{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:04:13Z","timestamp":1793477053800,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","award":["UIDB\/50021\/2020, CMUP-ERI\/TIC\/0046\/2014, and POCI-01-0247-FEDER-045915"],"award-info":[{"award-number":["UIDB\/50021\/2020, CMUP-ERI\/TIC\/0046\/2014, and POCI-01-0247-FEDER-045915"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3419111.3421305","type":"proceedings-article","created":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T04:40:25Z","timestamp":1602564025000},"page":"208-222","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Finding the right cloud configuration for analytics clusters"],"prefix":"10.1145","author":[{"given":"Muhammad","family":"Bilal","sequence":"first","affiliation":[{"name":"UCLouvain and IST(ULisboa)\/INESC-ID"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Canini","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rodrigo","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"IST(ULisboa)\/INESC-ID"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"https:\/\/airflow.apache.org. [Online","author":"Airflow Apache","year":"2020","unstructured":"Apache Airflow . https:\/\/airflow.apache.org. [Online ; accessed 25\/05\/ 2020 ]. Apache Airflow. https:\/\/airflow.apache.org. [Online; accessed 25\/05\/2020]."},{"key":"e_1_3_2_2_2_1","volume-title":"https:\/\/aws.amazon.com\/blogs\/big-data\/build-a-concurrent-data-orchestration-pipeline-using-amazon-emr-and-apache-livy\/. [Online","author":"Concurrent Data Orchestration Pipeline Build","year":"2020","unstructured":"Build a Concurrent Data Orchestration Pipeline Using Amazon EMR and Apache Livy . https:\/\/aws.amazon.com\/blogs\/big-data\/build-a-concurrent-data-orchestration-pipeline-using-amazon-emr-and-apache-livy\/. [Online ; accessed 25\/05\/ 2020 ]. Build a Concurrent Data Orchestration Pipeline Using Amazon EMR and Apache Livy. https:\/\/aws.amazon.com\/blogs\/big-data\/build-a-concurrent-data-orchestration-pipeline-using-amazon-emr-and-apache-livy\/. [Online; accessed 25\/05\/2020]."},{"key":"e_1_3_2_2_3_1","volume-title":"https:\/\/flink.apache.org\/usecases.html. [Online","author":"Flink Use","year":"2020","unstructured":"Flink Use cases. https:\/\/flink.apache.org\/usecases.html. [Online ; accessed 01\/03\/ 2020 ]. Flink Use cases. https:\/\/flink.apache.org\/usecases.html. [Online; accessed 01\/03\/2020]."},{"key":"e_1_3_2_2_4_1","unstructured":"GraphX lib github. https:\/\/github.com\/apache\/spark\/tree\/master\/graphx\/src\/main\/scala\/org\/apache\/spark\/graphx\/lib.  GraphX lib github. https:\/\/github.com\/apache\/spark\/tree\/master\/graphx\/src\/main\/scala\/org\/apache\/spark\/graphx\/lib."},{"key":"e_1_3_2_2_5_1","volume-title":"https:\/\/aws.amazon.com\/blogs\/big-data\/how-verizon-media-group-migrated-from-on-premises-apache-hadoop-and-spark-to-amazon-emr\/. [Online","author":"How Verizon Media Group migrated from on-premises Apache Hadoop and Spark to Amazon EMR.","year":"2020","unstructured":"How Verizon Media Group migrated from on-premises Apache Hadoop and Spark to Amazon EMR. https:\/\/aws.amazon.com\/blogs\/big-data\/how-verizon-media-group-migrated-from-on-premises-apache-hadoop-and-spark-to-amazon-emr\/. [Online ; accessed 25\/05\/ 2020 ]. How Verizon Media Group migrated from on-premises Apache Hadoop and Spark to Amazon EMR. https:\/\/aws.amazon.com\/blogs\/big-data\/how-verizon-media-group-migrated-from-on-premises-apache-hadoop-and-spark-to-amazon-emr\/. [Online; accessed 25\/05\/2020]."},{"key":"e_1_3_2_2_6_1","unstructured":"Intel's HiBench benchmark. https:\/\/github.com\/intel-hadoop\/HiBench.  Intel's HiBench benchmark. https:\/\/github.com\/intel-hadoop\/HiBench."},{"key":"e_1_3_2_2_7_1","volume-title":"https:\/\/github.com\/spotify\/luigi. [Online","year":"2020","unstructured":"Luigi. https:\/\/github.com\/spotify\/luigi. [Online ; accessed 25\/05\/ 2020 ]. Luigi. https:\/\/github.com\/spotify\/luigi. [Online; accessed 25\/05\/2020]."},{"key":"e_1_3_2_2_8_1","unstructured":"Modified version of Intel's HiBench benchmark. https:\/\/github.com\/MBtech\/HiBench.  Modified version of Intel's HiBench benchmark. https:\/\/github.com\/MBtech\/HiBench."