{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T15:58:41Z","timestamp":1757779121251},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2012,6,10]],"date-time":"2012-06-10T00:00:00Z","timestamp":1339286400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2012,10]]},"DOI":"10.1007\/s00778-012-0279-5","type":"journal-article","created":{"date-parts":[[2012,6,9]],"date-time":"2012-06-09T06:58:22Z","timestamp":1339225102000},"page":"589-609","source":"Crossref","is-referenced-by-count":15,"title":["On the optimization of schedules for MapReduce workloads in the presence of shared scans"],"prefix":"10.1007","volume":"21","author":[{"given":"Joel","family":"Wolf","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Balmin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepak","family":"Rajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kirsten","family":"Hildrum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Khandekar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sujay","family":"Parekh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun-Lung","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rares","family":"Vernica","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,6,10]]},"reference":[{"key":"279_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Kifer, D., Olston, C.: Scheduling shared scans of large data files. Proc. VLDB Endlow. 958\u2013969 (2008)","DOI":"10.14778\/1453856.1453960"},{"key":"279_CR2","unstructured":"Apache ZooKeeper: http:\/\/hadoop.apache.org\/zookeeper"},{"key":"279_CR3","doi-asserted-by":"crossref","unstructured":"Balmin, A., Kaldewey, T., Tata, S.: Clydesdale: Structured data processing on Hadoop. Proceedings of SIGMOD (2012)","DOI":"10.1145\/2213836.2213938"},{"key":"279_CR4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-00074-8","volume-title":"Scheduling in Computer and Manufacturing Systems","author":"J. Blazewicz","year":"1993","unstructured":"Blazewicz J., Ecker K., Schmidt G., Weglarz J.: Scheduling in Computer and Manufacturing Systems. Springer, New York (1993)"},{"key":"279_CR5","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1023\/B:ANOR.0000030682.25673.c0","volume":"129","author":"J. Blazewicz","year":"2004","unstructured":"Blazewicz J., Kovalyov M., Machowiak M., Trystram D., Weglarz J.: Malleable task scheduling to minimize the makespan. Ann. Oper. Res. 129, 65\u201380 (2004)","journal-title":"Ann. Oper. Res."},{"issue":"2","key":"279_CR6","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/s00778-011-0221-2","volume":"20","author":"G. Candea","year":"2011","unstructured":"Candea G., Polyzotis N., Vingralek R.: Predictable performance and high query concurrency for data. VLDB J. 20(2), 227\u2013248 (2011)","journal-title":"VLDB J."},{"issue":"4","key":"279_CR7","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1137\/0209062","volume":"9","author":"E. Coffman","year":"1980","unstructured":"Coffman E., Garey M., Johnson D., Tarjan R.: Performance bounds for level-oriented two-dimensional packing problems. SIAM J. Comput. 9(4), 808\u2013826 (1980)","journal-title":"SIAM J. Comput."},{"issue":"1","key":"279_CR8","first-page":"107","volume":"51","author":"J. Dean","year":"2008","unstructured":"Dean J., Ghemawat S.: MapReduce: simplified data processing on large clusters. ACM Trans. Comput. Syst. 51(1), 107\u2013113 (2008)","journal-title":"ACM Trans. Comput. Syst."},{"issue":"7","key":"279_CR9","doi-asserted-by":"crossref","first-page":"419","DOI":"10.14778\/1988776.1988778","volume":"4","author":"A. Floratou","year":"2011","unstructured":"Floratou A., Patel J., Shekita E., Tata S.: Column-oriented storage techniques for MapReduce. Proc. VLDB Endow. 4(7), 419\u2013429 (2011)","journal-title":"Proc. VLDB Endow."},{"key":"279_CR10","unstructured":"Hadoop. http:\/\/hadoop.apache.org"},{"key":"279_CR11","doi-asserted-by":"crossref","unstructured":"Harizopoulos, S., Ailamaki, A., Shkapenyuk, V.: QPipe: a simultaneously pipelined relational query. Proceedings of SIGMOD (2005)","DOI":"10.1145\/1066157.1066201"},{"key":"279_CR12","unstructured":"Hunt, P., Konar, M., Junqueira, F., Reed, B.: ZooKeeper: wait-free coordination for internet-scale systems. Proceedings of USENIX (2010)"},{"key":"279_CR13","volume-title":"Resource Allocation Problems","author":"T. Ibaraki","year":"1988","unstructured":"Ibaraki T., Katoh N.: Resource Allocation Problems. MIT Press, Cambridge, MA (1988)"},{"key":"279_CR14","doi-asserted-by":"crossref","unstructured":"Kaldeway, T., Shekita, E., Tata S. Clydesdale: Structured data processing on MapReduce. Proceedings of Extending Database Technology (2012)","DOI":"10.1145\/2247596.2247600"},{"key":"279_CR15","volume-title":"The Art of Computer Programming","author":"D. Knuth","year":"1998","unstructured":"Knuth D.: The Art of Computer Programming. Addison-Wesley, Reading, MA (1998)"},{"key":"279_CR16","doi-asserted-by":"crossref","DOI":"10.1201\/9780203489802","volume-title":"Handbook of Scheduling","author":"J.E. Leung","year":"2004","unstructured":"Leung J.E.: Handbook of Scheduling. Chapman and Hall\/CRC, London (2004)"},{"issue":"1\u20132","key":"279_CR17","doi-asserted-by":"crossref","first-page":"494","DOI":"10.14778\/1920841.1920906","volume":"3","author":"T. Nykiel","year":"2010","unstructured":"Nykiel T., Potamias M., Mishra C., Kollios G., Koudas N.: MRShare: sharing across multiple queries in MapReduce. Proc. VLDB Endow. 