{"id":571098,"date":"2019-03-03T09:34:18","date_gmt":"2019-03-03T17:34:18","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=571098"},"modified":"2019-03-03T09:34:18","modified_gmt":"2019-03-03T17:34:18","slug":"shoal-a-network-architecture-for-disaggregated-racks","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/shoal-a-network-architecture-for-disaggregated-racks\/","title":{"rendered":"Shoal: A Network Architecture for Disaggregated Racks"},"content":{"rendered":"

Disaggregated racks comprise a dense cluster of separate pools of compute, memory and storage blades, all inter-connected through an internal network within a single rack. However, their density poses a unique challenge for the rack\u2019s network: it needs to connect an order of magnitude more nodes than today\u2019s racks without exceeding the rack\u2019s fixed power budget and without compromising on performance. We present Shoal, a power-efficient yet performant intra-rack network fabric built using fast circuit switches. Such switches consume less power as they have no buffers and no packet inspection mechanism, yet can be reconfigured in nanoseconds. Rack nodes transmit according to a static schedule such that there is no in-network contention without requiring a centralized controller. Shoal\u2019s congestion control leverages the physical fabric to achieve fairness and both bounded worst-case network throughput and queuing. We use an FPGA-based prototype, testbed experiments, and simulations to illustrate Shoal\u2019s mechanisms are practical, and can simultaneously achieve high density and high performance: 71% lower power and comparable or higher performance than today\u2019s network designs.<\/p>\n","protected":false},"excerpt":{"rendered":"

Disaggregated racks comprise a dense cluster of separate pools of compute, memory and storage blades, all inter-connected through an internal network within a single rack. However, their density poses a unique challenge for the rack\u2019s network: it needs to connect an order of magnitude more nodes than today\u2019s racks without exceeding the rack\u2019s fixed power […]<\/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":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-571098","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-systems-and-networking","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2019-2-26","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_editors":"","msr_series":"","msr_issue":"","msr_organization":"USENIX","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\/2019\/03\/shrivastav19shoal.pdf","id":"571101","title":"shrivastav19shoal","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":571101,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/03\/shrivastav19shoal.pdf"}],"msr-author-ordering":[{"type":"text","value":"Vishal Shrivastav","user_id":0,"rest_url":false},{"type":"text","value":"Asaf Valadarsky","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Hitesh Ballani","user_id":32008,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hitesh Ballani"},{"type":"user_nicename","value":"Paolo Costa","user_id":33218,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Paolo Costa"},{"type":"text","value":"Ki Suh Lee","user_id":0,"rest_url":false},{"type":"text","value":"Han Wang","user_id":0,"rest_url":false},{"type":"text","value":"Rachit Agarwal","user_id":0,"rest_url":false},{"type":"text","value":"Hakim Weatherspoon","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199561],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/571098"}],"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\/571098\/revisions"}],"predecessor-version":[{"id":571104,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/571098\/revisions\/571104"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=571098"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=571098"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=571098"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=571098"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=571098"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=571098"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=571098"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=571098"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=571098"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=571098"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=571098"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=571098"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=571098"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=571098"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=571098"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}