{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T14:19:07Z","timestamp":1772374747601,"version":"3.50.1"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T00:00:00Z","timestamp":1466726400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Grid Computing"],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1007\/s10723-016-9371-1","type":"journal-article","created":{"date-parts":[[2016,6,25]],"date-time":"2016-06-25T16:35:04Z","timestamp":1466872504000},"page":"379-405","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Big Data 2.0 Processing Systems: Taxonomy and Open Challenges"],"prefix":"10.1007","volume":"14","author":[{"given":"Fuad","family":"Bajaber","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radwa","family":"Elshawi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omar","family":"Batarfi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulrahman","family":"Altalhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Barnawi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sherif","family":"Sakr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,6,24]]},"reference":[{"key":"9371_CR1","unstructured":"Amplab big data benchmark. https:\/\/amplab.cs.berkeley.edu\/benchmark\/"},{"issue":"12","key":"9371_CR2","first-page":"2050","volume":"8","author":"D Abadi","year":"2015","unstructured":"Abadi, D., Babu, S., Ozcan, F., Pandis, I.: Tutorial: SQL-on-Hadoop Systems. PVLDB 8(12), 2050\u20132061 (2015)","journal-title":"PVLDB"},{"issue":"1","key":"9371_CR3","first-page":"922","volume":"2","author":"A Abouzeid","year":"2009","unstructured":"Abouzeid, A., Bajda-Pawlikowski, K., Abadi, D.J., Rasin, A., Silberschatz, A.: HadoopDB: An Architectural Hybrid of MapReduce and DBMS Technologies for Analytical Workloads. PVLDB 2(1), 922\u2013933 (2009)","journal-title":"PVLDB"},{"issue":"2","key":"9371_CR4","first-page":"1625","volume":"3","author":"A Alexandrov","year":"2010","unstructured":"Alexandrov, A., Battr\u00e9, D., Ewen, S., Heimel, M., Hueske, F., Kao, O., Markl, V., Nijkamp, E., Warneke, D.: Massively Parallel Data Analysis with PACTs on Nephele. PVLDB 3(2), 1625\u20131628 (2010)","journal-title":"PVLDB"},{"issue":"6","key":"9371_CR5","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1007\/s00778-014-0357-y","volume":"23","author":"A Alexandrov","year":"2014","unstructured":"Alexandrov, A., Bergmann, R., Ewen, S., Freytag, J.-C., Hueske, F., Heise, A., Kao, O., Leich, M., Leser, U., Markl, V., Naumann, F., Peters, M., Rheinl\u00e4nder, A., Sax, M.J., Schelter, S., H\u00f6ger, M., Tzoumas, K., Warneke, D.: The Stratosphere platform for big data analytics. VLDB J. 23(6), 939\u2013964 (2014)","journal-title":"VLDB J."},{"key":"9371_CR6","doi-asserted-by":"crossref","unstructured":"Aly, A.M., Sallam, A., Gnanasekaran, B.M., Nguyen-Dinh, L.-V., Aref, W.G., Ouzzani, M., Ghafoor, A.: M3: stream processing on main-memory mapreduce. In: IEEE 28th International Conference on Data Engineering (ICDE 2012), Washington, DC, USA (Arlington, Virginia), 1-5 April, 2012, pp 1253\u20131256 (2012)","DOI":"10.1109\/ICDE.2012.120"},{"key":"9371_CR7","doi-asserted-by":"crossref","unstructured":"Armbrust, M., Xin, R.S., Lian, C., Huai, Y., Liu, D., Bradley, J.K., Meng, X., Kaftan, T., Franklin, M.J., Ghodsi, A., Zaharia, M.: Spark SQL: Relational Data Processing in Spark. In: SIGMOD, pp 1383\u20131394 (2015)","DOI":"10.1145\/2723372.2742797"},{"issue":"2","key":"9371_CR8","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1145\/606272.606299","volume":"46","author":"H Balakrishnan","year":"2003","unstructured":"Balakrishnan, H., Frans Kaashoek, M., Karger, D.R., Morris, R., Stoica, I.: Looking up data in p2p systems. Commun. ACM 46(2), 43\u201348 (2003)","journal-title":"Commun. ACM"},{"key":"9371_CR9","doi-asserted-by":"crossref","unstructured":"Barnawi, A., Batarfi, O., Beheshti, S.