{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:08:42Z","timestamp":1755907722512,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["506529034"],"award-info":[{"award-number":["506529034"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,10]]},"DOI":"10.1145\/3603719.3603733","type":"proceedings-article","created":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T06:09:45Z","timestamp":1693116585000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Selecting Efficient Cluster Resources for Data Analytics: When and How to Allocate for In-Memory Processing?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7834-8845","authenticated-orcid":false,"given":"Jonathan","family":"Will","sequence":"first","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3755-1503","authenticated-orcid":false,"given":"Lauritz","family":"Thamsen","sequence":"additional","affiliation":[{"name":"University of Glasgow, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0763-3233","authenticated-orcid":false,"given":"Dominik","family":"Scheinert","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6454-6799","authenticated-orcid":false,"given":"Odej","family":"Kao","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Blink: Lightweight Sample Runs for Cost Optimization of Big Data Applications. In New Trends in Database and Information Systems","author":"Al-Sayeh Hani","year":"2022","unstructured":"Hani Al-Sayeh, Muhammad\u00a0Attahir Jibril, Bunjamin Memishi, and Kai-Uwe Sattler. 2022. Blink: Lightweight Sample Runs for Cost Optimization of Big Data Applications. In New Trends in Database and Information Systems. Springer."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517892"},{"key":"e_1_3_2_1_3_1","volume-title":"Cherrypick: Adaptively Unearthing the Best Cloud Configurations for Big Data Analytics. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Alipourfard Omid","year":"2017","unstructured":"Omid Alipourfard, Hongqiang\u00a0Harry Liu, Jianshu Chen, Shivaram Venkataraman, Minlan Yu, and Ming Zhang. 2017. Cherrypick: Adaptively Unearthing the Best Cloud Configurations for Big Data Analytics. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)."},{"key":"e_1_3_2_1_4_1","volume-title":"Apache Flink: Stream and Batch Processing in a Single Engine. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering 36, 4","author":"Carbone Paris","year":"2015","unstructured":"Paris Carbone, Asterios Katsifodimos, Stephan Ewen, Volker Markl, Seif Haridi, and Kostas Tzoumas. 2015. Apache Flink: Stream and Batch Processing in a Single Engine. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering 36, 4 (2015)."},{"key":"e_1_3_2_1_5_1","volume-title":"Silhouette: Efficient Cloud Configuration Exploration for Large-Scale Analytics","author":"Chen Yanjiao","year":"2021","unstructured":"Yanjiao Chen, Long Lin, Baochun Li, Qian Wang, and Qian Zhang. 2021. Silhouette: Efficient Cloud Configuration Exploration for Large-Scale Analytics. IEEE Trans. Parallel Distributed Syst. (TPDS) (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_2_1_7_1","volume-title":"Arrow: Low-level Augmented Bayesian Optimization for Finding the Best Cloud VM. In 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS). IEEE.","author":"Hsu Chin-Jung","year":"2018","unstructured":"Chin-Jung Hsu, Vivek Nair, Vincent\u00a0W Freeh, and Tim Menzies. 2018. Arrow: Low-level Augmented Bayesian Optimization for Finding the Best Cloud VM. In 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS). IEEE."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2371536.2371547"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987566"},{"key":"e_1_3_2_1_10_1","volume-title":"On the Potential of Execution Traces for Batch Processing Workload Optimization in Public Clouds. In IEEE International Conference on Big Data (Big Data).","author":"Scheinert Dominik","year":"2021","unstructured":"Dominik Scheinert, Alireza Alamgiralem, Jonathan Bader, Jonathan Will, Thorsten Wittkopp, and Lauritz Thamsen. 2021. On the Potential of Execution Traces for Batch Processing Workload Optimization in Public Clouds. In IEEE International Conference on Big Data (Big Data)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/PCCC.2016.7820629"},{"key":"e_1_3_2_1_12_1","volume-title":"Ernest: Efficient Performance Prediction for Large-scale Advanced Analytics. In 13th USENIX Symposium on Networked Systems Design and Implementation (NSDI 16)","author":"Venkataraman Shivaram","year":"2016","unstructured":"Shivaram Venkataraman, Zongheng Yang, Michael Franklin, Benjamin Recht, and Ion Stoica. 2016. Ernest: Efficient Performance Prediction for Large-scale Advanced Analytics. In 13th USENIX Symposium on Networked Systems Design and Implementation (NSDI 16)."},{"key":"e_1_3_2_1_13_1","volume-title":"Get Your Memory Right: The Crispy Resource Allocation Assistant for Large-Scale Data Processing. In IEEE International Conference on Cloud Engineering (IC2E).","author":"Will Jonathan","year":"2022","unstructured":"Jonathan Will, Lauritz Thamsen, Jonathan Bader, Dominik Scheinert, and Odej Kao. 2022. Get Your Memory Right: The Crispy Resource Allocation Assistant for Large-Scale Data Processing. In IEEE International Conference on Cloud Engineering (IC2E)."},{"key":"e_1_3_2_1_14_1","volume-title":"Ruya: Memory-Aware Iterative Optimization of Cluster Configurations for Big Data Processing. In IEEE International Conference on Big Data (Big Data).","author":"Will Jonathan","year":"2022","unstructured":"Jonathan Will, Lauritz Thamsen, Jonathan Bader, Dominik Scheinert, and Odej Kao. 2022. Ruya: Memory-Aware Iterative Optimization of Cluster Configurations for Big Data Processing. In IEEE International Conference on Big Data (Big Data)."},{"key":"e_1_3_2_1_15_1","volume-title":"Spark: Cluster Computing with Working Sets. HotCloud 10, 10","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Michael\u00a0J Franklin, Scott Shenker, Ion Stoica, 2010. Spark: Cluster Computing with Working Sets. HotCloud 10, 10 (2010)."}],"event":{"name":"SSDBM 2023: 35th International Conference on Scientific and Statistical Database Management","acronym":"SSDBM 2023","location":"Los Angeles CA USA"},"container-title":["35th International Conference on Scientific and Statistical Database Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603719.3603733","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603719.3603733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:08:01Z","timestamp":1755889681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603719.3603733"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,10]]},"references-count":15,"alternative-id":["10.1145\/3603719.3603733","10.1145\/3603719"],"URL":"https:\/\/doi.org\/10.1145\/3603719.3603733","relation":{},"subject":[],"published":{"date-parts":[[2023,7,10]]},"assertion":[{"value":"2023-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}