Druid 实时分析架构设计思路—Imply

Druid 实时分析架构设计思路—Imply

ID:39878998

大小:6.56 MB

页数:57页

时间:2019-07-13

Druid 实时分析架构设计思路—Imply_第1页
Druid 实时分析架构设计思路—Imply_第2页
Druid 实时分析架构设计思路—Imply_第3页
Druid 实时分析架构设计思路—Imply_第4页
Druid 实时分析架构设计思路—Imply_第5页
资源描述:

《Druid 实时分析架构设计思路—Imply》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库

1、DRUIDINTERACTIVEEXPLORATORYANALYTICSATSCALEFANGJINYANG·DRUIDCOMMITTEROVERVIEWDEMOSEESOMENEATTHINGSMOTIVATIONWHYDRUID?ARCHITECTUREPICTURESWITHARROWSCOMMUNITYCONTRIBUTETODRUIDTHEPROBLEM‣Arbitraryandinteractiveexplorationoftimeseriesdata•Ad-tech,system/appmetrics,network/websitetrafficanalysis‣Multi-ten

2、ancy:lotsofconcurrentusers‣Scalability:10+TB/day,ad-hocqueriesontrillionsofevents‣Recencymatters!Real-timeanalysis2013DEMOINCASETHEINTERNETDIDN’TWORKPRETENDYOUSAWSOMETHINGCOOLREQUIREMENTS‣Scalable&highlyavailable‣Real-timedataingestion‣Arbitrarydataexplorationwithad-hocqueries‣Sub-secondqueries‣Many

3、concurrentreads2015FINDINGASOLUTION‣LoadallyourdataintoHadoop.Queryit.Done!‣Goodjobguys,let’sgohome2015FINDINGASOLUTIONHadoopInsightEventStreams2015PROBLEMSWITHTHENAIVESOLUTION‣MapReducecanhandlealmosteverydistributedcomputingproblem‣MapReduceoveryourrawdataisflexiblebutslow‣Hadoopisnotoptimizedforqu

4、erylatency‣Tooptimizequeries,weneedaquerylayer2015FINDINGASOLUTIONHadoopHadoop(pre-processingandstorage)QueryLayerInsightEventStreams2015MAKEQUERIESFASTER‣Whattypesofqueriestooptimizefor?•Businessintelligence/OLAP/pivottablesqueries•Aggregations,filters,groupBys2015WHATWETRIEDFINDINGASOLUTIONHadoopHa

5、doop(pre-processingandstorage)RDBMS?InsightEventStreams2015I.RDBMS-THESETUP‣Commonsolutionindatawarehousing:•StarSchema•AggregateTables•QueryCaching2015I.RDBMS-THERESULTS‣Queriesthatwerecached•fast‣Queriesagainstaggregatetables•fasttoacceptable‣Queriesagainstbasefacttable•generallyunacceptable2015I.

6、RDBMS-PERFORMANCENaivebenchmarkscanrate~5.5Mrows/second/core1dayofsummarizedaggregates60M+rows1queryover1week,16cores~5secondsPageloadwith20queriesoveraweeklongtimeofdata2015FINDINGASOLUTIONHadoopNoSQLK/VHadoop(pre-processingandstorage)Stores?InsightEventStreams2015II.NOSQL-THESETUP‣Pre-aggregateall

7、dimensionalcombinations‣StoreresultsinaNoSQLstoreKeyValue1revenue=$1.19tsgenderagerevenue1,Mrevenue=$0.151M18$0.151,Frevenue=$1.041F25$1.031,18revenue=$0.161F18$0.011,25revenue=$1.031,M,18revenue=$0.1

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。