3(1\u20132), 494\u2013505 (2010)","journal-title":"Proc. VLDB Endow."},{"key":"279_CR18","unstructured":"O\u2019Neil, P., O\u2019Neil, E., Chen, X.: The Star Schema Benchmark (SSB). http:\/\/www.cs.umb.edu\/poneil\/StarSchemaB.PDF"},{"key":"279_CR19","volume-title":"Scheduling: Theory, Algorithms and Systems","author":"M. Pinedo","year":"1995","unstructured":"Pinedo M.: Scheduling: Theory, Algorithms and Systems. Prentice Hall, Englewood Cliffs, NJ (1995)"},{"key":"279_CR20","doi-asserted-by":"crossref","unstructured":"Qiao, L., Raman, V., Reiss, F., Haas, P., Lohman, G.: Main-memory scan sharing for multi-core CPUS. Proc. VLDB Endow. 610\u2013621 (2008)","DOI":"10.14778\/1453856.1453924"},{"key":"279_CR21","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1137\/S0097539795286831","volume":"28","author":"U. Schwiegelshohn","year":"1999","unstructured":"Schwiegelshohn U., Ludwig W., Wolf J., Turek J., Yu P.: Smart SMART bounds for weighted response time scheduling. SIAM J. Comput. 28, 237\u2013253 (1999)","journal-title":"SIAM J. Comput."},{"key":"279_CR22","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Sarma, J., Jain, N., Shao, Z., Chakka, P., Zhang, N., Anthony, S., Liu, H., Murthy, R.: Hive\u2014a petabyte scale data warehouse using Hadoop. International Conference on Data Engineering (2010)","DOI":"10.1109\/ICDE.2010.5447738"},{"key":"279_CR23","doi-asserted-by":"crossref","unstructured":"Turek, J., Wolf, J., Yu, P.: Approximate algorithms for scheduling parallelizable tasks. Proceedings of SPAA (1992)","DOI":"10.1145\/140901.141909"},{"key":"279_CR24","doi-asserted-by":"crossref","unstructured":"Vernica, R., Balmin, A., Beyer, K., Ercegovac, V.: Adaptive MapReduce using situation-aware mappers. Proceedings of Extending Database Technology (2012)","DOI":"10.1145\/2247596.2247646"},{"key":"279_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X., Sarma, A., Olston, C.,Burns, R.: CoScan: Cooperative scan sharing in the cloud. Proceedings of SOCC (2011)","DOI":"10.1145\/2038916.2038927"},{"key":"279_CR26","doi-asserted-by":"crossref","unstructured":"Wolf, J.L., Rajan, D., Hildrum, K., Khandekar, R., Kumar, V., Parekh, S., Wu, K.-L., Balmin, A.: FLEX: a slot allocation scheduling optimizer for MapReduce workloads. Proceedings of Middleware (2010)","DOI":"10.1007\/978-3-642-16955-7_1"},{"issue":"5","key":"279_CR27","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/69.956097","volume":"13","author":"J.L. Wolf","year":"2001","unstructured":"Wolf J.L., Squillante M.S., Turek J.J., Yu P.S., Sethuraman J.: Scheduling algorithms for the broadcast delivery of digital products. IEEE Trans. Knowl. Data Eng. 13(5), 721\u2013741 (2001)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"279_CR28","unstructured":"Zaharia, M.: Hadoop fair scheduler design document. http:\/\/svn.apache.org\/repos\/asf\/hadoop\/mapreduce\/trunk\/src\/contrib\/fairscheduler\/designdoc\/fair_scheduler_design_doc.pdf"},{"key":"279_CR29","unstructured":"Zaharia, M., Borthakur, D., Sarma, J., Elmeleegy, K., Shenker, S., Stoica, I.: Job scheduling for multi-user MapReduce clusters. Technical Report EECS-2009-55, UC Berkeley Technical Report (2009)"},{"key":"279_CR30","doi-asserted-by":"crossref","unstructured":"Zaharia, M., Borthakur, D., Sarma, J., Elmeleegy, K., Shenker, S., Stoica, I.: Delay scheduling: a simple technique for achieving locality and fairness in cluster scheduling. Proceedings of EuroSys (2010)","DOI":"10.1145\/1755913.1755940"},{"key":"279_CR31","unstructured":"Zukowski, M., H\u00e9man, S., Nes, N., Boncz, P.: Cooperative scans: dynamic bandwidth sharing in a DBMS. Proc. VLDB Endow. 723\u2013734 (2007)"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-012-0279-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-012-0279-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-012-0279-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T04:43:45Z","timestamp":1642394625000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-012-0279-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,10]]},"references-count":31,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2012,10]]}},"alternative-id":["279"],"URL":"https:\/\/doi.org\/10.1007\/s00778-012-0279-5","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,6,10]]}}}