{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:27:46Z","timestamp":1729664866901,"version":"3.28.0"},"reference-count":69,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1109\/icde.2015.7113417","type":"proceedings-article","created":{"date-parts":[[2015,6,3]],"date-time":"2015-06-03T15:23:28Z","timestamp":1433345008000},"page":"1523-1526","source":"Crossref","is-referenced-by-count":4,"title":["Blind men and an elephant coalescing open-source, academic, and industrial perspectives on BigData"],"prefix":"10.1109","author":[{"given":"Chris","family":"Douglas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlo","family":"Curino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213840"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920908"},{"journal-title":"Hadoop The Definitive Guide","year":"2009","author":"white","key":"ref33"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1145\/2670979.2670981","article-title":"Reservation-based scheduling: If you're late don't blame us!","author":"curino","year":"2014","journal-title":"SOCC"},{"key":"ref31","article-title":"Dominant resource fairness: fair allocation of multiple resource types","author":"ghodsi","year":"2011","journal-title":"NSDI"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1145\/1272998.1273005","article-title":"Dryad: distributed data-parallel programs from sequential building blocks","author":"isard","year":"2007","journal-title":"SIGOPS"},{"key":"ref37","article-title":"Reining in the outliers in map-reduce clusters using mantri","author":"ananthanarayanan","year":"2010","journal-title":"OSDI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391242"},{"key":"ref35","article-title":"Mapreduce online","author":"condie","year":"2010","journal-title":"NSDI"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s00778-012-0269-7","article-title":"The HaLoop approach to large-scale iterative data analysis","volume":"21","author":"bu","year":"2012","journal-title":"The VLDB Journal"},{"year":"0","key":"ref60","article-title":"Hadoop Capacity Scheduler"},{"key":"ref62","article-title":"Apollo: scalable and coordinated scheduling for cloud-scale computing","author":"boutin","year":"2014","journal-title":"OSDI"},{"year":"0","key":"ref61","article-title":"RM should dynamically schedule containers based on utilization of currently allocated containers"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522716"},{"year":"0","key":"ref28","article-title":"Apache Falcon"},{"year":"0","key":"ref64","article-title":"Extend yarn to support distributed scheduling"},{"year":"0","key":"ref27","article-title":"Apache Ranger"},{"key":"ref65","article-title":"Spark: Cluster computing with working sets","author":"zaharia","year":"0","journal-title":"HotCloud"},{"key":"ref66","article-title":"Differential dataflow","author":"mcsherry","year":"2013","journal-title":"CIDR"},{"key":"ref29","article-title":"Zookeeper: Wait-free coordination for internet-scale systems","author":"hunt","year":"0","journal-title":"USENIX ATC 2010"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.14778\/2212351.2212354"},{"journal-title":"Giraph Apache project","year":"2014","key":"ref68"},{"key":"ref69","first-page":"1","article-title":"Tachyon: Reliable, memory speed storage for cluster computing frameworks","author":"li","year":"2014","journal-title":"Proceedings of the ACM Symposium on Cloud Computing"},{"key":"ref2","article-title":"Hdfs architecture guide","author":"borthakur","year":"2008","journal-title":"Apache Hadoop Project"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/945449.945450"},{"journal-title":"Presto developer community","article-title":"Presto: Distributed sql query engine for big data","year":"2014","key":"ref20"},{"year":"0","key":"ref22","article-title":"Create a new Optimized Row Columnar file format for Hive"},{"year":"0","key":"ref21","article-title":"Implement insert, update, and delete in Hive with full ACID support"},{"journal-title":"Calcite Apache incubator project","year":"2014","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920886"},{"year":"0","key":"ref26","article-title":"Apache Sentry"},{"year":"0","key":"ref25","article-title":"Apache Knox"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213934"},{"key":"ref51","article-title":"Tajo: A distributed data warehouse system on large clusters","author":"choi","year":"2013","journal-title":"ICDE"},{"year":"0","key":"ref59","article-title":"Hadoop Fair Scheduler"},{"year":"0","key":"ref58","article-title":"Apache Slider"},{"journal-title":"Apache Oozie Workflow Scheduler for Hadoop","year":"0","key":"ref57"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.1992.183180"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03422-0_7"},{"journal-title":"Kylin developer community","article-title":"Kylin: Extreme olap engine for big data","year":"2014","key":"ref54"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1089\/big.2013.0011"},{"year":"0","key":"ref52","article-title":"Apache Phoenix"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465386"},{"key":"ref11","article-title":"Mesos: A platform for fine-grained resource sharing in the data center","author":"hindman","year":"2011","journal-title":"NSDI"},{"key":"ref40","article-title":"Hadoop acceleration through network levitated merge","author":"wang","year":"2011","journal-title":"SC"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/10968987_3","article-title":"Slurm: Simple linux utility for resource management","author":"yoo","year":"2003","journal-title":"Job Scheduling Strategies for Parallel Processing"},{"key":"ref13","article-title":"Condor: a distributed job scheduler","author":"tannenbaum","year":"2001","journal-title":"Beowulf Cluster Computing With Linux"},{"year":"0","key":"ref14","article-title":"Maui Scheduler Open Cluster Software"},{"key":"ref15","article-title":"Torque resource manager","author":"staples","year":"2006","journal-title":"IEEE SC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1629175.1629197"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687731"},{"key":"ref18","article-title":"Asterixdb: A scalable, open source bdms","author":"altwaijry","year":"2014","journal-title":"PVLDB"},{"article-title":"Impala: A modern, open-source sql engine for hadoop","year":"2015","author":"kornacker","key":"ref19"},{"key":"ref4","article-title":"Architecture of next generation apache hadoop mapreduce framework","author":"murthy","year":"2011","journal-title":"Tech rep Apache Hadoop Tech Rep"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"ref5","article-title":"Hive - a warehousing solution over a map-reduce framework","author":"thusoo","year":"2009","journal-title":"PVLDB"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom.2010.39"},{"year":"0","key":"ref49","article-title":"Apache Lens"},{"journal-title":"Under the Hood Scheduling MapReduce jobs more efficiently with Corona","article-title":"Facebook Engineering","year":"2012","key":"ref9"},{"year":"0","key":"ref46","article-title":"Apache Tez"},{"journal-title":"Twill Apache incubator project","year":"2014","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2595630"},{"journal-title":"Concurrent Inc","article-title":"Cascading: Application platform for enterprise big data","year":"2014","key":"ref47"},{"key":"ref42","article-title":"Scope: Parallel databases meet mapreduce","volume":"21","author":"zhou","year":"0","journal-title":"VLDB Journal"},{"key":"ref41","article-title":"Jaql: A scripting language for large scale semistructured data analysis","author":"beyer","year":"2011","journal-title":"PVLDB"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.14778\/2536274.2536318"},{"key":"ref43","article-title":"Disk-locality in datacenter computing considered irrelevant","author":"ananthanarayanan","year":"2011","journal-title":"HOTOS"}],"event":{"name":"2015 IEEE 31st International Conference on Data Engineering (ICDE)","start":{"date-parts":[[2015,4,13]]},"location":"Seoul, South Korea","end":{"date-parts":[[2015,4,17]]}},"container-title":["2015 IEEE 31st International Conference on Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7109453\/7113253\/07113417.pdf?arnumber=7113417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T17:08:54Z","timestamp":1652202534000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7113417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,4]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/icde.2015.7113417","relation":{},"subject":[],"published":{"date-parts":[[2015,4]]}}}