The use of big data in a business revolves around a monitor-mine-manage (M3) loop: data is monitored in real-time, while mined insights are used to manage the business and derive value. While mining has traditionally been performed offline, recent years have seen an increasing need to perform all phases of M3 in real-time. A stream processing engine (SPE) enables such a seamless M3 loop for applications such as targeted advertising, recommender systems, risk analysis, and call-center analytics. However, these M3 applications require the SPE to maintain massive amounts of state in memory, leading to resource usage skew: memory is scarce and over-utilized, whereas CPU and I\/O are under-utilized. In this paper, we propose a novel solution to scaling SPEs for memory-bound M3 applications that leverages natural access skew in data-parallel subqueries, where a small fraction of the state is hot (frequently accessed) and most state is cold (infrequently accessed). We present ICE (incremental coldstate engine), a framework that allows an SPE to seamlessly migrate cold state to secondary storage (disk or flash). ICE uses a novel architecture that exploits the semantics of individual stream operators to efficiently manage cold state in an SPE using an incremental log-structured store. We implemented ICE inside an SPE. Experiments using real and synthetic datasets show that ICE can reduce memory usage significantly without sacrificing performance, and can sometimes even improve performance.d<\/p>\n","protected":false},"excerpt":{"rendered":"
The use of big data in a business revolves around a monitor-mine-manage (M3) loop: data is monitored in real-time, while mined insights are used to manage the business and derive value. While mining has traditionally been performed offline, recent years have seen an increasing need to perform all phases of M3 in real-time. A stream […]<\/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":[13563],"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-245552","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-data-platform-analytics","msr-locale-en_us"],"msr_publishername":"IEEE \u2013 Institute of Electrical and Electronics Engineers","msr_edition":"IEEE International Conference on Data Engineering (ICDE)","msr_affiliation":"","msr_published_date":"2016-05-01","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":"245555","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"ice-icde2016","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/06\/ice-icde2016.pdf","id":245555,"label_id":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Badrish Chandramouli","user_id":31166,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Badrish Chandramouli"},{"type":"user_nicename","value":"Justin Levandoski","user_id":32451,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Justin Levandoski"},{"type":"text","value":"Eli Cortez","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[957177],"msr_project":[171207,170875],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":171207,"post_title":"Trill","post_name":"trill","post_type":"msr-project","post_date":"2013-09-19 14:35:28","post_modified":"2019-07-16 08:47:44","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/trill\/","post_excerpt":"Trill is a high-performance open-source in-memory incremental analytics library. It can handle both real-time and offline data, and is based on a temporal data and query model. Trill can be used as a streaming engine, a lightweight in-memory relational engine, and as a progressive query processor (for early query results on partial data). You can learn more about Trill from the publications below, or from our slides\u00a0here pdf | pptx. Trill is now open-source, and…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171207"}]}},{"ID":170875,"post_title":"Streams","post_name":"streams","post_type":"msr-project","post_date":"2011-11-21 13:31:30","post_modified":"2017-06-19 10:26:41","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/streams\/","post_excerpt":"In the streams research project, we propose novel architectures, efficient processing techniques, models, and applications to support time-oriented queries over real-time and offline data streams. Our current focus in the project centers around Trill, a high-performance streaming analytics engine that is now used across Microsoft. Our currect focus areas include efficient query processing, scale-out, resiliency, streaming state management, and unstructured data support.","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170875"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/245552"}],"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\/245552\/revisions"}],"predecessor-version":[{"id":480447,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/245552\/revisions\/480447"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=245552"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=245552"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=245552"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=245552"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=245552"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=245552"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=245552"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=245552"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=245552"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=245552"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=245552"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=245552"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=245552"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=245552"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=245552"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=245552"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}