INAF experience in Grid projects C. Vuerli, G. Taffoni, V. Manna, A. Barisani, F. Pasian INAF – Trieste.

INAF experience in Grid INAF experience in Grid projectsprojects

C. Vuerli, G. Taffoni, V. Manna, C. Vuerli, G. Taffoni, V. Manna, A. Barisani, F. PasianA. Barisani, F. Pasian

INAF – TriesteINAF – Trieste

Wed 10 May 2006Wed 10 May 2006 22

OverviewOverview

• The GRID.IT ProjectThe GRID.IT Project

• DRACO and the VO INAFDRACO and the VO INAF

• Planck Simulations in EGEEPlanck Simulations in EGEE

• New powerful Grid infrastructuresNew powerful Grid infrastructures– TriGrid Virtual LaboratoryTriGrid Virtual Laboratory

• Training and DisseminationTraining and Dissemination

Wed 10 May 2006Wed 10 May 2006 33

GRID.IT ProjectGRID.IT Project

• The GRID.IT ProjectThe GRID.IT Project– Application 1Application 1

• Accessing Databases through the GRIDAccessing Databases through the GRID

• Processing Data extracted from DatabasesProcessing Data extracted from Databases

• Ingesting results of Data Processing in DatabasesIngesting results of Data Processing in Databases

– Application 2Application 2• Porting in GRID the VST PipelinesPorting in GRID the VST Pipelines

– Application 3Application 3• Monitoring of Astronomical Instrumentation through Monitoring of Astronomical Instrumentation through

the GRIDthe GRID

Wed 10 May 2006Wed 10 May 2006 44

GRID.IT / Application 1GRID.IT / Application 1

• ProblemProblem– The middleware based on Globus 2.4 didn’t The middleware based on Globus 2.4 didn’t

offer any mechanism to access databasesoffer any mechanism to access databases

• SolutionsSolutions– Evaluation of a number of possible solutionsEvaluation of a number of possible solutions

•SpitfireSpitfire

•OGSA-DAIOGSA-DAI

•G-DSEG-DSE

Wed 10 May 2006Wed 10 May 2006 55

GRID.IT / Application 1GRID.IT / Application 1

• SpitfireSpitfire– Not suitable for us (poor functionalities)Not suitable for us (poor functionalities)

• OGSA-DAIOGSA-DAI– WS-based: we don’t want to merely access WS-based: we don’t want to merely access

data. We want databases integrated in Grid data. We want databases integrated in Grid and look at DBMS machines as computational and look at DBMS machines as computational machinesmachines

• G-DSEG-DSE– Databases as embedded resources in GRIDDatabases as embedded resources in GRID

Wed 10 May 2006Wed 10 May 2006 66

GRID.IT / Application 3GRID.IT / Application 3

• Past experience in developing Past experience in developing Telescope and instrumentation control Telescope and instrumentation control systems and participation to EU pilot systems and participation to EU pilot projects to remotely monitor and projects to remotely monitor and control themcontrol them– We want to go ahead with this experience We want to go ahead with this experience

and use GRID for this purposeand use GRID for this purpose– First simple monitoring prototype: tests First simple monitoring prototype: tests

carried out at Trieste and Naples carried out at Trieste and Naples

Wed 10 May 2006Wed 10 May 2006 77

GRID.IT / Future evolutionGRID.IT / Future evolution

• G-DSE + QEG-DSE + QE– G-DSE prototype engineeringG-DSE prototype engineering– Design, implementation and test of the Design, implementation and test of the

QEQE– G-DSE + QE in productionG-DSE + QE in production

• G-ICS + IEG-ICS + IE– Design, implementation and test of the Design, implementation and test of the

G-ICS and of the IEG-ICS and of the IE– G-ICS + IE in productionG-ICS + IE in production

Wed 10 May 2006Wed 10 May 2006 88

In production…but where ?In production…but where ?

• G-DSE + QEG-DSE + QE– All INAF Databases in GRID with G-DSEAll INAF Databases in GRID with G-DSE– Other scientific communities are testing it : INFN, Other scientific communities are testing it : INFN,

Bioinformatics, Archaeologists, …Bioinformatics, Archaeologists, …– Supporting Planck simulations in future releasesSupporting Planck simulations in future releases– Projects in preparation to port it on EGEE and Projects in preparation to port it on EGEE and

DEISADEISA• G-ICS + IEG-ICS + IE

– Close contacts with GridCCClose contacts with GridCC– Strong interest for instruments and sensors in GridStrong interest for instruments and sensors in Grid

• ICTP and INAF Naples : monitoring and controlling ICTP and INAF Naples : monitoring and controlling networks of sensors via Gridnetworks of sensors via Grid

Wed 10 May 2006Wed 10 May 2006 99

DRACODRACO

• A Grid portal thought and designed for A Grid portal thought and designed for astrophysical applicationsastrophysical applications

• Porting astrophysical applications in GRIDPorting astrophysical applications in GRID– Definition of astronomical data analysis workflow on a Definition of astronomical data analysis workflow on a

service-oriented Grid architecture using BPEL (Manna et service-oriented Grid architecture using BPEL (Manna et al.)al.)

