{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T00:01:23Z","timestamp":1780358483071,"version":"3.54.1"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/bigdata.2017.8258209","type":"proceedings-article","created":{"date-parts":[[2018,1,15]],"date-time":"2018-01-15T22:47:28Z","timestamp":1516056448000},"page":"2508-2517","source":"Crossref","is-referenced-by-count":13,"title":["Understanding and improving disk-based intermediate data caching in Spark"],"prefix":"10.1109","author":[{"given":"Kaihui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusuke","family":"Tanimura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hidemoto","family":"Nakada","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirotaka","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"axboe","year":"2006","journal-title":"Fio (Flexible I\/O Tester)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3584"},{"key":"ref12","article-title":"Neutrino: Revisiting Memory Caching for Iterative Data Analytics","author":"xu","year":"2016","journal-title":"8th USENIX Workshop on Hot Topics in Storage and File Systems (Hot-Storage 16)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.105"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.14778\/2831360.2831365"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2907294.2907310"},{"key":"ref16","article-title":"Tachyon: Memory Throughput I\/O for Cluster Computing Frameworks","author":"li","year":"2013","journal-title":"Large-Scale Distributed Systems and Middleware (LADIS"},{"key":"ref17","first-page":"1","article-title":"Tachyon: Reliable, Memory Speed Storage for Cluster Computing Frameworks","author":"li","year":"2014","journal-title":"Proceeding SOCC'14 Proceedings of the ACM Symposium on Cloud Computing"},{"key":"ref4","author":"xin","year":"2015","journal-title":"Project Tungsten Bringing Apache Spark Closer to Bare Metal"},{"key":"ref3","first-page":"1","article-title":"MapReduce: Simplified Data Processing on Large Clusters","author":"dean","year":"2004","journal-title":"Proceedings of the 6th USENIX Symposium on Operating Systems Design and Implementation (OSDI'04)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797"},{"key":"ref5","author":"armbrust","year":"2015","journal-title":"Deep dive into spark SQL's catalyst optimizer"},{"key":"ref8","article-title":"HiBench Suite","year":"2017","journal-title":"Intel-Hadoop"},{"key":"ref7","first-page":"1235","article-title":"MLlib: Machine Learning in Apache Spark","volume":"17","author":"meng","year":"2016","journal-title":"Machine Learning Research"},{"key":"ref2","article-title":"Apache Hadoop","year":"2006","journal-title":"Apache Software Foundation"},{"key":"ref1","first-page":"15","article-title":"Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing","author":"zaharia","year":"2012","journal-title":"Proceedings of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI '12)"},{"key":"ref9","article-title":"Project Tungsten (SPARK-7075)","year":"2015","journal-title":"Apache Software Foundation"}],"event":{"name":"2017 IEEE International Conference on Big Data (Big Data)","location":"Boston, MA","start":{"date-parts":[[2017,12,11]]},"end":{"date-parts":[[2017,12,14]]}},"container-title":["2017 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8241556\/8257893\/08258209.pdf?arnumber=8258209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,28]],"date-time":"2018-02-28T20:36:16Z","timestamp":1519850176000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8258209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/bigdata.2017.8258209","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}