},{"key":"e_1_3_2_2_9_1","volume-title":"https:\/\/www.qubole.com\/developers\/spark-getting-started-guide\/workflow\/. [Online","author":"Pipeline Quoble","year":"2020","unstructured":"Quoble Pipeline . https:\/\/www.qubole.com\/developers\/spark-getting-started-guide\/workflow\/. [Online ; accessed 25\/05\/ 2020 ]. Quoble Pipeline. https:\/\/www.qubole.com\/developers\/spark-getting-started-guide\/workflow\/. [Online; accessed 25\/05\/2020]."},{"key":"e_1_3_2_2_10_1","unstructured":"Spearmint Github repo. https:\/\/github.com\/HIPS\/Spearmint.  Spearmint Github repo. https:\/\/github.com\/HIPS\/Spearmint."},{"key":"e_1_3_2_2_11_1","volume-title":"Lambda Architecture. https:\/\/medium.com\/walmartlabs\/how-we-built-a-data-pipeline-with-lambda-architecture-using-spark-spark-streaming-9d3b4b4555d3. [Online","author":"Labs Walmart","year":"2020","unstructured":"Walmart Labs : Lambda Architecture. https:\/\/medium.com\/walmartlabs\/how-we-built-a-data-pipeline-with-lambda-architecture-using-spark-spark-streaming-9d3b4b4555d3. [Online ; accessed 01\/03\/ 2020 ]. Walmart Labs: Lambda Architecture. https:\/\/medium.com\/walmartlabs\/how-we-built-a-data-pipeline-with-lambda-architecture-using-spark-spark-streaming-9d3b4b4555d3. [Online; accessed 01\/03\/2020]."},{"key":"e_1_3_2_2_12_1","first-page":"21","volume-title":"NSDI","author":"Agarwal S.","year":"2012","unstructured":"S. Agarwal , S. Kandula , N. Bruno , M.-C. Wu , I. Stoica , and J. Zhou . Re-optimizing data-parallel computing . In NSDI , pages 21 -- 21 . USENIX Association , 2012 . S. Agarwal, S. Kandula, N. Bruno, M.-C. Wu, I. Stoica, and J. Zhou. Re-optimizing data-parallel computing. In NSDI, pages 21--21. USENIX Association, 2012."},{"key":"e_1_3_2_2_13_1","volume-title":"NSDI","author":"Alipourfard O.","year":"2017","unstructured":"O. Alipourfard , H. H. Liu , J. Chen , S. Venkataraman , M. Yu , and M. Zhang . CherryPick: Adaptively Unearthing the Best Cloud Configurations for Big Data Analytics . In NSDI , 2017 . O. Alipourfard, H. H. Liu, J. Chen, S. Venkataraman, M. Yu, and M. Zhang. CherryPick: Adaptively Unearthing the Best Cloud Configurations for Big Data Analytics. In NSDI, 2017."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807150"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3127492"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1921591.1921593"},{"key":"e_1_3_2_2_17_1","volume-title":"Lynceus: Cost-efficient tuning and provisioning of data analytic jobs. arXiv preprint arXiv:1905.02119","author":"Casimiro M.","year":"2019","unstructured":"M. Casimiro , D. Didona , P. Romano , L. Rodrigues , W. Zwanepoel , and D. Garlan . Lynceus: Cost-efficient tuning and provisioning of data analytic jobs. arXiv preprint arXiv:1905.02119 , 2019 . M. Casimiro, D. Didona, P. Romano, L. Rodrigues, W. Zwanepoel, and D. Garlan. Lynceus: Cost-efficient tuning and provisioning of data analytic jobs. arXiv preprint arXiv:1905.02119, 2019."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451125"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541941"},{"key":"e_1_3_2_2_20_1","first-page":"1256","volume-title":"ICML","author":"Denil M.","year":"2013","unstructured":"M. Denil , D. Matheson , and N. Freitas . Consistency of online random forests . In ICML , pages 1256 -- 1264 , 2013 . M. Denil, D. Matheson, and N. Freitas. Consistency of online random forests. In ICML, pages 1256--1264, 2013."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAI.2018.8599304"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687767"},{"key":"e_1_3_2_2_23_1","volume-title":"Tuneful: An online significance-aware configuration tuner for big data analytics. arXiv preprint arXiv:2001.08002","author":"Fekry A.","year":"2020","unstructured":"A. Fekry , L. Carata , T. Pasquier , A. Rice , and A. Hopper . Tuneful: An online significance-aware configuration tuner for big data analytics. arXiv preprint arXiv:2001.08002 , 2020 . A. Fekry, L. Carata, T. Pasquier, A. Rice, and A. Hopper. Tuneful: An online significance-aware configuration tuner for big data analytics. arXiv preprint arXiv:2001.08002, 2020."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168847"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402746"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2038916.2038934"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2018.00058"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00070"},{"key":"e_1_3_2_2_29_1","volume-title":"Scout: An experienced guide to find the best cloud configuration. arXiv preprint arXiv:1803.01296","author":"Hsu C.-J.","year":"2018","unstructured":"C.