Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ......

12
EOSC-hub receives funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 777536. eosc-hub.eu @EOSC_eu Daniele Spiga INFN ([email protected] ) on behalf of CMS Collaboration and DODAS Team. Exploiting private and commercial clouds to generate on-demand CMS computing facilities with DODAS

Transcript of Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ......

Page 1: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

EOSC-hubreceivesfundingfromtheEuropeanUnion’sHorizon2020researchandinnovationprogrammeundergrantagreementNo.777536.

eosc-hub.eu@EOSC_eu

DanieleSpigaINFN([email protected])onbehalfofCMSCollaborationandDODASTeam.

Exploitingprivateandcommercialcloudstogenerateon-demandCMScomputingfacilities

withDODAS

Page 2: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 2

Outline

DanieleSpiga

•  IntroductiontoDODAS– ArchitecturalPillars&HighLevelOverview

•  OpportunisticcomputingwithDODASinCMS– PublicandPrivateclouds

•  Dataprocessing:Cachingmechanism•  MachineLearningasaService:anewusecase•  Conclusions

Page 3: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 3

 DynamicOnDemandAnalysisService:DODAS

  PlatformasaServicetoolwhichaimistoguaranteedeploymentofcomplexandintricatesetupon“anycloudprovider”withalmostzeroeffort.  Allowstoinstantiateon-demandcontainerbasedclustertoexecutesoftwareapplications

DODASisaThematicServiceunderEOSC-hubHorizon2020EUproject.

  InitiallydevelopedasanINDIGO-DataCloudusecasesbasedonCMSworkflow.

DODASinanutshell

DanieleSpiga

Opportunisticcomputing:Temporarilyavailableforaspecifictask,userorgroup.

ExtensionofexistingFacilityManagepeaksofusage

BatchSystemasaServiceHTCondorbatchSystem

ExploitationofMachineLearningasaService

MulticloudclusterdeploymentHarvestdispersedresources(PaaSlevelfederation)

Page 4: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 4

Thepillars

DanieleSpiga

ResourcesAbstractionTOSCAtodescribesoftwareapplicationsanddependenciesInfastructureManagerasconnectorwithunderlyingIaaSes

AutomationAnsibleforsoftwareandapplicationsetupMesos/MarathontomanageresourceandorchestrateCluestoautomatehorizontalscalability

Multi-cloudsupportINDIGO-PaaSOrchestratortodealwithmultipleheterogeneousCloudinfrastructures

Seetalk:

Beyon

dX.509:Tok

en-based

Authe

nticationan

dAu

thorizationforH

EP

Federatedauthentication

INDIGO-IdentityAccessManagementtomanageJWT,OpenIDConnect,SAML2.0,LDAP,Local(Username/Passwd);Identityharmonizationetc

Page 5: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 5

Puttingeverythingtogether

DanieleSpiga

5

HomeIdP

AuthN

DODASUser

IAMPaaSOrchestrator

SubmitTOSCA

IM

PrivateCloud PublicCloud

Marathon

Provsioning,Setup,Configurat

ion Provsioning,Setup,Configuration

MasterMasterMasterSlave

Executor

Executor

ExecutorSoftware

ApplicationSoftwareApplication

Slave

Executor

Executor

Executor

MarathonMasterMasterMaster

Slave

Executor

Executor

Executor

Slave

Executor

Executor

Executor

DataAnalysts

SoftwareApplication SoftwareApplication

SoftwareApplication

SoftwareApplication

PaaS

IaaS

Page 6: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 6

AndhowallofthisintegrateswithCMSHTCondorGlobalpool

DanieleSpiga

CMSPhysicists

SquidProxy

CVMFS

CVMFS

CVMFS

Auto-RegisterandGETjobs

Master

LoadBalancer

SlaveSlave

Slave

HTCondor

HTCondorHTCondor

HTCondor

HTCondor

CMSDistributedStorages

ü  CompletelytransparenttoCMSphysicistsü  Seamlesslyintegratingtheglobalinfrastructure

