{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:29:18Z","timestamp":1767338958806,"version":"3.44.0"},"reference-count":36,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2018,1,28]],"date-time":"2018-01-28T00:00:00Z","timestamp":1517097600000},"content-version":"am","delay-in-days":392,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1561041","1564647"],"award-info":[{"award-number":["1561041","1564647"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Parallel Computing"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1016\/j.parco.2016.10.004","type":"journal-article","created":{"date-parts":[[2016,10,10]],"date-time":"2016-10-10T11:49:45Z","timestamp":1476100185000},"page":"68-82","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":13,"special_numbering":"C","title":["FARMS: Efficient mapreduce speculation for failure recovery in short jobs"],"prefix":"10.1016","volume":"61","author":[{"given":"Huansong","family":"Fu","sequence":"first","affiliation":[]},{"given":"Haiquan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Weikuan","family":"Yu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"unstructured":"Apache Hadoop Nextgen Mapreduce (yarn), (http:\/\/hadoop.apache.org\/docs\/r2.3.0\/hadoop-yarn\/hadoop-yarn-site\/YARN.html).","key":"10.1016\/j.parco.2016.10.004_bib0001"},{"unstructured":"Apache Hadoop Project, (http:\/\/hadoop.apache.org\/).","key":"10.1016\/j.parco.2016.10.004_bib0002"},{"key":"10.1016\/j.parco.2016.10.004_bib0003","series-title":"NSDI","first-page":"185","article-title":"Effective straggler mitigation: attack of the clones.","volume":"13","author":"Ananthanarayanan","year":"2013"},{"key":"10.1016\/j.parco.2016.10.004_sbref0002","series-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation","article-title":"Pacman: coordinated memory caching for parallel jobs","author":"Ananthanarayanan","year":"2012"},{"key":"10.1016\/j.parco.2016.10.004_bib0005","article-title":"Grass: trimming stragglers in approximation analytics","author":"Ananthanarayanan","year":"2014","journal-title":"Proc. of the 11th USENIX NSDI"},{"key":"10.1016\/j.parco.2016.10.004_bib0006","series-title":"Proceedings of the 9th USENIX Conference on Operating systems Design and Implementation","first-page":"1","article-title":"Reining in the outliers in map-reduce clusters using mantri","author":"Ananthanarayanan","year":"2010"},{"key":"10.1016\/j.parco.2016.10.004_bib0007","series-title":"Proceedings of the 4th annual Symposium on Cloud Computing","first-page":"20","article-title":"Scale-up vs scale-out for hadoop: time to rethink?","author":"Appuswamy","year":"2013"},{"issue":"1","key":"10.1016\/j.parco.2016.10.004_bib0008","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1145\/1672308.1672325","article-title":"Understanding data center traffic characteristics","volume":"40","author":"Benson","year":"2010","journal-title":"ACM SIGCOMM Comput. Commun. Rev."},{"issue":"12","key":"10.1016\/j.parco.2016.10.004_bib0009","doi-asserted-by":"crossref","first-page":"1802","DOI":"10.14778\/2367502.2367519","article-title":"Interactive analytical processing in big data systems: a cross-industry study of mapreduce workloads","volume":"5","author":"Chen","year":"2012","journal-title":"Proc. VLDB Endowment"},{"key":"10.1016\/j.parco.2016.10.004_bib0010","series-title":"Proceedings of the 2015 USENIX Conference on Usenix Annual Technical Conference","first-page":"31","article-title":"Tiered replication: a cost-effective alternative to full cluster geo-replication","author":"Cidon","year":"2015"},{"key":"10.1016\/j.parco.2016.10.004_sbref0009","series-title":"Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation","article-title":"Mapreduce online","author":"Condie","year":"2010"},{"key":"10.1016\/j.parco.2016.10.004_sbref0010","series-title":"PACT","article-title":"Experiences with mapreduce, an abstraction for large-scale computation","volume":"vol. 6","author":"Dean","year":"2006"},{"key":"10.1016\/j.parco.2016.10.004_bib0013","series-title":"Proceedings of the 6th Symposium on Operating System Design and Implementation","first-page":"137","article-title":"Mapreduce: simplified data processing on large clusters","author":"Dean","year":"2004"},{"issue":"1","key":"10.1016\/j.parco.2016.10.004_bib0014","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","article-title":"Mapreduce: simplified data processing on large clusters","volume":"51","author":"Dean","year":"2008","journal-title":"Commun. ACM"},{"key":"10.1016\/j.parco.2016.10.004_bib0015","series-title":"Parallel and Distributed Processing Symposium, 2014 IEEE 28th International","first-page":"962","article-title":"Rcmp: enabling efficient recomputation based failure resilience for big data analytics","author":"Dinu","year":"2014"},{"key":"10.1016\/j.parco.2016.10.004_bib0016","series-title":"Proceedings of the 21st International Symposium on High-Performance Parallel and Distributed Computing","first-page":"187","article-title":"Understanding the effects and implications of compute node related failures in hadoop","author":"Dinu","year":"2012"},{"issue":"11","key":"10.1016\/j.parco.2016.10.004_bib0017","doi-asserted-by":"crossref","first-page":"985","DOI":"10.14778\/2536222.2536225","article-title":"Piranha: optimizing short jobs in Hadoop","volume":"6","author":"Elmeleegy","year":"2013","journal-title":"Proc. VLDB Endowment"},{"key":"10.1016\/j.parco.2016.10.004_bib0018","series-title":"Proceedings of the 2015 International Workshop on Data-Intensive Scalable Computing Systems","first-page":"7","article-title":"A