{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T23:11:25Z","timestamp":1768345885164,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,19]]},"DOI":"10.1145\/3772052.3772214","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T16:19:00Z","timestamp":1768321140000},"page":"867-880","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Balancing Fairness and Performance in Multi-User Spark Workloads with Dynamic Scheduling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7076-619X","authenticated-orcid":false,"given":"D\u0101vis","family":"Ka\u017eemaks","sequence":"first","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6999-7297","authenticated-orcid":false,"given":"Laurens","family":"Versluis","sequence":"additional","affiliation":[{"name":"ASML, Veldhoven, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7038-165X","authenticated-orcid":false,"given":"Burcu Kulahcioglu","family":"Ozkan","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9143-3984","authenticated-orcid":false,"given":"J\u00e9r\u00e9mie","family":"Decouchant","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.comnet.2019.05.020","article-title":"Analysis of the age of data in data backup systems","volume":"160","author":"Saxena A.","year":"2019","unstructured":"A. Saxena, D. Claeys, H. Bruneel, and J. Walraevens. \u201cAnalysis of the age of data in data backup systems\u201d. In: Computer Networks 160 (2019), pp. 41\u201350.","journal-title":"Computer Networks"},{"key":"e_1_3_2_1_2_1","first-page":"3780","volume-title":"2023 IEEE 39th International Conference on Data Engineering (ICDE).","author":"Tang S.","year":"2023","unstructured":"S. Tang, B. He, C. Yu, Y. Li, and K. Li. \u201cA Survey on Spark Ecosystem: Big Data Processing Infrastructure, Machine Learning, and Applications (Extended abstract)\u201d. In: 2023 IEEE 39th International Conference on Data Engineering (ICDE). 2023, pp. 3779\u20133780."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. SIGMOD '15","author":"Armbrust M.","unstructured":"M. Armbrust, R. S. Xin, C. Lian, Y. Huai, D. Liu, J. K. Bradley, X. Meng, T. Kaftan, M. J. Franklin, A. Ghodsi, and M. Zaharia. \u201cSpark SQL: Relational Data Processing in Spark\u201d. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. SIGMOD '15. Melbourne, Victoria, Australia: Association for Computing Machinery, 2015, pp. 1383\u20131394."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2957754"},{"key":"e_1_3_2_1_5_1","first-page":"652","volume-title":"2018 18th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID).","author":"Wang G.","year":"2018","unstructured":"G. Wang, J. Xu, R. Liu, and S. Huang. \u201cA Hard Real-time Scheduler for Spark on YARN\u201d. In: 2018 18th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). 2018, pp. 645\u2013652."},{"key":"e_1_3_2_1_6_1","first-page":"639","volume-title":"2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS).","author":"Chen W.","year":"2018","unstructured":"W. Chen, A. Pi, S. Wang, and X. Zhou. \u201cCharacterizing Scheduling Delay for Low-Latency Data Analytics Workloads\u201d. In: 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 2018, pp. 630\u2013639."},{"key":"e_1_3_2_1_7_1","first-page":"9","volume-title":"IEEE INFOCOM 2017 - IEEE Conference on Computer Communications.","author":"Chen L.","year":"2017","unstructured":"L. Chen, S. Liu, B. Li, and B. Li. \u201cScheduling jobs across geo-distributed datacenters with max-min fairness\u201d. In: IEEE INFOCOM 2017 - IEEE Conference on Computer Communications. 2017, pp. 1\u20139."},{"key":"e_1_3_2_1_8_1","first-page":"9","volume-title":"IEEE INFOCOM 2017 - IEEE Conference on Computer Communications.","author":"Chen C.","year":"2017","unstructured":"C. Chen, W. Wang, S. Zhang, and B. Li. \u201cCluster fair queueing: Speeding up data-parallel jobs with delay guarantees\u201d. In: IEEE INFOCOM 2017 - IEEE Conference on Computer Communications. 