-M.-R., Shawi, R.E., Fayoumi, A.G., Nouri, R., Sakr, S.: On Characterizing the Performance of Distributed Graph Computation Platforms. In Performance Characterization and Benchmarking. Traditional to Big Data - 6th TPC Technology Conference, TPCTC 2014, Hangzhou, China, September 1-5, 2014. Revised Selected Papers, 29\u201343 (2014)","DOI":"10.1007\/978-3-319-15350-6_3"},{"issue":"3","key":"9371_CR10","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1007\/s10586-015-0472-6","volume":"18","author":"O Batarfi","year":"2015","unstructured":"Batarfi, O., Shawi, R.E., Fayoumi, A.G., Nouri, R., Beheshti, S.-M.-R., Barnawi, A., Sakr, S.: Large scale graph processing systems: survey and an experimental evaluation. Clust. Comput. 18(3), 1189\u20131213 (2015)","journal-title":"Clust. Comput."},{"key":"9371_CR11","doi-asserted-by":"crossref","unstructured":"Battr\u00e9, D., Ewen, S., Hueske, F., Kao, O., Markl, V., Warneke, D.: Nephele\/PACTs: a programming model and execution framework for web-scale analytical processing. In: SoCC, pp 119\u2013130 (2010)","DOI":"10.1145\/1807128.1807148"},{"key":"9371_CR12","doi-asserted-by":"crossref","unstructured":"Bedini, I., Sakr, S., Theeten, B., Sala, A., Cogan, P.: Modeling performance of a parallel streaming engine: bridging theory and costs. In: ICPE, pp 173\u2013184 (2013)","DOI":"10.1145\/2479871.2479895"},{"key":"9371_CR13","doi-asserted-by":"crossref","unstructured":"Borkar, V.R., Carey, M.J., Grover, R., Onose, N., Vernica, R.: Hyracks: A flexible and extensible foundation for data-intensive computing. In: ICDE, pp 1151\u20131162 (2011)","DOI":"10.1109\/ICDE.2011.5767921"},{"issue":"2","key":"9371_CR14","first-page":"161","volume":"8","author":"Y Bu","year":"2014","unstructured":"Bu, Y., Borkar, V.R., Jia, J., Carey, M.J., Condie, T.: Pregelix: Big(ger) Graph Analytics on a Dataflow Engine. PVLDB 8(2), 161\u2013172 (2014)","journal-title":"PVLDB"},{"issue":"2","key":"9371_CR15","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s00778-012-0269-7","volume":"21","author":"Y Bu","year":"2012","unstructured":"Bu, Y., Howe, B., Balazinska, M., Ernst, M.D.: The HaLoop approach to large-scale iterative data analysis. VLDB J. 21(2), 169\u2013190 (2012)","journal-title":"VLDB J."},{"key":"9371_CR16","doi-asserted-by":"crossref","unstructured":"Chang, L., Wang, Z., Ma, T., Jian, L., Ma, L., Goldshuv, A., Lonergan, L., Cohen, J., Welton, C., Sherry, G., Bhandarkar, M.: HAWQ: a massively parallel processing SQL engine in hadoop. In: SIGMOD, pp 1223\u20131234 (2014)","DOI":"10.1145\/2588555.2595636"},{"issue":"1","key":"9371_CR17","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/s10723-012-9238-z","volume":"11","author":"N Chohan","year":"2013","unstructured":"Chohan, N., Bunch, C., Krintz, C., Canumalla, N.: Cloud platform datastore support. J. Grid Comput. 