AsterixDB大数据管理系统中合并策略的优化

2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI) Pub Date : 2016-10-01 DOI:10.1109/IIKI.2016.29

Jie Zhang, Zhiyuan Li, Yidou You, R. Huang, Jin Liu, Xu Chen

{"title":"AsterixDB大数据管理系统中合并策略的优化","authors":"Jie Zhang, Zhiyuan Li, Yidou You, R. Huang, Jin Liu, Xu Chen","doi":"10.1109/IIKI.2016.29","DOIUrl":null,"url":null,"abstract":"AsterixDB Big Data Management System isone of the non-relational databases, developed and researched by researcher in UC Irvine, UC Riverside, andUC San Diego. One of the basic storage structures of AsterixDB is a log structured merge tree, and the log structured merge tree cannot get away from merging operations. When we research in this project closely, we foundthat a better merge policy helps improve the CURD performance of log structured merge tree in a great level. The existing merging policies show a lot of drawbackswhen data size gets bigger and bigger. Our method aimsat optimizing merge policy utilizing a new scheduler–Level Scheduler which was proposed in [6]. Experimentsshow that our merge algorithm is much more efficient.","PeriodicalId":371106,"journal":{"name":"2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optimization of Merge Policy in AsterixDB Big Data Management System\",\"authors\":\"Jie Zhang, Zhiyuan Li, Yidou You, R. Huang, Jin Liu, Xu Chen\",\"doi\":\"10.1109/IIKI.2016.29\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"AsterixDB Big Data Management System isone of the non-relational databases, developed and researched by researcher in UC Irvine, UC Riverside, andUC San Diego. One of the basic storage structures of AsterixDB is a log structured merge tree, and the log structured merge tree cannot get away from merging operations. When we research in this project closely, we foundthat a better merge policy helps improve the CURD performance of log structured merge tree in a great level. The existing merging policies show a lot of drawbackswhen data size gets bigger and bigger. Our method aimsat optimizing merge policy utilizing a new scheduler–Level Scheduler which was proposed in [6]. Experimentsshow that our merge algorithm is much more efficient.\",\"PeriodicalId\":371106,\"journal\":{\"name\":\"2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IIKI.2016.29\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IIKI.2016.29","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

AsterixDB大数据管理系统是非关系型数据库之一，由加州大学欧文分校、加州大学河滨分校和加州大学圣地亚哥分校的研究人员开发和研究。AsterixDB的基本存储结构之一是日志结构的合并树，日志结构的合并树不能脱离合并操作。通过对该项目的深入研究，我们发现一个更好的合并策略可以在很大程度上提高日志结构合并树的CURD性能。当数据量越来越大时，现有的合并策略显示出很多缺点。我们的方法旨在利用[6]中提出的一种新的调度器级调度器来优化合并策略。实验表明，我们的合并算法效率更高。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Optimization of Merge Policy in AsterixDB Big Data Management System

AsterixDB Big Data Management System isone of the non-relational databases, developed and researched by researcher in UC Irvine, UC Riverside, andUC San Diego. One of the basic storage structures of AsterixDB is a log structured merge tree, and the log structured merge tree cannot get away from merging operations. When we research in this project closely, we foundthat a better merge policy helps improve the CURD performance of log structured merge tree in a great level. The existing merging policies show a lot of drawbackswhen data size gets bigger and bigger. Our method aimsat optimizing merge policy utilizing a new scheduler–Level Scheduler which was proposed in [6]. Experimentsshow that our merge algorithm is much more efficient.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2016 International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)

自引率

0.00%

发文量