2017, pp. 1\u20139."},{"key":"e_1_3_2_1_9_1","article-title":"Clustering-based multi-objective optimization considering fairness for multi-workflow scheduling on clouds","author":"Li F.","year":"2024","unstructured":"F. Li, W. J. Tan, M. G. Seok, and W. Cai. \u201cClustering-based multi-objective optimization considering fairness for multi-workflow scheduling on clouds\u201d. In: J. Parallel Distrib. Comput. 194.C (Dec. 2024).","journal-title":"J. Parallel Distrib. Comput. 194.C"},{"key":"e_1_3_2_1_10_1","first-page":"862","volume-title":"2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing.","author":"Quang B. T.","year":"2015","unstructured":"B. T. Quang, J.-S. Kim, S. Rho, S. Kim, S. Kim, S. Hwang, E. Medernach, and V. Breton. \u201cA Comparative Analysis of Scheduling Mechanisms for Virtual Screening Workflow in a Shared Resource Environment\u201d. In: 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing. 2015, pp. 853\u2013862."},{"issue":"14","key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1002\/cpe.3303","article-title":"Controlling fairness and task granularity in distributed, online, non-clairvoyant workflow executions","volume":"26","author":"da Silva R. Ferreira","year":"2014","unstructured":"R. Ferreira da Silva, T. Glatard, and F. Desprez. \u201cControlling fairness and task granularity in distributed, online, non-clairvoyant workflow executions\u201d. In: Concurrency and Computation: Practice and Experience 26.14 (2014), pp. 2347\u20132366.","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"e_1_3_2_1_12_1","first-page":"341","volume-title":"2018 18th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID).","author":"Ilyushkin A.","year":"2018","unstructured":"A. Ilyushkin and D. Epema. \u201cThe Impact of Task Runtime Estimate Accuracy on Scheduling Workloads of Workflows\u201d. In: 2018 18th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). 2018, pp. 331\u2013341."},{"key":"e_1_3_2_1_13_1","first-page":"1","article-title":"A novel cloud workflow scheduling algorithm based on stable matching game theory","volume":"77","author":"Pan Z.-h. JIA, L.","year":"2021","unstructured":"Z.-h. JIA, L. Pan, X. Liu, and X.-j. Li. \u201cA novel cloud workflow scheduling algorithm based on stable matching game theory\u201d. In: The Journal of Supercomputing 77 (Oct. 2021), pp. 1\u201328.","journal-title":"The Journal of Supercomputing"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2015.2396056"},{"key":"e_1_3_2_1_15_1","first-page":"559","volume-title":"2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).","author":"Chen C.","year":"2017","unstructured":"C. Chen, W. Wang, and B. Li. \u201cSpeculative Slot Reservation: Enforcing Service Isolation for Dependent Data-Parallel Computations\u201d. In: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). 2017, pp. 549\u2013559."},{"key":"e_1_3_2_1_16_1","volume-title":"Workflow Trace Archive Google trace. https:\/\/zenodo.org\/record\/3254540. Zenodo","year":"2019","unstructured":"Google. Workflow Trace Archive Google trace. https:\/\/zenodo.org\/record\/3254540. Zenodo. June 2019."},{"key":"e_1_3_2_1_17_1","volume-title":"Balancing Fairness and Performance in Multi-User Spark Workloads with Dynamic Scheduling (extended version)","author":"Ka\u017eemaks D.","year":"2025","unstructured":"D. Ka\u017eemaks, L. Versluis, B. K. Ozkan, and J. Decouchant. Balancing Fairness and Performance in Multi-User Spark Workloads with Dynamic Scheduling (extended version). 2025.arXiv: 2510.15485 [cs.DC]."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/90.234856"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2016.127"},{"key":"e_1_3_2_1_20_1","first-page":"616","volume-title":"Proceedings of the 15th IEEE\/ACM International Symposium on Cluster, Cloud, and Grid Computing. CCGRID '15. Shenzhen","author":"Ilyushkin A.","year":"2015","unstructured":"A. Ilyushkin, B. Ghit, and D. Epema. \u201cScheduling workloads of workflows with unknown task runtimes\u201d. In: Proceedings of the 15th IEEE\/ACM International Symposium on Cluster, Cloud, and Grid Computing. CCGRID '15. Shenzhen, China: IEEE Press, 2015, pp. 606\u2013616."