谷歌Google与云计算.ppt

上传人:b****2 文档编号:2136943 上传时间:2022-10-27 格式:PPT 页数:32 大小:2.96MB
下载 相关 举报
谷歌Google与云计算.ppt_第1页
第1页 / 共32页
谷歌Google与云计算.ppt_第2页
第2页 / 共32页
谷歌Google与云计算.ppt_第3页
第3页 / 共32页
谷歌Google与云计算.ppt_第4页
第4页 / 共32页
谷歌Google与云计算.ppt_第5页
第5页 / 共32页
点击查看更多>>
下载资源
资源描述

谷歌Google与云计算.ppt

《谷歌Google与云计算.ppt》由会员分享,可在线阅读,更多相关《谷歌Google与云计算.ppt(32页珍藏版)》请在冰豆网上搜索。

谷歌Google与云计算.ppt

GoogleandCloudComputingGoogle与云计算王咏刚王咏刚Google资深工程师AgendaTheInternet:

FromHardwaretoCommunityTheInnovation:

AComputingCloudBreakthroughsforCloudComputingGoogleAppsforCloudComputingGoogleInfrastructureforCloudComputingTheInternetFromHardwaretoCommunityTheInternet:

FromHardwaretoCommunityMySpaceFacebook开心网校内网WhatDoTodaysUsersWant?

AccessibilityAccessfromanywhereandfrommultipledevicesShareabilityMakesharingaseasyascreatingandsavingFreedomUsersdontwanttheirdataheldhostageSimplicityEasy-to-learn,easy-to-useSecurityTrustthatdatawillnotbelostorseenbyunwantedparties6TheInnovationAComputingCloudCloudComputing7AttributesofCloudComputing8DatastoredonthecloudSoftware&servicesonthecloud-AccessviawebbrowserBasedonstandardsandprotocols-Linux,AJAX,LAMP,etc.AccessiblefromanydeviceHardwareCentricSoftwareCentricServiceCentricPersonalPCClientServerCloudComputing9BreakthroughsforCloudComputingBreakthroughsforCloudComputing10User-Centric1Task-Centric2Powerful3Intelligent4Affordable5Programmable6UserCentricDatastoredinthe“Cloud”Datafollowsyou&yourdevicesDataaccessibleanywhereDatacanbesharedwithothersmusicpreferencesmapsnewscontactsmessagesmailinglistsphotoe-mailscalendarphonenumbersinvestmentsExample:

GMailJustawebbrowserandyouraccountwithpassword!

Onceyoulogin,thedeviceis“yours”.Datastoredonremoteserversinthe“cloud”(withlargecapacity)Beijing,ontravelSanFrancisco,MondayHome,WednesdayUseGoogleDocstoSolveaTaskAccessyourdocsfromanywhereChatwithothersinrealtimeChangesinstantlyappeartoothercollaboratorsTask=“Teacherscreatingadepartmentalcurriculum”CommunicationTaskEmail,Chat,Contacts,ChatHistoryTask:

CollaborateonSpreadsheetCommunicateChatwithotherseditingthespreadsheetTask:

CollaborateonSpreadsheetCollaborateInviteotherstocollaborateonthespreadsheetTask:

CollaborateonSpreadsheetPublishInviteotherstoviewthespreadsheetYoucanalsoeasilyorganizeallyourcommontasksCloudComputingisPowerful:

ItcandowhatnoPCcandoIsGoogleSearchfasterthansearchinWindows/Outlook/Word?

AndGoogleSearchmustbemuchharder.Howmuchstoragedoesittaketostoreallofthewebpages?

100Bpages*10Kperpage=1000Tdisk!

CloudcomputinghasatitsdisposalEssentiallyinfiniteamountofdiskEssentiallyinfiniteamountofcomputation(Assumingtheycanbeparallelized)Example:

GoogleSearchWebPageSearchUniversalSearchW1stGeneration:

eraofsinglesearchnotdiverse2ndGeneration:

eraofverticalsearchtoocomplex3rdGeneration:

aneraofUniversalSearchABCDEFromverticalsearchtouniversalsearchABCDEIntegrationofuserexperienceUniversalSearchExampleUniversalSearchExampleCloudComputingInfrastructure25GFSArchitectureGoogle48%MSN19%Yahoo33%Filesbrokenintochunks(typically64MB)MastermanagesmetadataDatatransfershappendirectlybetweenclients/chunkserversClientClientClientReplicasMastersGFSMasterGFSMasterC0C1C2C5Chunkserver1C0C2C5ChunkserverNC1C3C5Chunkserver2ClientClientClientClientClientClientTypicalCluster26SchedulingmastersGFSchunkserverSchedulerslaveLinuxMachine1Userapp2Userapp1GFSmasterLockserviceGFSchunkserverSchedulerslaveLinuxMachineNUserapp3Userapp2Userapp1GFSchunkserverSchedulerslaveLinuxMachine2Userapp3MapReduce27Morespecifically28Programmerspecifiestwoprimarymethods:

map(k,v)*reduce(k,*)*Allvwithsamekarereducedtogether,inorder.Usuallyalsospecify:

partition(k,totalpartitions)-partitionforkoftenasimplehashofthekeyallowsreduceoperationsfordifferentktobeparallelized29BigTableDistributedmulti-levelmapWithaninterestingdatamodelFault-tolerant,persistentScalableThousandsofserversTerabytesofin-memorydataPetabyteofdisk-baseddataMillionsofreads/writespersecond,efficientscansSelf-managingServerscanbeadded/removeddynamicallyServersadjusttoloadimbalance30BigTable:

BasicDataModelDistributedmulti-dimensionalsparsemap(row,column,timestamp)cellcontentsGoodmatchformostofourapplications“”ROWSCOLUMNSTIMESTAMPS“contents”BigTable:

SystemArchitectureClusterSchedulingMasterhandlesfailover,monitoringGFSholdstabletdata,logsLockserviceholdsmetadata,handlesmaster-electionBigtabletabletserverservesdataBigtabletabletserverservesdataBigtabletabletserverservesdataBigtablemasterperformsmetadataops,loadbalancingBigtablecellBigtableclientBigtableclientlibraryOpen()ThanksQ&A

展开阅读全文
相关资源
猜你喜欢
相关搜索

当前位置:首页 > 考试认证 > IT认证

copyright@ 2008-2022 冰豆网网站版权所有

经营许可证编号:鄂ICP备2022015515号-1