{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T23:00:24Z","timestamp":1777158024725,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1145\/3722212.3724443","type":"proceedings-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T09:01:44Z","timestamp":1750150904000},"page":"662-674","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Managed Resource Scaling in Amazon EMR"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5189-0203","authenticated-orcid":false,"given":"Vishal","family":"Vyas","sequence":"first","affiliation":[{"name":"Amazon Web Services, East Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1431-2272","authenticated-orcid":false,"given":"Andrei","family":"Paduroiu","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9494-6435","authenticated-orcid":false,"given":"Srikanth","family":"Kandula","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2216-2442","authenticated-orcid":false,"given":"Hari Ohm Prasath","family":"Rajagopal","sequence":"additional","affiliation":[{"name":"Amazon Web Services, East Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3699-0855","authenticated-orcid":false,"given":"Mukesh","family":"Punhani","sequence":"additional","affiliation":[{"name":"Amazon Web Services, East Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0882-7733","authenticated-orcid":false,"given":"Marco","family":"Manzo","sequence":"additional","affiliation":[{"name":"Amazon Web Services, East Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2664-8027","authenticated-orcid":false,"given":"Ankur","family":"Goyal","sequence":"additional","affiliation":[{"name":"Amazon Web Services, East Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4928-711X","authenticated-orcid":false,"given":"Santosh","family":"Chandrachood","sequence":"additional","affiliation":[{"name":"Amazon Web Services, East Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7991-8713","authenticated-orcid":false,"given":"Rick","family":"Sears","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Arlington, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5208-6639","authenticated-orcid":false,"given":"Joseph","family":"Marques","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9477-1986","authenticated-orcid":false,"given":"Sushant","family":"Majithia","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Redmond, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, and Ramachandran Ramjee. 2024. Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). USENIX Association, Santa Clara, CA, 117--134. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/agrawal"},{"key":"e_1_3_2_1_2_1","volume-title":"SaaS Lens: AWS Well-Architected Framework. https:\/\/docs.aws.amazon.com\/pdfs\/wellarchitected\/latest\/saas-lens\/wellarchitected-saas-lens.pdf. Accessed","year":"2024","unstructured":"Amazon. 2023. SaaS Lens: AWS Well-Architected Framework. https:\/\/docs.aws.amazon.com\/pdfs\/wellarchitected\/latest\/saas-lens\/wellarchitected-saas-lens.pdf. Accessed November 1, 2024."},{"key":"e_1_3_2_1_3_1","volume-title":"Accessed","year":"2024","unstructured":"Amazon. 2024a. Amazon Elastic Kubernetes Service. https:\/\/aws.amazon.com\/eks. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_4_1","volume-title":"Accessed","year":"2024","unstructured":"Amazon. 2024b. Amazon EMR archive of release notes. https:\/\/docs.aws.amazon.com\/emr\/latest\/ReleaseGuide\/emr-whatsnew-history.html. Accessed October 15, 2024."},{"key":"e_1_3_2_1_5_1","volume-title":"Accessed","year":"2024","unstructured":"Amazon. 2024c. Amazon Machine Images in Amazon EC2. https:\/\/docs.aws.amazon.com\/AWSEC2\/latest\/UserGuide\/AMIs.html. Accessed November 12, 2024."},{"key":"e_1_3_2_1_6_1","volume-title":"Accessed","year":"2024","unstructured":"Amazon. 2024 d. Big Data Platform -- Amazon EMR - AWS. https:\/\/aws.amazon.com\/emr. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_7_1","volume-title":"Accessed","year":"2024","unstructured":"Amazon. 2024 e. Cloud Compute Capacity -- Amazon EC2 - AWS. https:\/\/aws.amazon.com\/ec2. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_8_1","volume-title":"Accessed","year":"2024","unstructured":"Amazon. 2024 f. CPU options for Amazon EC2 instances. https:\/\/docs.aws.amazon.com\/AWSEC2\/latest\/UserGuide\/instance-optimize-cpu.html. Accessed November 12, 2024."},{"key":"e_1_3_2_1_9_1","volume-title":"Accessed","year":"2024","unstructured":"Amazon. 2024 g. Open-Source Big Data Analytics | Amazon EMR Serverless | Amazon Web Services. https:\/\/aws.amazon.com\/emr\/serverless. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1924943.1924962"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685825"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--1--4419--7997--1_35"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168847"},{"key":"e_1_3_2_1_16_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024a. Apache Flink. https:\/\/flink.apache.org\/. Accessed: October 18, 2024."},{"key":"e_1_3_2_1_17_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024b. Apache Hadoop YARN. https:\/\/hadoop.apache.org\/docs\/stable\/hadoop-yarn\/hadoop-yarn-site\/YARN.html. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_18_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024c. Apache Hive. https:\/\/hive.apache.org. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_19_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024 d. Apache Iceberg. https:\/\/iceberg.apache.org. