{"id":800932,"date":"2021-11-30T16:58:21","date_gmt":"2021-12-01T00:58:21","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=800932"},"modified":"2022-02-12T11:51:07","modified_gmt":"2022-02-12T19:51:07","slug":"decentralized-cloud-wide-area-network-traffic-engineering-with-blastshield","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/decentralized-cloud-wide-area-network-traffic-engineering-with-blastshield\/","title":{"rendered":"Decentralized cloud wide-area network traffic engineering with BlastShield"},"content":{"rendered":"<p>Cloud networks are increasingly managed by centralized software defined<br \/>\ncontrollers. Centralized traffic engineering controllers achieve higher network<br \/>\nthroughput than decentralized implementations, but are a single point of failure<br \/>\nin the network.<br \/>\nLarge scale networks require controllers with isolated fault domains to contain<br \/>\nthe<em> blast radius<\/em> of faults. In this work, we present BlastShield,<br \/>\nMicrosoft&#8217;s SDN-based decentralized WAN traffic engineering system.<br \/>\nBlastShield <em>slices<\/em>\u00a0the WAN into smaller fault domains, each managed by<br \/>\nits own slice controller. Slice controllers independently engineer traffic in<br \/>\ntheir slices to maximize global network throughput without relying on<br \/>\nhierarchical or central coordination.<br \/>\nDespite the lack of central coordination, BlastShield achieves similar network<br \/>\nthroughput as state-of-the-art centralized deployments. Moreover, BlastShield<br \/>\nreduces throughput loss from the failure of a single controller by over 65%.<br \/>\nBlastShield is deployed in Microsoft&#8217;s WAN today and carries a<br \/>\nmajority of the backbone traffic.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Cloud networks are increasingly managed by centralized software defined controllers. Centralized traffic engineering controllers achieve higher network throughput than decentralized implementations, but are a single point of failure in the network. Large scale networks require controllers with isolated fault domains to contain the blast radius of faults. In this work, we present BlastShield, Microsoft&#8217;s SDN-based [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13547],"msr-publication-type":[193718],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[249427],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-800932","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-systems-and-networking","msr-locale-en_us","msr-field-of-study-traffic-engineering"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2021-11-30","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"MSR-TR-2021-31","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"Microsoft","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/11\/blastshield-nsdi-paper.pdf","id":"820000","title":"blastshield-nsdi-paper","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":820000,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2022\/02\/blastshield-nsdi-paper.pdf"},{"id":800938,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/11\/blastshield-61a6c89e0ca05.pdf"}],"msr-author-ordering":[{"type":"text","value":"Umesh Krishnaswamy","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Rachee Singh","user_id":39952,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Rachee Singh"},{"type":"user_nicename","value":"Nikolaj Bj\u00f8rner","user_id":33067,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Nikolaj Bj\u00f8rner"},{"type":"user_nicename","value":"Himanshu Raj","user_id":33391,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Himanshu Raj"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[827029],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"techreport","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/800932"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/800932\/revisions"}],"predecessor-version":[{"id":800935,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/800932\/revisions\/800935"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=800932"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=800932"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=800932"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=800932"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=800932"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=800932"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=800932"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=800932"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=800932"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=800932"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=800932"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=800932"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=800932"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=800932"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=800932"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}