Further, our approach to designing heterogeneous topologies (i.e., where all the network switches are not identical) achieves 43% higher throughput than a comparable VL2 topology, a heterogeneous network already deployed in Microsoft’s data centers. We acknowledge that the use of random graphs also poses challenges, particularly with regards to efficient routing and physical cabling. We thus present here high-efficiency routing and cabling schemes for such networks as well.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2016-03-02 without embargo terms","The student, Ankit Singla, accepted the attached license on 2015-11-19 at 05:12.","The student, Ankit Singla, submitted this Dissertation for approval on 2015-11-19 at 05:22.","This Dissertation was approved for publication on 2015-11-20 at 08:44.","DSpace SAF Submission Ingestion Package generated from Vireo submission #8805 on 2016-03-02 at 12:50:15","Made available in DSpace on 2016-03-02T19:33:46Z (GMT). No. of bitstreams: 2 SINGLA-DISSERTATION-2015.pdf: 2205747 bytes, checksum: 37f87f236b44f545883f93db5b0efe71 (MD5) LICENSE.txt: 4209 bytes, checksum: fdbd7c50e82f7720525e793d0707dd85 (MD5) Previous issue date: 2015-11-20"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/88997"],"dc:language":["en"],"dc:rights":["Copyright 2015 Ankit Singla"],"dc:subject":["topology design","topology","network","random","throughput"],"dc:title":["Designing data center networks for high throughput"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:32Z"}