CertCache

DATAI/O

DODASephemeralsite

TokenTranslation

X.509

OpenIDConnect

SeeTalk:

ExploringGlid

einW

MSan

dHT

Cond

or

scalab

ilityfron

tiersfo

ranexpa

nding

CMSGloba

lPoo

l

Page 7: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 7DanieleSpiga

DODASintheRealLife@CMS

ADODASgeneratedCMS-

Site

T3_IT_Opportunistic_hnsci DODASwithintop6CMSTier2sfor10days

-FrancescoBrivioINFN-ChiaraAmendolaLLR

CMSusersanalysis:hh—>2b2tauà SkimmingminAOD(Data&MC)to

produceflat-ntuple

Page 8: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 8DanieleSpiga

-Elasticityandself-healing-Handling“specialrequirements”highmemoryjobs-Stabilityoverdays/weeks(120kjobs)

àWorkdoneinconjunctionwithThankstoAndreaChierici

ResourcesManagementwithDODAS

Page 9: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 9

DataIngestion:CachingStrategy

DanieleSpiga

•  DeploymentofacachelayerbetweenWorkerNodesandremoteGridStorageElements.

•  CachelayerimplementedwithXRootDDataCache(XCache)•  SeamlesslyintegratingtheCMSruntime

environment

•  SupportinganOn-DemandCachingdeploymentmodel•  TOSCA(plusAnsible) DODASgenerated

CMS-SiteCMSAAAXRootD

Federation

àDevelopmentdoneinthecontextof SeeTalk:Advancementsindatamanagementservicesfordistributede-infrastructures:theeXtreme-DataCloudproject

CourtesyofDiegoCiangottini

Page 10: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 10

 DODASonOpenStack@ICL:cloud.grid.hep.ph.ic.ac.uk-  UseCases

§  ProducingCMSnanoAODformatforICSMPAnalyses§  ProducingGen-SimfromCMSgridpacks§  ProducingCMSgridpacks

MoreaboutDODASusage:PrivateCloud

DanieleSpiga

DODASadoptedtorunworkflowswithspecificMemoryrequests(upto32GB)

T3_U

K_Opp

ortunisitc_d

odas

CourtesyofRiccardoDiMaria

Page 11: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 11

DODASasMLaaService

DanieleSpiga

EndUsers

SparkDispatcher

Master

LoadBalancer

SlaveSlave

Slave

SparkNode

SparkNodeSparkNode

SparkNode

SparkNode

SparkNode

DODASephemeralsite

 Analysisof“DataCache”relatedmetadataflow-  Toimprovecachinglayermanagement:SmartCache

1.  Collectionofrawdata•  Workloadmanagement•  Datamanagement

2.  DataenrichmentandreductionwithSparkjobs•  StoringofoutputdatainHDFS

3.  Analysisofstructureddata4.  Prototypingofamodel

CourtesyofMaricaAntonacciandMircoTracolli

Page 12: Exploiting private and commercial clouds to generate on ...€¦ · • Introduction to DODAS ... à Development done in the context of See Talk: Advancements in data management services

CHEP2018Sofia,Bulgaria 12

 DODASseamlessintegratedintoexistingHTCondorGlobalPoolofCMS-  SeveralusecasesbasedbothonHTCondorandBigData

 SuccessfullytestedonmanyPublicandPrivateclouds

 DODASisaThematicServiceundertheEOSC-hubProject,assuchitissupposedtobeadoptedalsooutsideCMS

§  AMSExperimentisalreadytesting/evaluatingDODAS

 DODASexpertsareavailableforconsultancyandtraininginterestedcommunities.-  [email protected]  Additionalinfo:https://dodas.gitbook.io/dynamic-on-demand-analysis-service/

Conclusions

DanieleSpiga