case study of mapreduce speculation for failure recovery","author":"Fu","year":"2015"},{"key":"10.1016\/j.parco.2016.10.004_bib0019","series-title":"Proceedings of the ACM Symposium on Cloud Computing","first-page":"1","article-title":"What bugs live in the cloud? A study of 3000+ issues in cloud systems","author":"Gunawi","year":"2014"},{"key":"10.1016\/j.parco.2016.10.004_bib0020","series-title":"FAST","first-page":"1","article-title":"Eio: error handling is occasionally correct.","volume":"8","author":"Gunawi","year":"2008"},{"key":"10.1016\/j.parco.2016.10.004_bib0021","series-title":"New Frontiers in Information and Software as Services","first-page":"209","article-title":"The hibench benchmark suite: characterization of the mapreduce-based data analysis","author":"Huang","year":"2011"},{"key":"10.1016\/j.parco.2016.10.004_bib0022","series-title":"ACM SIGOPS Operating Systems Review","first-page":"59","article-title":"Dryad: distributed data-parallel programs from sequential building blocks","volume":"vol. 41","author":"Isard","year":"2007"},{"key":"10.1016\/j.parco.2016.10.004_bib0023","series-title":"Cluster, Cloud and Grid Computing (CCGrid), 2010 10th IEEE\/ACM International Conference on","first-page":"94","article-title":"An analysis of traces from a production mapreduce cluster","author":"Kavulya","year":"2010"},{"key":"10.1016\/j.parco.2016.10.004_bib0024","series-title":"Proc. USENIX ATC","article-title":"Gestalt: fast, unified fault localization for networked systems","author":"Mysore","year":"2014"},{"key":"10.1016\/j.parco.2016.10.004_bib0025","series-title":"Proceedings of the 2011 IEEE 27th International Conference on Data Engineering","first-page":"589","article-title":"Rafting mapreduce: fast recovery on the raft","author":"Quiane-Ruiz","year":"2011"},{"key":"10.1016\/j.parco.2016.10.004_bib0026","series-title":"Proceedings of the Third ACM Symposium on Cloud Computing","first-page":"7","article-title":"Heterogeneity and dynamicity of clouds at scale: Google trace analysis","author":"Reiss","year":"2012"},{"key":"10.1016\/j.parco.2016.10.004_bib0027","series-title":"Mass Storage Systems and Technologies (MSST), 2010 IEEE 26th Symposium on","first-page":"1","article-title":"The Hadoop distributed file system","author":"Shvachko","year":"2010"},{"key":"10.1016\/j.parco.2016.10.004_bib0028","series-title":"Proceedings of the 12th ACM SIGMETRICS\/PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","first-page":"5","article-title":"Delay tails in mapreduce scheduling","author":"Tan","year":"2012"},{"key":"10.1016\/j.parco.2016.10.004_bib0029","series-title":"Proceedings of the 4th Annual Symposium on Cloud Computing","first-page":"5:1","article-title":"Apache Hadoop yarn: yet another resource negotiator","author":"Vavilapalli","year":"2013"},{"key":"10.1016\/j.parco.2016.10.004_bib0030","series-title":"Proceedings of the 1st ACM symposium on Cloud computing","first-page":"193","article-title":"Characterizing cloud computing hardware reliability","author":"Vishwanath","year":"2010"},{"key":"10.1016\/j.parco.2016.10.004_sbref0029","series-title":"Proceedings of the 2nd USENIX conference on Hot topics in cloud computing","article-title":"Distributed systems meet economics: pricing in the cloud","author":"Wang","year":"2010"},{"key":"10.1016\/j.parco.2016.10.004_bib0032","series-title":"Proceedings of the 10th International Conference on Autonomic Computing","article-title":"Preemptive reducetask scheduling for fair and fast job completion","author":"Wang","year":"2013"},{"year":"2009","author":"White","series-title":"Hadoop: The Definitive Guide","key":"10.1016\/j.parco.2016.10.004_bib0033"},{"key":"10.1016\/j.parco.2016.10.004_bib0034","series-title":"29th IEEE International Parallel & Distributed Processing Symposium (IEEE IPDPS 2015), Hyderabad, India","article-title":"Cracking down MapReduce failure amplification through analytics logging and migration","author":"Wang","year":"2015"},{"key":"10.1016\/j.parco.2016.10.004_bib0035","series-title":"Proceedings of the 11th Symposium on Operating Systems Design and Implementation (OSDI)","first-page":"249","article-title":"Simple testing can prevent most critical failures: an analysis of production failures in distributed data-intensive systems","author":"Yuan","year":"2014"},{"key":"10.1016\/j.parco.2016.10.004_bib0036","series-title":"Proceedings of the 8th USENIX Conference on Operating Systems Design and Implementation","first-page":"29","article-title":"Improving mapreduce performance in heterogeneous environments","author":"Zaharia","year":"2008"}],"container-title":["Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819116301077?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819116301077?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T05:30:55Z","timestamp":1759123855000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167819116301077"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1]]},"references-count":36,"alternative-id":["S0167819116301077"],"URL":"https:\/\/doi.org\/10.1016\/j.parco.2016.10.004","relation":{},"ISSN":["0167-8191"],"issn-type":[{"type":"print","value":"0167-8191"}],"subject":[],"published":{"date-parts":[[2017,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FARMS: Efficient mapreduce speculation for failure recovery in short jobs","name":"articletitle","label":"Article Title"},{"value":"Parallel Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.parco.2016.10.004","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2016 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}