-J. Hsu , V. Nair , T. Menzies , and V. W. Freeh . Scout: An experienced guide to find the best cloud configuration. arXiv preprint arXiv:1803.01296 , 2018 . C.-J. Hsu, V. Nair, T. Menzies, and V. W. Freeh. Scout: An experienced guide to find the best cloud configuration. arXiv preprint arXiv:1803.01296, 2018."},{"key":"e_1_3_2_2_30_1","first-page":"117","volume-title":"OSDI","author":"Jyothi S. A.","year":"2016","unstructured":"S. A. Jyothi , C. Curino , I. Menache , S. M. Narayanamurthy , A. Tumanov , J. Yaniv , R. Mavlyutov , I. Goiri , S. Krishnan , J. Kulkarni , : Towards automated slos for enterprise clusters . In OSDI , pages 117 -- 134 . USENIX Association , 2016 . S. A. Jyothi, C. Curino, I. Menache, S. M. Narayanamurthy, A. Tumanov, J. Yaniv, R. Mavlyutov, I. Goiri, S. Krishnan, J. Kulkarni, et al. Morpheus: Towards automated slos for enterprise clusters. In OSDI, pages 117--134. USENIX Association, 2016."},{"key":"e_1_3_2_2_31_1","first-page":"759","volume-title":"USENIX ATC","author":"Klimovic A.","year":"2018","unstructured":"A. Klimovic , H. Litz , and C. Kozyrakis . Selecta: Heterogeneous cloud storage configuration for data analytics . In USENIX ATC , pages 759 -- 773 , 2018 . A. Klimovic, H. Litz, and C. Kozyrakis. Selecta: Heterogeneous cloud storage configuration for data analytics. In USENIX ATC, pages 759--773, 2018."},{"key":"e_1_3_2_2_32_1","first-page":"3140","volume-title":"NIPS","author":"Lakshminarayanan B.","year":"2014","unstructured":"B. Lakshminarayanan , D. M. Roy , and Y. W. Teh . Mondrian forests: Efficient online random forests . In NIPS , pages 3140 -- 3148 , 2014 . B. Lakshminarayanan, D. M. Roy, and Y. W. Teh. Mondrian forests: Efficient online random forests. In NIPS, pages 3140--3148, 2014."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387520"},{"key":"e_1_3_2_2_34_1","first-page":"28","volume-title":"Middleware","author":"Mahgoub A.","year":"2017","unstructured":"A. Mahgoub , P. Wood , S. Ganesh , S. Mitra , W. Gerlach , T. Harrison , F. Meyer , A. Grama , S. Bagchi , and S. Chaterji . Rafiki: a middleware for parameter tuning of NoSQL datastores for dynamic metagenomics workloads . In Middleware , pages 28 -- 40 , 2017 . A. Mahgoub, P. Wood, S. Ganesh, S. Mitra, W. Gerlach, T. Harrison, F. Meyer, A. Grama, S. Bagchi, and S. Chaterji. Rafiki: a middleware for parameter tuning of NoSQL datastores for dynamic metagenomics workloads. In Middleware, pages 28--40, 2017."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987566"},{"key":"e_1_3_2_2_36_1","first-page":"1377","volume-title":"NIPS","author":"Roy D. M.","year":"2008","unstructured":"D. M. Roy , Y. W. Teh , The mondrian process . In NIPS , pages 1377 -- 1384 , 2008 . D. M. Roy, Y. W. Teh, et al. The mondrian process. In NIPS, pages 1377--1384, 2008."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457447"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372071"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362716"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2019.00025"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2151021"},{"key":"e_1_3_2_2_42_1","first-page":"363","volume-title":"NSDI","author":"Venkataraman S.","year":"2016","unstructured":"S. Venkataraman , Z. Yang , M. J. Franklin , B. Recht , and I. Stoica . Ernest: Efficient Performance Prediction for Large-Scale Advanced Analytics . In NSDI , pages 363 -- 378 . USENIX Association , 2016 . S. Venkataraman, Z. Yang, M. J. Franklin, B. Recht, and I. Stoica. Ernest: Efficient Performance Prediction for Large-Scale Advanced Analytics. In NSDI, pages 363--378. USENIX Association, 2016."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3131614"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3128605"}],"event":{"name":"SoCC '20: ACM Symposium on Cloud Computing","location":"Virtual Event USA","acronym":"SoCC '20","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 11th ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3419111.3421305","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3419111.3421305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:06Z","timestamp":1750195926000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3419111.3421305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":44,"alternative-id":["10.1145\/3419111.3421305","10.1145\/3419111"],"URL":"https:\/\/doi.org\/10.1145\/3419111.3421305","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}