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_20_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024 e. Apache Spark. https:\/\/spark.apache.org. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_21_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024 f. Apache Spark. https:\/\/spark.apache.org\/docs\/latest\/job-scheduling.html. Accessed: November 15, 2024."},{"key":"e_1_3_2_1_22_1","volume-title":"2024 g. Hadoop: Capacity Scheduler. https:\/\/hadoop.apache.org\/docs\/current\/hadoop-yarn\/hadoop-yarn-site\/CapacityScheduler.html. Accessed","author":"Foundation Apache Software","year":"2025","unstructured":"Apache Software Foundation. 2024 g. Hadoop: Capacity Scheduler. https:\/\/hadoop.apache.org\/docs\/current\/hadoop-yarn\/hadoop-yarn-site\/CapacityScheduler.html. Accessed: April 7, 2025."},{"key":"e_1_3_2_1_23_1","volume-title":"2024 h. Hadoop: Fair Scheduler. https:\/\/hadoop.apache.org\/docs\/stable\/hadoop-yarn\/hadoop-yarn-site\/FairScheduler.html. Accessed","author":"Foundation Apache Software","year":"2025","unstructured":"Apache Software Foundation. 2024 h. Hadoop: Fair Scheduler. https:\/\/hadoop.apache.org\/docs\/stable\/hadoop-yarn\/hadoop-yarn-site\/FairScheduler.html. Accessed: April 7, 2025."},{"key":"e_1_3_2_1_24_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024 i. HDFS Architecture. https:\/\/hadoop.apache.org\/docs\/current\/hadoop-project-dist\/hadoop-hdfs\/HdfsDesign.html. Accessed: October 16, 2024."},{"key":"e_1_3_2_1_25_1","volume-title":"Accessed","author":"Foundation Apache Software","year":"2024","unstructured":"Apache Software Foundation. 2024 j. Spark Structured Streaming. https:\/\/spark.apache.org\/streaming. Accessed: October 16, 2024."},{"key":"e_1_3_2_1_26_1","volume-title":"Accessed","author":"Foundation Presto","year":"2024","unstructured":"Presto Foundation. 2024 k. Presto: Free, Open-Source SQL Query Engine for Any Data. https:\/\/prestodb.io\/. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_27_1","volume-title":"Accessed","author":"Foundation Trino Software","year":"2024","unstructured":"Trino Software Foundation. 2024 l. Trino | Distributed SQL query engine for big data. https:\/\/trino.io. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation","author":"Ghodsi Ali","year":"2011","unstructured":"Ali Ghodsi, Matei Zaharia, Benjamin Hindman, Andy Konwinski, Scott Shenker, and Ion Stoica. 2011. Dominant resource fairness: fair allocation of multiple resource types. In Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation (Boston, MA) (NSDI'11). USENIX Association, USA, 323--336."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"e_1_3_2_1_30_1","volume-title":"Morpheus: Towards Automated SLOs for Enterprise Clusters. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Jyothi Sangeetha Abdu","year":"2016","unstructured":"Sangeetha Abdu Jyothi, Carlo Curino, Ishai Menache, Shravan Matthur Narayanamurthy, Alexey Tumanov, Jonathan Yaniv, Ruslan Mavlyutov, Inigo Goiri, Subru Krishnan, Janardhan Kulkarni, and Sriram Rao. 2016. Morpheus: Towards Automated SLOs for Enterprise Clusters. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). USENIX Association, Savannah, GA, 117--134. https:\/\/www.usenix.org\/conference\/osdi16\/technical-sessions\/presentation\/jyothi"},{"key":"e_1_3_2_1_31_1","volume-title":"50th International Conference on Very Large Databases. VLDB Endowment","author":"K\u00f6nig Arnd Christian","unstructured":"Arnd Christian K\u00f6nig, Yi Shan, Karan Newatia, Luke Marshall, and Vivek Narasayya. 2023. Solver-In-The-Loop Cluster Resource Management for Database-as-a-Service. In 50th International Conference on Very Large Databases. VLDB Endowment, Inc. https:\/\/www.microsoft.com\/en-us\/research\/publication\/solver-in-the-loop-cluster-resource-management-for-database-as-a-service\/"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626246.3653394"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00060"},{"key":"e_1_3_2_1_34_1","unstructured":"Abhishek Sinha Joseph Marques Srinivas Addanki and Vishal Vyas. 2020. Introducing Amazon EMR Managed Scaling -- Automatically Resize Clusters to Lower Cost. https:\/\/aws.amazon.com\/blogs\/big-data\/introducing-amazon-emr-managed-scaling-automatically-resize-clusters-to-lower-cost\/. Accessed October 16 2024."},{"key":"e_1_3_2_1_35_1","volume-title":"Accessed","author":"TPC.","year":"2021","unstructured":"TPC. 2021. TPC Benchmark DS. https:\/\/www.tpc.org\/TPC_Documents_Current_Versions\/pdf\/TPC-DS_v3.2.0.pdf. Accessed: October 15, 2024."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901355"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI'12)","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI'12). USENIX Association, 15--28."}],"event":{"name":"SIGMOD\/PODS '25: International Conference on Management of Data","location":"Berlin Germany","acronym":"SIGMOD\/PODS '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Companion of the 2025 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3722212.3724443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:38:03Z","timestamp":1757543883000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3722212.3724443"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":37,"alternative-id":["10.1145\/3722212.3724443","10.1145\/3722212"],"URL":"https:\/\/doi.org\/10.1145\/3722212.3724443","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]},"assertion":[{"value":"2025-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}