},{"key":"e_1_3_2_1_21_1","first-page":"512","volume-title":"IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.","author":"Chen C.","year":"2018","unstructured":"C. Chen, W. Wang, and B. Li. \u201cPerformance-Aware Fair Scheduling: Exploiting Demand Elasticity of Data Analytics Jobs\u201d. In: IEEE INFOCOM 2018 - IEEE Conference on Computer Communications. 2018, pp. 504\u2013512."},{"key":"e_1_3_2_1_22_1","unstructured":"J. Wilkes. Google cluster-usage traces v3. Technical Report. Posted at https:\/\/github.com\/google\/cluster-data\/blob\/master\/ClusterData2019.md. Mountain View CA USA: Google Inc. Apr. 2020."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2984821"},{"key":"e_1_3_2_1_24_1","first-page":"74","volume-title":"Proceedings of the 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. PPoPP '09","author":"Li T.","year":"2009","unstructured":"T. Li, D. Baumberger, and S. Hahn. \u201cEfficient and scalable multiprocessor fair scheduling using distributed weighted round-robin\u201d. In: Proceedings of the 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. PPoPP '09. Raleigh, NC, USA: Association for Computing Machinery, 2009, pp. 65\u201374."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/35043.35047"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","DOI":"10.1109\/INFCOM.2002.1019322","volume-title":"Proceedings. Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.","volume":"2","author":"Tassiulas L.","year":"2002","unstructured":"L. Tassiulas and S. Sarkar. \u201cMaxmin fair scheduling in wireless networks\u201d. In: Proceedings. Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies. Vol. 2. 2002, 763\u2013772 vol.2."},{"key":"e_1_3_2_1_27_1","first-page":"279","volume-title":"Mobile WiMAX.","author":"Ahmadi S.","year":"2011","unstructured":"S. Ahmadi. \u201cChapter 6 - The IEEE 802.16m Medium Access Control Common Part Sub-layer (Part I)\u201d. In: Mobile WiMAX. Oxford: Academic Press, 2011, pp. 169\u2013279."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2846234"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1987.1096782"},{"key":"e_1_3_2_1_30_1","first-page":"1162","volume-title":"2023 8th International Conference on Computer and Communication Systems (ICCCS).","author":"Zhao L.","year":"2023","unstructured":"L. Zhao. \u201cA Two-Level Multi-task Fair Allocation Mechanism in Cloud Computing\u201d. In: 2023 8th International Conference on Computer and Communication Systems (ICCCS). 2023, pp. 1158\u20131162."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2018.2866421"},{"key":"e_1_3_2_1_33_1","first-page":"578","volume-title":"2020 20th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID).","author":"Cadorel E.","year":"2020","unstructured":"E. Cadorel, H. Coullon, and J.-M. Menaud. \u201cOnline Multi-User Workflow Scheduling Algorithm for Fairness and Energy Optimization\u201d. In: 2020 20th IEEE\/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID). 2020, pp. 569\u2013578."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.future.2015.08.009","article-title":"Static scheduling of multiple workflows with soft deadlines in non-dedicated heterogeneous environments","author":"Bochenina K.","year":"2016","unstructured":"K. Bochenina, N. Butakov, and A. Boukhanovsky. \u201cStatic scheduling of multiple workflows with soft deadlines in non-dedicated heterogeneous environments\u201d. In: Future Gener. Comput. Syst. 55.C (Feb. 2016), pp. 51\u201361.","journal-title":"Future Gener. Comput. Syst. 55.C"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","DOI":"10.1007\/s11227-018-2604-2","article-title":"Fair multiple-workflow scheduling with