11(1), 63\u201381 (2013)","journal-title":"J. Grid Comput."},{"key":"9371_CR18","doi-asserted-by":"crossref","unstructured":"Choi, H., Son, J., Yang, H., Ryu, H., Lim, B., Kim, S., Chung, Y.D.: Tajo: A distributed data warehouse system on large clusters. In: ICDE, pp 1320\u20131323 (2013)","DOI":"10.1109\/ICDE.2013.6544934"},{"key":"9371_CR19","volume-title":"Foundations of Actor Semantics. Technical report","author":"WD Clinger","year":"1981","unstructured":"Clinger, W.D.: Foundations of Actor Semantics. Technical report. Cambridge, MA, USA (1981)"},{"key":"9371_CR20","unstructured":"Condie, T., Conway, N., Alvaro, P., Hellerstein, J.M., Elmeleegy, K., Sears, R.: MapReduce Online. In: NSDI, pp 313\u2013328 (2010)"},{"key":"9371_CR21","doi-asserted-by":"crossref","unstructured":"Condie, T., Conway, N., Alvaro, P., Hellerstein, J.M., Gerth, J., Talbot, J., Elmeleegy, K., Sears, R.: Online aggregation and continuous query support in MapReduce. In: SIGMOD Conference, pp 1115\u20131118 (2010)","DOI":"10.1145\/1807167.1807295"},{"issue":"1","key":"9371_CR22","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/TNSM.2014.031714.130407","volume":"11","author":"D Dahiphale","year":"2014","unstructured":"Dahiphale, D., Karve, R., Vasilakos, A.V., Liu, H., Yu, Z., Chhajer, A., Wang, J., Wang, C.: An advanced mapreduce: Cloud mapreduce, enhancements and applications. IEEE Trans. Netw. Serv. Manag. 11(1), 101\u2013115 (2014)","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"issue":"1","key":"9371_CR23","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1145\/1629175.1629198","volume":"53","author":"J Dean","year":"2010","unstructured":"Dean, J., Ghemawat, S.: MapReduce: a flexible data processing tool. Commun. ACM 53(1), 72\u201377 (2010)","journal-title":"Commun. ACM"},{"key":"9371_CR24","unstructured":"Dean, J., Ghemawa, S.: MapReduce: Simplified Data Processing on Large Clusters. In: OSDI, pp 137\u2013150 (2004)"},{"key":"9371_CR25","doi-asserted-by":"crossref","unstructured":"DeWitt, D.J., Halverson, A., Nehme, R.V., Shankar, S., Aguilar-Saborit, J., Avanes, A., Flasza, M., Gramling, J.: Split query processing in polybase. In: SIGMOD, pp 1255\u20131266 (2013)","DOI":"10.1145\/2463676.2463709"},{"issue":"1","key":"9371_CR26","first-page":"518","volume":"3","author":"J Dittrich","year":"2010","unstructured":"Dittrich, J., Quian\u00e9-Ruiz, J., Jindal, A., Kargin, Y., Setty, V., Schad, J.: Hadoop++: Making a Yellow Elephant Run Like a Cheetah (Without It Even Noticing). PVLDB 3(1), 518\u2013529 (2010)","journal-title":"PVLDB"},{"key":"9371_CR27","doi-asserted-by":"crossref","unstructured":"Ekanayake, J., Li, H., Zhang, B., Gunarathne, T., Bae, S.-H., Qiu, J., Fox, G.: Twister: a runtime for iterative MapReduce. In: HPDC, pp 810\u2013818 (2010)","DOI":"10.1145\/1851476.1851593"},{"key":"9371_CR28","doi-asserted-by":"crossref","unstructured":"Elghandour, I., Aboulnaga, A.: ReStore: reusing results of MapReduce jobs in pig. In: SIGMOD Conference, pp 701\u2013704 (2012)","DOI":"10.1145\/2213836.2213937"},{"issue":"7","key":"9371_CR29","first-page":"419","volume":"4","author":"A Floratou","year":"2011","unstructured":"Floratou, A., Patel, J.M., Shekita, E.J., Tata, S.: Column-Oriented Storage Techniques for MapReduce. PVLDB 4(7), 419\u2013429 (2011)","journal-title":"PVLDB"},{"issue":"13","key":"9371_CR30","first-page":"1520","volume":"7","author":"VR Gankidi","year":"2014","unstructured":"Gankidi, V.R., Teletia, N., Patel, J.M., Halverson, A., DeWitt, D.J.: Indexing HDFS Data in PDW: Splitting the data from the index. PVLDB 7(13), 1520\u20131528 (2014)","journal-title":"PVLDB"},{"key":"9371_CR31","doi-asserted-by":"crossref","unstructured":"Gedik, B., Andrade, H., Wu, K.