{"created":"2020-08-06T11:27:58.125704+00:00","id":2930,"links":{},"metadata":{"_buckets":{"deposit":"a30e1b93-7141-4f3a-8ee0-8b3d1b3edab9"},"_deposit":{"created_by":45,"id":"2930","owner":"45","owners":[45],"owners_ext":{"displayname":"","email":"dimennyaung@uit.edu.mm","username":""},"pid":{"revision_id":0,"type":"recid","value":"2930"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/2930","sets":["1582963342780:1596102355557"]},"communities":["uit"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Performance-Aware Data Placement Policy for Hadoop Distributed File System","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"Apache Hadoop is an open-source software\nframework for distributed storage and distributed\nprocessing of very large data sets on computer\nclusters built from commodity hardware. The Hadoop\nDistributed File System (HDFS) is the underlying file\nsystem of a Hadoop cluster. The default HDFS data\nplacement strategy works well in homogeneous\ncluster. But it performs poorly in heterogeneous\nclusters because of the heterogeneity of the nodes\ncapabilities. It may cause overload in some\ncomputing nodes and reduce Hadoop performance.\nTherefore, Hadoop Distributed File System (HDFS)\nhas to rely on load balancing utility to balance data\ndistribution. As a result, data can be placed evenly\nacross the Hadoop cluster. But it may cause the\noverhead of transferring unprocessed data from slow\nnodes to fast nodes because each node has different\ncomputing capacity in heterogeneous Hadoop\ncluster. In order to solve these problems, a\ndata/replica placement policy based on storage\nutilization and computing capacity of each data node\nin heterogeneous Hadoop Cluster is proposed. The\nproposed policy tends to reduce the overload of some\ncomputing nodes as well as reduce overhead of data\ntransmission between different computing nodes."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"HDFS"},{"interim":"Data Placement Policy"}]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2020-08-06"}],"displaytype":"preview","filename":"Performance-Aware Data Placement Policy for Hadoop Distributed File System.pdf","filesize":[{"value":"302 Kb"}],"format":"application/pdf","licensetype":"license_0","url":{"url":"https://meral.edu.mm/record/2930/files/Performance-Aware Data Placement Policy for Hadoop Distributed File System.pdf"},"version_id":"931982f3-372c-46ab-bb00-06522be97d4c"}]},"item_1583103147082":{"attribute_name":"Conference papers","attribute_value_mlt":[{"subitem_acronym":"ICCA 2018","subitem_c_date":"22-23 February, 2018","subitem_conference_title":"16th International Conference on Computer Applications","subitem_place":"Sedona Hotel, Yangon, Myanmar","subitem_website":"https://www.ucsy.edu.mm/page228.do"}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Nang Kham Soe"},{"subitem_authors_fullname":"Tin Tin Yee"},{"subitem_authors_fullname":"Ei Chaw Htoon"}]}]},"item_1583108359239":{"attribute_name":"Upload type","attribute_value_mlt":[{"interim":"Publication"}]},"item_1583108428133":{"attribute_name":"Publication type","attribute_value_mlt":[{"interim":"Conference paper"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2018-02-23"},"item_title":"Performance-Aware Data Placement Policy for Hadoop Distributed File System","item_type_id":"21","owner":"45","path":["1596102355557"],"publish_date":"2020-08-06","publish_status":"0","recid":"2930","relation_version_is_last":true,"title":["Performance-Aware Data Placement Policy for Hadoop Distributed File System"],"weko_creator_id":"45","weko_shared_id":-1},"updated":"2022-03-24T23:11:39.833161+00:00"}