– Data Mining and Massive computing for GRID at Naples-Data Mining and Massive computing for GRID at Naples-Salerno UnitSalerno Unit

– Astronomical Data Reduction in Data GridAstronomical Data Reduction in Data Grid– Various kinds of evolutionary modelsVarious kinds of evolutionary models– ACME for GRIDACME for GRID

• The INAF VO is now growingThe INAF VO is now growing

Wed 10 May 2006Wed 10 May 2006 1010

Planck simulations in EGEEPlanck simulations in EGEE

• Planck simulations is an officially Planck simulations is an officially supported pilot EGEE application supported pilot EGEE application since November 2004since November 2004

• Planck application also in EGEE-2Planck application also in EGEE-2

• A Planck VO, led by INAF Trieste, is in A Planck VO, led by INAF Trieste, is in place. It groups together Grid sites place. It groups together Grid sites located in six European countrieslocated in six European countries

Wed 10 May 2006Wed 10 May 2006 1111

Planck simulations in EGEEPlanck simulations in EGEE

• First experiments to port the Planck First experiments to port the Planck simulations in Grid at INAF-Triestesimulations in Grid at INAF-Trieste– Partial Planck simulation pipelines in June 2004 Partial Planck simulation pipelines in June 2004

using the GRID.IT Grid infrastructureusing the GRID.IT Grid infrastructure– Simulation of the whole Planck mission (two Simulation of the whole Planck mission (two

complete sky surveys) in Grid and comparison of complete sky surveys) in Grid and comparison of results with those got on a single dual-CPU results with those got on a single dual-CPU workstationworkstation

– New bricks of the Planck pipeline in Grid in the New bricks of the Planck pipeline in Grid in the next monthsnext months• WG8 meeting at MPA (Germany) in June 2006WG8 meeting at MPA (Germany) in June 2006

Wed 10 May 2006Wed 10 May 2006 1212

Planck simulations in EGEEPlanck simulations in EGEE

• Planck simulations didn’t make use of Planck simulations didn’t make use of databases until now, but…databases until now, but…– They could be profitably integrated and used in They could be profitably integrated and used in

the near futurethe near future– Ground based test and calibrations of the Ground based test and calibrations of the

spacecraft and of the instruments are now in spacecraft and of the instruments are now in progressprogress

– Data collected in this phase must be saved Data collected in this phase must be saved somewhere and used during the operative somewhere and used during the operative phase of the missionphase of the mission

• ……therefore this is a new test-bed for G-DSE therefore this is a new test-bed for G-DSE

Wed 10 May 2006Wed 10 May 2006 1313

TriGrid Virtual LaboratoryTriGrid Virtual Laboratory

Wed 10 May 2006Wed 10 May 2006 1414

TriGrid Virtual LaboratoryTriGrid Virtual Laboratory

• CataniaCatania Pole: Pole:– ~100 machines dual CPU 32/64 bit. Aggregated power of ~100 machines dual CPU 32/64 bit. Aggregated power of

300 kSpecInt2000.300 kSpecInt2000.– 30 TB of storage EIDE-to-SCSI or FC-to-SATA in RAID 0,1,530 TB of storage EIDE-to-SCSI or FC-to-SATA in RAID 0,1,5– 20 working stations for development/porting of 20 working stations for development/porting of

applicationsapplications• MessinaMessina Pole: Pole:

– ~80 machines dual CPU 32/64 bit. Aggregated power of ~80 machines dual CPU 32/64 bit. Aggregated power of ~240 kSpecInt2000.~240 kSpecInt2000.

– 20 TB of storage EIDE-to-SCSI or FC-to-SATA in RAID 0,1,520 TB of storage EIDE-to-SCSI or FC-to-SATA in RAID 0,1,5• PalermoPalermo Pole: Pole:

– ~30 machines dual CPU 32/64 bit. Aggregated power of ~30 machines dual CPU 32/64 bit. Aggregated power of ~100 kSpecInt2000.~100 kSpecInt2000.

– 10 TB of storage EIDE-to-SCSI or FC-to-SATA in RAID 0,1,510 TB of storage EIDE-to-SCSI or FC-to-SATA in RAID 0,1,5

Wed 10 May 2006Wed 10 May 2006 1515

Training and disseminationTraining and dissemination

• The knowledge of GRID must grow both The knowledge of GRID must grow both at national and European levelat national and European level– It is necessary to train Grid managers able It is necessary to train Grid managers able

to install, configure and maintain Grid sitesto install, configure and maintain Grid sites– It is necessary to train astronomers to It is necessary to train astronomers to

illustrate them this new technology and illustrate them this new technology and make them aware of what they can make them aware of what they can profitably do with the Grid for their profitably do with the Grid for their everyday workeveryday work

Wed 10 May 2006Wed 10 May 2006 1616

Training and disseminationTraining and dissemination

• How to train ?How to train ?– Meetings and workshops both at national and Meetings and workshops both at national and

European levelEuropean level• Theoretical lessonsTheoretical lessons• Practical trainingPractical training

– Astronomers bring applications of interest and try to Astronomers bring applications of interest and try to gridify them with our helpgridify them with our help

– On site dedicated workshopsOn site dedicated workshops– Grid schoolsGrid schools– Coordination with Working Groups having the Coordination with Working Groups having the

same objectives (the Planck Working Group 8)same objectives (the Planck Working Group 8)

Wed 10 May 2006Wed 10 May 2006 1717

The EndThe End

Thank you for your attentionThank you for your attention