-L., Yu, P.S., Doo, M.: SPADE: the system s declarative stream processing engine. In: SIGMOD, pp 1123\u20131134 (2008)","DOI":"10.1145\/1376616.1376729"},{"key":"9371_CR32","doi-asserted-by":"crossref","unstructured":"Ghazal, A., Rabl, T., Hu, M., Raab, F., Poess, M., Crolotte, A., Jacobsen, H.-A.: BigBench: towards an industry standard benchmark for big data analytics. In: SIGMOD, pp 1197\u20131208 (2013)","DOI":"10.1145\/2463676.2463712"},{"key":"9371_CR33","unstructured":"Gonzalez, J.E., Low, Y., Gu, H., Bickson, D., Guestrin, C.: PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs. In: OSDI, pp 17\u201330 (2012)"},{"key":"9371_CR34","unstructured":"Gonzalez, J.E., Xin, R.S., Dave, A., Crankshaw, D., Franklin, M.J., Stoica, I.: GraphX: Graph Processing in a Distributed Dataflow Framework. In: OSDI, pp 599\u2013613 (2014)"},{"issue":"12","key":"9371_CR35","first-page":"1047","volume":"7","author":"M Han","year":"2014","unstructured":"Han, M., Daudjee, K., Ammar, K., \u00d6zsu, M.T., Wang, X., Jin, T.: An Experimental Comparison of Pregel-like Graph Processing Systems. PVLDB 7(12), 1047\u20131058 (2014)","journal-title":"PVLDB"},{"key":"9371_CR36","doi-asserted-by":"crossref","unstructured":"Han, W.-S., Lee, S., Park, K., Lee, J.-H., Kim, M.-S., Kim, J., Yu, H.: TurboGraph: a fast parallel graph engine handling billion-scale graphs in a single PC. In: KDD, pp 77\u201385 (2013)","DOI":"10.1145\/2487575.2487581"},{"key":"9371_CR37","unstructured":"Heise, A., Rheinlnder, A., Leich, U., Leser, U., Naumann, F.: Meteor\/Sopremo: An Extensible Query Language and Operator Model. In: BigData Workshop in conjunection with VLDB (2012)"},{"key":"9371_CR38","doi-asserted-by":"crossref","unstructured":"Huai, Y., Chauhan, A., Gates, A., Hagleitner, G., Hanson, E.N., O\u2019Malley, O., Pandey, J., Yuan, Y., Lee, R., Zhang, X.: Major technical advancements in Apache Hive. In: SIGMOD, pp 1235\u20131246 (2014)","DOI":"10.1145\/2588555.2595630"},{"issue":"9","key":"9371_CR39","first-page":"1299","volume":"23","author":"D Jiang","year":"2011","unstructured":"Jiang, D., Tung, A.K.H., Chen, G.: MAP-JOIN-REDUCE: Toward Scalable and Efficient Data Analysis on Large Clusters. IEEE TKDE 23(9), 1299\u20131311 (2011)","journal-title":"IEEE TKDE"},{"issue":"13","key":"9371_CR40","first-page":"1709","volume":"7","author":"A Khan","year":"2014","unstructured":"Khan, A., Elnikety, S.: Systems for big-graphs. PVLDB 7(13), 1709\u20131710 (2014)","journal-title":"PVLDB"},{"key":"9371_CR41","doi-asserted-by":"crossref","unstructured":"Khayyat, Z., Awara, K., Alonazi, A., Jamjoom, H., Williams, D., Kalnis, P.: Mizan: a system for dynamic load balancing in large-scale graph processing. In: EuroSys, pp 169\u2013182 (2013)","DOI":"10.1145\/2465351.2465369"},{"key":"9371_CR42","unstructured":"Kornacker, M., Behm, A., Bittorf, V., Bobrovytsky, T., Ching, C., Choi, A., Erickson, J., Grund, M., Hecht, D., Jacobs, M., Joshi, I., Kuff, L., Kumar, D., Leblang, A., Li, N., Pandis, I., Robinson, H., Rorke, D., Rus, S., Russell, J., Tsirogiannis, D., Wanderman-Milne, S., Yoder, M.: Impala: A Modern, Open-Source SQL Engine for Hadoop. In: CIDR 2015, Seventh Biennial Conference on Innovative Data Systems Research, Asilomar, CA, USA, January 4-7, 2015, Online Proceedings (2015)"},{"key":"9371_CR43","unstructured":"Kyrola, A., Blelloch, G.E., Guestrin, C.: GraphChi: Large-Scale Graph Computation on Just a PC. In: OSDI, pp 31\u201346 (2012)"},{"key":"9371_CR44","doi-asserted-by":"crossref","unstructured":"Lin, Y., Agrawal, D., Chen, C., Ooi, B.C., Wu, S.: Llama: leveraging columnar storage for scalable join processing in the MapReduce framework. In: SIGMOD Conference, pp 961\u2013972 (2011)","DOI":"10.1145\/1989323.1989424"},{"key":"9371_CR45","doi-asserted-by":"crossref","unstructured":"Loesing, S., Hentschel, M., Kraska, T., Kossmann, D.: Stormy: an elastic and highly available streaming service in the cloud. In: EDBT\/ICDT Workshops, pp 55\u201360 (2012)","DOI":"10.1145\/2320765.2320789"},{"issue":"8","key":"9371_CR46","first-page":"716","volume":"5","author":"Y Low","year":"2012","unstructured":"Low, Y., Gonzalez, J., Kyrola, A., Bickson, D., Guestrin, C., Hellerstein, J.M.: Distributed GraphLab: A Framework for Machine Learning in the Cloud. PVLDB 5(8), 716\u2013727 (2012)","journal-title":"PVLDB"},{"key":"9371_CR47","doi-asserted-by":"crossref","unstructured":"Malewicz, G., Austern, M.H., Bik, A.J.C., Dehnert, J.C., Horn, I., Leiser, N., Czajkowski, G.: Pregel: a system for large-scale graph processing. In: SIGMOD Conference, pp 135\u2013146 (2010)","DOI":"10.1145\/1807167.1807184"},{"issue":"1","key":"9371_CR48","first-page":"330","volume":"3","author":"S Melnik","year":"2010","unstructured":"Melnik, S., Gubarev, A., Long, J.J., Romer, G., Shivakumar, S., Tolton, M., Vassilakis, T.: Dremel: Interactive Analysis of Web-Scale Datasets. PVLDB 3(1), 330\u2013339 (2010)","journal-title":"PVLDB"},{"key":"9371_CR49","doi-asserted-by":"crossref","unstructured":"Neumeyer, L., Robbins, B., Nair, A., Kesari, A.: S4: Distributed Stream Computing Platform. In: ICDMW, pp 170\u2013177 (2010)","DOI":"10.1109\/ICDMW.2010.172"},{"issue":"1","key":"9371_CR50","first-page":"494","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. PVLDB 3(1), 494\u2013505 (2010)","journal-title":"PVLDB"},{"key":"9371_CR51","doi-asserted-by":"crossref","unstructured":"Pavlo, A., Paulson, E., Rasin, A., Abadi, D.J., DeWitt, D.J., Madden, S., Stonebraker, M.: A comparison of approaches to large-scale data analysis. In: SIGMOD, pp 165\u2013178 (2009)","DOI":"10.1145\/1559845.1559865"},{"key":"9371_CR52","doi-asserted-by":"crossref","unstructured":"Saha, B., Shah, H., Seth, S., Vijayaraghavan, G., Murthy, A.C., Curino, C.: Apache Tez: A Unifying Framework for Modeling and Building Data Processing Applications. In: SIGMOD, pp 1357\u20131369 (2015)","DOI":"10.1145\/2723372.2742790"},{"key":"9371_CR53","doi-asserted-by":"crossref","unstructured":"Sakr, S.: GraphREL: A Decomposition-Based and Selectivity-Aware Relational Framework for Processing Sub-graph Queries. In: Database Systems for Advanced Applications, 14th International Conference, DASFAA 2009, Brisbane, Australia, April 21-23, 2009. Proceedings, pp 123\u2013137 (2009)","DOI":"10.1007\/978-3-642-00887-0_11"},{"key":"9371_CR54","doi-asserted-by":"crossref","unstructured":"Sakr, S., Elnikety, S., He, Y.: G-SPARQL: a hybrid