{"created":"2020-09-13T17:24:22.435475+00:00","id":5340,"links":{},"metadata":{"_buckets":{"deposit":"1cdc22cd-b9b5-4553-a754-587dd68c64f1"},"_deposit":{"created_by":45,"id":"5340","owner":"45","owners":[45],"owners_ext":{"displayname":"","email":"dimennyaung@uit.edu.mm","username":""},"pid":{"revision_id":0,"type":"recid","value":"5340"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/5340","sets":["1582963342780:1596102391527"]},"communities":["uit"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Efficient Checkpoint Interval for Speculative Execution in MapReduce","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"The MapReduce has become popular in big data\nenvironment due to its efficient parallel processing.\nHowever, MapReduce still has the problem from job\ndelay caused by straggling tasks, which prolong job\ncompletion time. In MapReduce framework, although the\nexisting speculative execution mechanism mitigate\nstragglers, its tasks are slower than their original tasks so\nthis makes job completion time get long when straggling\ntasks occur. So, in this paper, a checkpoint mechanism is\nproposed in order to increase the efficiency of speculative\nexecution of MapReduce, and not to prolong job\ncompletion time in case of straggling tasks. However,\nMapReduce produces too much intermediate data; as a\nresult, checkpoint of every intermediate data can still\ndecrease the performance of MapReduce. So, to avoid this\nproblem, the proposed system evaluates checkpoint\ninterval in order to reduce job completion time in case of\nstragglers. Then, the proposed system defines stragglers\nusing LATE scheduler. The proposed checkpoint interval\nis based on five parameters: expected job completion time\nwithout checkpointing, checkpoint overhead time, rework\ntime, down time and restart time. Experimental results\nshow that the proposed system leads to less completion\ntime, rework time and checkpoint overhead."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value_mlt":[{"interim":"MapReduce"},{"interim":"straggling task"},{"interim":"big data"},{"interim":"checkpoint interval"},{"interim":"completion time"}]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2020-09-13"}],"displaytype":"preview","filename":"Efficient Checkpoint Interval for Speculative Execution in MapReduce.pdf","filesize":[{"value":"903 Kb"}],"format":"application/pdf","licensetype":"license_0","url":{"url":"https://meral.edu.mm/record/5340/files/Efficient Checkpoint Interval for Speculative Execution in MapReduce.pdf"},"version_id":"efbe1f6e-00c6-499d-946e-655ecd24c2b3"}]},"item_1583103147082":{"attribute_name":"Conference papers","attribute_value_mlt":[{"subitem_acronym":"ICAIT","subitem_c_date":"1 November, 2018","subitem_conference_title":"International Conference on Advanced Information Technologies","subitem_place":"Yangon, Myanmar","subitem_website":"https://www.uit.edu.mm/icait-2018/"}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Naychi Nway Nway"},{"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":"2018-11-01"},"item_title":"Efficient Checkpoint Interval for Speculative Execution in MapReduce","item_type_id":"21","owner":"45","path":["1596102391527"],"publish_date":"2020-09-13","publish_status":"0","recid":"5340","relation_version_is_last":true,"title":["Efficient Checkpoint Interval for Speculative Execution in MapReduce"],"weko_creator_id":"45","weko_shared_id":-1},"updated":"2021-12-13T03:12:40.178228+00:00"}