different quality-of-service goals","volume":"75","author":"Rezaeian A.","year":"2019","unstructured":"A. Rezaeian, M. Naghibzadeh, and D. Epema. \u201cFair multiple-workflow scheduling with different quality-of-service goals\u201d. In: The Journal of Supercomputing 75 (Feb. 2019).","journal-title":"The Journal of Supercomputing"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.88"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.jpdc.2016.06.013","article-title":"Fattened backfilling","author":"G\u00f3mez-Mart\u00edn C.","year":"2016","unstructured":"C. G\u00f3mez-Mart\u00edn, M. A. Vega-Rodr\u00edguez, and J.-L. Gonz\u00e1lez-S\u00e1nchez. \u201cFattened backfilling\u201d. In: J. Parallel Distrib. Comput. 97.C (Nov. 2016), pp. 69\u201377.","journal-title":"J. Parallel Distrib. Comput. 97.C"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536219"},{"key":"e_1_3_2_1_39_1","first-page":"124","volume-title":"2019 IEEE 35th International Conference on Data Engineering Workshops (ICDEW).","author":"Al-Sayeh H.","year":"2019","unstructured":"H. Al-Sayeh and K.-U. Sattler. \u201cGray Box Modeling Methodology for Runtime Prediction of Apache Spark Jobs\u201d. In: 2019 IEEE 35th International Conference on Data Engineering Workshops (ICDEW). 2019, pp. 117\u2013124."},{"key":"e_1_3_2_1_40_1","first-page":"8","volume-title":"2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS).","author":"Gulino A.","year":"2020","unstructured":"A. Gulino, A. Canakoglu, S. Ceri, and D. Ardagna. \u201cPerformance Prediction for Data-driven Workflows on Apache Spark\u201d. In: 2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS). 2020, pp. 1\u20138."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350269"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"K. Wang and M. M. H. Khan. \u201cPerformance Prediction for Apache Spark Platform\u201d. In: 2015 IEEE 17th International Conference on High Performance Computing and Communications 2015 IEEE 7th International Symposium on Cyberspace Safety and Security and 2015 IEEE 12th International Conference on Embedded Software and Systems. 2015 pp. 166\u2013173.","DOI":"10.1109\/HPCC-CSS-ICESS.2015.246"},{"key":"e_1_3_2_1_43_1","first-page":"431","volume-title":"2016 IEEE 9th International Conference on Cloud Computing (CLOUD).","author":"Wang K.","year":"2016","unstructured":"K. Wang, M. M. H. Khan, N. Nguyen, and S. Gokhale. \u201cModeling Interference for Apache Spark Jobs\u201d. In: 2016 IEEE 9th International Conference on Cloud Computing (CLOUD). 2016, pp. 423\u2013431."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/2556549.2556553"},{"key":"e_1_3_2_1_45_1","first-page":"378","volume-title":"Proceedings of the 13th Usenix Conference on Networked Systems Design and Implementation. NSDI'16. Santa Clara, CA: USENIX Association","author":"Venkataraman S.","year":"2016","unstructured":"S. Venkataraman, Z. Yang, M. Franklin, B. Recht, and I. Stoica. \u201cErnest: efficient performance prediction for large-scale advanced analytics\u201d. In: Proceedings of the 13th Usenix Conference on Networked Systems Design and Implementation. NSDI'16. Santa Clara, CA: USENIX Association, 2016, pp. 363\u2013378."}],"event":{"name":"SoCC '25: ACM Symposium on Cloud Computing","location":"Online USA","acronym":"SoCC '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2025 ACM Symposium on Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772052.3772214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T16:24:01Z","timestamp":1768321441000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772052.3772214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":45,"alternative-id":["10.1145\/3772052.3772214","10.1145\/3772052"],"URL":"https:\/\/doi.org\/10.1145\/3772052.3772214","relation":{},"subject":[],"published":{"date-parts":[[2025,11,19]]},"assertion":[{"value":"2026-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}