engine for querying large attributed graphs. In: 21st ACM International Conference on Information and Knowledge Management, CIKM\u201912, Maui, HI, USA, October 29 - November 02, 2012, pp 335\u2013344 (2012)","DOI":"10.1145\/2396761.2396806"},{"key":"9371_CR55","doi-asserted-by":"crossref","unstructured":"Sakr, S., Gaber, M.M.: editors. Large Scale and Big Data - Processing and Management. Auerbach Publications (2014)","DOI":"10.1201\/b17112"},{"issue":"1","key":"9371_CR56","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/2522968.2522979","volume":"46","author":"S Sakr","year":"2013","unstructured":"Sakr, S., Liu, A., Fayoumi, A.G.: The family of mapreduce and large-scale data processing systems. ACM Comput. Surv. 46(1), 11 (2013)","journal-title":"ACM Comput. Surv."},{"key":"9371_CR57","doi-asserted-by":"crossref","unstructured":"Salihoglu, S., Widom, J.: GPS: a graph processing system. In: SSDBM, p 22 (2013)","DOI":"10.1145\/2484838.2484843"},{"key":"9371_CR58","doi-asserted-by":"crossref","unstructured":"Selinger, P.G., Astrahan, M.M., Chamberlin, D.D., Lorie, R.A., Price, T.G.: Access Path Selection in a Relational Database Management System. In: SIGMOD Conference, pp 23\u201334 (1979)","DOI":"10.1145\/582095.582099"},{"issue":"2","key":"9371_CR59","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/s10723-013-9255-6","volume":"11","author":"J Shamsi","year":"2013","unstructured":"Shamsi, J., Khojaye, M.A., Qasmi, M.A.: Data-intensive cloud computing: Requirements, expectations, challenges, and solutions. J. Grid Comput. 11(2), 281\u2013310 (2013)","journal-title":"J. Grid Comput."},{"key":"9371_CR60","doi-asserted-by":"crossref","unstructured":"Shao, B., Wang, H., Li, Y.: Trinity: a distributed graph engine on a memory cloud. In: SIGMOD, pp 505\u2013516 (2013)","DOI":"10.1145\/2463676.2467799"},{"key":"9371_CR61","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The Hadoop Distributed File System. In: IEEE 26th Symposium on Mass Storage Systems and Technologies, MSST, pp 1\u201310 (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"9371_CR62","doi-asserted-by":"crossref","unstructured":"Sparks, E.R., Talwalkar, A., Smith, V., Kottalam, J., Pan, X., Gonzalez, J.E., Franklin, M.J., Jordan, M.I., Kraska, T.: MLI: An API for Distributed Machine Learning. In: ICDM, pp 1187\u20131192 (2013)","DOI":"10.1109\/ICDM.2013.158"},{"key":"9371_CR63","doi-asserted-by":"crossref","unstructured":"Stutz, P., Bernstein, A., Cohen, W.W.: Signal\/Collect: Graph Algorithms for the (Semantic) Web. In: International Semantic Web Conference (1), pp 764\u2013780 (2010)","DOI":"10.1007\/978-3-642-17746-0_48"},{"key":"9371_CR64","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Shao, Z., Anthony, S., Borthakur, D., Jain, N., Sarma, J.S., Murthy, R., Liu, H.: Data warehousing and analytics infrastructure at facebook. In: SIGMOD, pp 1013\u20131020 (2010)","DOI":"10.1145\/1807167.1807278"},{"issue":"3","key":"9371_CR65","first-page":"193","volume":"7","author":"Y Tian","year":"2013","unstructured":"Tian, Y., Balmin, A., Corsten, S.A., Tatikonda, S., McPherson, J.: From \u201dThink Like a Vertex\u201d to \u201dThink Like a Graph\u201d. PVLDB 7(3), 193\u2013204 (2013)","journal-title":"PVLDB"},{"key":"9371_CR66","doi-asserted-by":"crossref","unstructured":"Tsai, C.W., Lai, C.F., Chao, H.C., Vasilakos, A. V.: Big data analytics: a survey. Journal of Big Data 2(21) (2015)","DOI":"10.1186\/s40537-015-0030-3"},{"issue":"3","key":"9371_CR67","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s10723-013-9265-4","volume":"11","author":"K Vahi","year":"2013","unstructured":"Vahi, K., Harvey, I., Samak, T., Gunter, D.K., Evans, K., Rogers, D.H., Taylor, I.J., Goode, M., Silva, F., Al-Shakarchi, E., Mehta, G., Deelman, E., Jones, A.: A case study into using common real-time workflow monitoring infrastructure for scientific workflows. J. Grid Comput. 11(3), 381\u2013406 (2013)","journal-title":"J. Grid Comput."},{"issue":"8","key":"9371_CR68","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"LG Valiant","year":"1990","unstructured":"Valiant, L.G.: A Bridging Model for Parallel Computation. Commun. ACM 33(8), 103\u2013111 (1990)","journal-title":"Commun. ACM"},{"key":"9371_CR69","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K., Murthy, A.C., Douglas, C., Agarwal, S., Konar, M., Evans, R., Graves, T., Lowe, J., Shah, H., Seth, S., Saha, B., Curino, C., O\u2019Malley, O., Radia, S., Reed, B., Baldeschwieler, E.: Apache Hadoop YARN: yet another resource negotiator. In: ACM Symposium on Cloud Computing, SOCC \u201913, Santa Clara, CA, USA October 1-3, 2013, pp 5:1\u20135:16 (2013)","DOI":"10.1145\/2523616.2523633"},{"issue":"1","key":"9371_CR70","first-page":"31","volume":"37","author":"S Wanderman-Milne","year":"2014","unstructured":"Wanderman-Milne, S., Li, N.: Runtime Code Generation in Cloudera Impala. IEEE Data Eng. Bull. 37(1), 31\u201337 (2014)","journal-title":"IEEE Data Eng. Bull."},{"key":"9371_CR71","unstructured":"White, T.: Hadoop: The Definitive Guide. O\u2019Reilly Media (2012)"},{"key":"9371_CR72","doi-asserted-by":"crossref","unstructured":"Yang, H., Dasdan, A., Hsiao, R., Parker, D.: Map-reduce-merge: simplified relational data processing on large clusters. In: SIGMOD, pp 1029\u20131040 (2007)","DOI":"10.1145\/1247480.1247602"},{"key":"9371_CR73","unstructured":"Zaharia, M., Chowdhury, M. , Franklin, M.J., Shenker, S., Stoica, I.: Spark: Cluster Computing with Working Sets. In: 2nd USENIX Workshop on Hot Topics in Cloud Computing, HotCloud\u201910, Boston, MA, USA, June 22, 2010 (2010)"},{"issue":"1","key":"9371_CR74","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s10723-012-9204-9","volume":"10","author":"Y Zhang","year":"2012","unstructured":"Zhang, Y., Gao, Q., Gao, L., Wang, C.: iMapReduce: A Distributed Computing Framework for Iterative Computation. J. Grid Comput. 10(1), 47\u201368 (2012)","journal-title":"J. Grid Comput."}],"container-title":["Journal of Grid Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-016-9371-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10723-016-9371-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-016-9371-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T22:45:04Z","timestamp":1748990704000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10723-016-9371-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6,24]]},"references-count":74,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,9]]}},"alternative-id":["9371"],"URL":"https:\/\/doi.org\/10.1007\/s10723-016-9371-1","relation":{},"ISSN":["1570-7873","1572-9184"],"issn-type":[{"value":"1570-7873","type":"print"},{"value":"1572-9184","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,6,24]]}}}