{"id":238096,"date":"2016-04-01T00:00:00","date_gmt":"2016-04-01T07:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/optimizing-distributed-actor-systems-for-dynamic-interactive-services\/"},"modified":"2018-10-16T19:58:23","modified_gmt":"2018-10-17T02:58:23","slug":"optimizing-distributed-actor-systems-for-dynamic-interactive-services","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/optimizing-distributed-actor-systems-for-dynamic-interactive-services\/","title":{"rendered":"Optimizing Distributed Actor Systems for Dynamic Interactive Services"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Distributed actor systems are widely used for developing interactive scalable cloud services, such as social networks and on-line games. By modeling an application as a dynamic set of lightweight communicating \u201cactors\u201d, developers can easily build complex distributed applications, while the underlying runtime system deals with low-level complexities of a distributed environment.<\/p>\n<p>We present <em>ActOp<\/em> \u2014 a data-driven, application-independent runtime mechanism for optimizing end-to-end service latency of actor-based distributed applications. <em>ActOp<\/em> targets the two dominant factors affecting latency: the overhead of remote inter-actor communications across servers, and the intra-server queuing delay. <em>ActOp<\/em> automatically identifies frequently communicating actors and migrates them to the same server transparently to the running application. The migration decisions are driven by a novel scalable distributed graph partitioning algorithm which does not rely on a single server to store the whole communication graph, thereby enabling efficient actor placement even for applications with rapidly changing graphs (e.g., chat services). Further, each server autonomously reduces the queuing delay by learning an internal queuing model and configuring threads according to instantaneous request rate and application demands.<\/p>\n<p>We prototype <em>ActOp<\/em> by integrating it with <em>Orleans<\/em> \u2013 a popular open-source actor system [4, 13]. Experiments with realistic workloads show latency improvements of up to 75% for the 99th percentile, up to 63% for the mean, with up to 2x increase in peak system throughput.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Distributed actor systems are widely used for developing interactive scalable cloud services, such as social networks and on-line games. By modeling an application as a dynamic set of lightweight communicating \u201cactors\u201d, developers can easily build complex distributed applications, while the underlying runtime system deals with low-level complexities of a distributed environment. We present ActOp \u2014 [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","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-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-238096","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-systems-and-networking","msr-locale-en_us"],"msr_publishername":"ACM - Association for Computing Machinery","msr_edition":"EuroSys 2016","msr_affiliation":"","msr_published_date":"2016-04-01","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":"","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":"238410","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"eurosys16loca_camera_ready.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/eurosys16loca_camera_ready-1.pdf","id":238410,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":238410,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/eurosys16loca_camera_ready-1.pdf"}],"msr-author-ordering":[{"type":"text","value":"Andrew Newell","user_id":0,"rest_url":false},{"type":"user_nicename","value":"gkliot","user_id":31883,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=gkliot"},{"type":"user_nicename","value":"ishai","user_id":32116,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=ishai"},{"type":"text","value":"Aditya Gopalan","user_id":0,"rest_url":false},{"type":"text","value":"Soramichi Akiyama","user_id":0,"rest_url":false},{"type":"text","value":"Mark Silberstein","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[170573],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":170573,"post_title":"Orleans - Virtual Actors","post_name":"orleans-virtual-actors","post_type":"msr-project","post_date":"2010-10-14 17:19:52","post_modified":"2018-04-02 13:24:10","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/orleans-virtual-actors\/","post_excerpt":"Project \"Orleans\" invented the Virtual Actor abstraction, which provides a straightforward approach to building distributed interactive\u00a0applications, without the need to learn complex programming\u00a0patterns for handling concurrency, fault tolerance, and resource management. Orleans applications scale-up automatically and are meant to be deployed\u00a0in the cloud. It has been used heavily by a number of high-scale cloud services at Microsoft, starting with cloud services for the Halo franchise running in production in Microsoft Azure since 2011. The core&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170573"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/238096"}],"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\/238096\/revisions"}],"predecessor-version":[{"id":515663,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/238096\/revisions\/515663"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=238096"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=238096"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=238096"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=238096"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=238096"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=238096"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=238096"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=238096"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=238096"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=238096"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=238096"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=238096"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=238096"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=238096"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=238096"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=238096"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}