[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-140127-105":59,"doc-detail-140127-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","fast-and-effective-distribution-key-recommendation-for-amazon-redshift","Fast and Effective Distribution-Key Recommendation for Amazon Redshift","","Distributed data warehouses require careful partitioning to accelerate forecasted workloads. This paper analyzes how alternative data distribution schemes affect the total network cost of pairwise joins in Amazon Redshift. It presents a generally applicable distribution framework, introduces the Join Multi-Graph to model cluster workload history, and defines the Distribution-Key Recommendation problem. Theoretical results prove NP-completeness and intractable approximation. A hybrid heuristic-plus-exact method, BaW, finds high-quality distribution keys, reducing network cost up to 32x in real workloads and improving cluster performance.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/fast-and-effective-distribution-key-recommendation-for-amazon-redshift/140127/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/fast-and-effective-distribution-key-recommendation-for-amazon-redshift/140127.png","ImageObject",300,407,{"name":92,"@type":93},"Terk","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-28","2026-08-24",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the paper address in Amazon Redshift?","Question",{"text":113,"@type":114},"It studies how to split data across compute nodes to reduce network cost and speed up query execution for a forecasted join-heavy workload.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the paper represent workload history for analysis?",{"text":118,"@type":114},"It introduces the Join Multi-Graph, a graph-theoretic representation of cluster workload history.",{"name":120,"@type":111,"acceptedAnswer":121},"Why is “Distribution-Key Recommendation” difficult?",{"text":122,"@type":114},"The paper proves the problem is NP-complete and hard to approximate efficiently.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},140127,1787568205,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145},1099525198933,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Fast and Effective Distribution-Key Recommendation for  \nAmazon Redshift  \nPanos Parchas  \nAmazon Web Services Berlin, Germany  \n[parchp@amazon.com](parchp@amazon.com)  \nYonatan Naamad  \nAmazon Devices Sunnyvale, CA, USA  \n[ynaamad@amazon.com](ynaamad@amazon.com)  \nPeter Van Bouwel  \nAmazon Web Services Dublin, Ireland  \n[pbbouwel@amazon.com](pbbouwel@amazon.com)  \nChristos Faloutsos  \nCarnegie Mellon University & Amazon  \n[faloutso@amazon.com](faloutso@amazon.com)  \nMichalis Petropoulos  \nAmazon Web Services Palo Alto, CA, USA  \n[mpetropo@amazon.com](mpetropo@amazon.com)  \nABSTRACT  \nHow should we split data among the nodes of a distributed data warehouse in order to boost performance for a forecasted workload? In this paper, we study the e􀀋ect of di􀀋erent data partitioning schemes on the overall network cost of pairwise joins. We describe a generally-applicable data distribution framework initially designed for Amazon Redshift, a fully-managed petabyte-scale data warehouse in the cloud. To formalize the problem, we 􀀌rst introduce the Join Multi-Graph, a concise graph-theoretic representation of the workload history of a cluster. We then formulate the \\Distribution-Key Recommendation\" problem { a novel combinatorial problem on the Join Multi-Graph{ and relate it to problems studied in other sub􀀌elds of computer science. Our theoretical analysis proves that \\Distribution-Key Recommendation\" is NP-complete and is hard to approximate e􀀎ciently. Thus, we propose BaW, a hybrid approach that combines heuristic and exact algorithms to 􀀌nd a good data distribution scheme. Our extensive experimental evaluation on real and synthetic data showcases the e􀀎cacy of our method into recommending optimal (or close to optimal) distribution keys, which improve the cluster performance by reducing network cost up to 32x in some real workloads.  \nPVLDB Reference Format:  \nPanos Parchas, Yonatan Naamad, Peter Van Bouwel, Christos Faloutsos, Michalis Petropoulos. Fast and E􀀋ective DistributionKey Recommendation for Amazon Redshift. PVLDB, 13(11): 2411-2423, 2020 .  \nDOI: [https://doi.org/10.14778/3407790.3407834](https://doi.org/10.14778/3407790.3407834)  \n[1. INTRODUCTION](1. INTRODUCTION)  \nGiven a database query workload with joins on several relational tables, which are partitioned over a number of ma  \nThis work is licensed under the Creative Commons AttributionNonCommercial-NoDerivatives 4.0 International License. To view a copy of this license, visit [http://creativecommons.org/licenses/by-nc-nd/4.0/. For](http://creativecommons.org/licenses/by-nc-nd/4.0/. For)[ ](http://creativecommons.org/licenses/by-nc-nd/4.0/. For)any use beyond those covered by this license, obtain permission by emailing [info@vldb.org. Copyright](info@vldb.org. Copyright) is held by the owner/author(s). Publication rights licensed to the VLDB Endowment.  \nProceedings of the VLDB Endowment, Vol. 13, No. 11 ISSN 2150-8097 .  \nDOI: [https://doi.org/10.14778/3407790.3407834](https://doi.org/10.14778/3407790.3407834)  \nchines, how should we distribute the data to reduce network cost and ensure fast query execution?  \nAmazon Redshift [12, 2, 3] is a massively parallel processing MPP database system, meaning that both the storage and processing of a cluster is distributed among several machines (compute nodes) . In such systems, data is typically distributed row-wise, so that each row appears (in its entirety) at one compute node, but distinct rows from the same table may reside on di􀀋erent machines. Like most commercial data warehouse systems, Redshift supports 3 distinct ways of distributing the rows of each table:  \n􀀏 \\Even\" (= uniform/random), which distributes the rows among compute nodes in a round-robin fashion;  \n􀀏 \\All\" (= replicated), which makes full copies of a database table on each of the machines;  \n􀀏 \\Dist-Key\" (=fully distributed = hashed), which hashes the rows of a table on the values of a speci􀀌c attribute known as distribution key (DK) .  \nIn this work, we","cbCais326zLIeEGX","https://ap.wps.com/l/cbCais326zLIeEGX","pdf",1662207,13,"English","# Abstract\n# Introduction\n## Redshift distributed data and distribution styles\n## Collocation and network cost in joins\n## Example: even distribution vs dist-key distribution","[{\"question\":\"What problem does the paper address in Amazon Redshift?\",\"answer\":\"It studies how to split data across compute nodes to reduce network cost and speed up query execution for a forecasted join-heavy workload.\"},{\"question\":\"How does the paper represent workload history for analysis?\",\"answer\":\"It introduces the Join Multi-Graph, a graph-theoretic representation of cluster workload history.\"},{\"question\":\"Why is “Distribution-Key Recommendation” difficult?\",\"answer\":\"The paper proves the problem is NP-complete and hard to approximate efficiently.\"}]","Fast and Effective Distribution-Key Recommendation for Amazon Redshift | PDF",33]