{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T03:38:29Z","timestamp":1772595509236,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/bigdata.2016.7840608","type":"proceedings-article","created":{"date-parts":[[2017,2,7]],"date-time":"2017-02-07T21:46:59Z","timestamp":1486504019000},"page":"223-232","source":"Crossref","is-referenced-by-count":12,"title":["Efficient data access strategies for Hadoop and Spark on HPC cluster with heterogeneous storage"],"prefix":"10.1109","author":[{"given":"Nusrat Sharmin","family":"Islam","sequence":"first","affiliation":[]},{"given":"Md.","family":"Wasi-ur-Rahman","sequence":"additional","affiliation":[]},{"given":"Xiaoyi","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Dhabaleswar K. D K","family":"Panda","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Resilient Distributed Datasets: A Fault-tolerant Abstraction for In-memory Cluster Computing","author":"zaharia","year":"2012","journal-title":"Proc USENIX Conf Networked Systems Design and Implementation (NSDI)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502057"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"ref30","article-title":"The Apache Software Foundation. The Apache Hadoop Project","year":"0"},{"key":"ref34","article-title":"Spark: Cluster Computing with Working Sets","author":"zaharia","year":"2010","journal-title":"2nd USENIX Conf on Hot Topics in Cloud Comp"},{"key":"ref10","article-title":"Game-Changer: The Big Data Behind Social Gaming","year":"0","journal-title":"Alex Woodie"},{"key":"ref11","article-title":"Alex Woodie","year":"0","journal-title":"What Pokemon GO Means for Big Data"},{"key":"ref12","article-title":"PACMan: Coordinated Memory Caching for Parallel Jobs","author":"ananthanarayanan","year":"2012","journal-title":"Proc USENIX Conf Networked Systems Design and Implementation (NSDI)"},{"key":"ref13","article-title":"MapReduce: Simplified Data Processing on Large Clusters","author":"dean","year":"2004","journal-title":"Operating Systems Design and Implementation (OSDI)"},{"key":"ref14","article-title":"Hadoop 2.6 Storage Policies","year":"0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600715"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2014.7004235"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2015.161"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.65"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1109\/BigData.2015.7363761","article-title":"Performance Characterization and Acceleration of In-Memory File Systems for Hadoop and Spark Applications on HPC Clusters","author":"islam","year":"2015","journal-title":"2015 IEEE International Conference on Big Data (IEEE BigData)"},{"key":"ref28","article-title":"A Dynamic Caching Mechanism for Hadoop using Memcached","author":"singh","year":"0"},{"key":"ref4","year":"0","journal-title":"Future of Hadoop"},{"key":"ref27","article-title":"HDFS Scalability: The Limits to Growth","author":"shvachko","year":"2010","journal-title":"LOGIN The USENIX Magazine"},{"key":"ref3","year":"0","journal-title":"Cloudera Spark Roadmap"},{"key":"ref6","year":"0","journal-title":"King"},{"key":"ref29","article-title":"The Apache Software Foundation. Centralized Cache Management in HDFS","year":"0"},{"key":"ref5","year":"0","journal-title":"Intel HiBench"},{"key":"ref8","year":"0","journal-title":"Supercell"},{"key":"ref7","year":"0","journal-title":"Memcached High-Performance Distributed Memory Object Caching System"},{"key":"ref2","article-title":"Cloudera: Data access based on Locality and Storage Type","year":"0"},{"key":"ref9","article-title":"The Ohio State Micro Benchmarks","year":"0"},{"key":"ref1","year":"0","journal-title":"Apache Mesos"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2015.79"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.78"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1145\/2670979.2670985","article-title":"Speed Storage for Cluster Computing Frameworks","author":"li","year":"2014","journal-title":"ACM Symposium on Cloud Computing (SOCC)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2597652.2597684"},{"key":"ref23","article-title":"A Comprehensive Study of MapReduce over Lustre for Intermediate Data Placement and Shuffle Strategies on HPC Clusters","author":"rahman","year":"2016","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452045"},{"key":"ref25","article-title":"High-Performance Design of YARN MapReduce on Modern HPC Clusters with Lustre and RDMA","author":"rahman","year":"2015","journal-title":"IEEE 29th InternationalParallel and Distributed Processing Symposium (IPDPS)"}],"event":{"name":"2016 IEEE International Conference on Big Data (Big Data)","location":"Washington DC,USA","start":{"date-parts":[[2016,12,5]]},"end":{"date-parts":[[2016,12,8]]}},"container-title":["2016 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7818133\/7840573\/07840608.pdf?arnumber=7840608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,23]],"date-time":"2022-07-23T19:07:09Z","timestamp":1658603229000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7840608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2016.7840608","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}