infn - ferrara babargrid meeting spgrid efforts in italy babar collaboration meeting - slac december...

14
INFN - Ferrara INFN - Ferrara BaBarGrid Meeting BaBarGrid Meeting SPGrid Efforts in Italy SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

Upload: erica-reynolds

Post on 16-Dec-2015

219 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

INFN - FerraraINFN - Ferrara

BaBarGrid MeetingBaBarGrid Meeting

SPGrid Efforts in ItalySPGrid Efforts in Italy

BaBar Collaboration Meeting - SLACDecember 11, 2002

Enrica Antonioli - Paolo Veronesi

Page 2: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 2

Topics Topics

Ferrara Farm Configuration

First SP submissions through the Grid

Work in Progress

Future Plans

Conclusions

Page 3: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 3

SPGrid Farm in FerraraSPGrid Farm in Ferrara

LCFGServer

Management

Lock serverLock server

Data serverData server

SCSISCSI

250 GB250 GB

IR 0A DSESE

CE-WNCE-WN

UIUI

Ferrara - EDG 1.2.2

RBRB

CNAF - BolognaCERN

Page 4: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 4

ConfigurationConfiguration INFN Grid Testbed Status: EDG 1.2.2 (RedHat 6.2).

A BaBar software special release (12.3.2y) has been built and installed to:

Write Kanga files Run Moose on RH 6.2

A special tag of ProdTools has been installed to perform tests.

A pool of BaBar accounts (babar000, babar001,…) has been created in the EDG farm of Ferrara.

Each member of BaBar VO is able to submit jobs to the farm of Ferrara through the RB located at CNAF (grid009g.cnaf.infn.it).

Page 5: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 5

Current StatusCurrent Status

Created a JDL file to run Moose on Grid resources.

Created scripts containing EDG commands to submit jobs, to check their status and retrieve output files.

An user can submit a range of runs.

For each run a job is created and submitted to the Resource Broker, then it is sent to the Ferrara CE (grid0.fe.infn.it).

The output file is then transferred to the closest SE (grid2.fe.infn.it).

Page 6: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 6

Moose.jdlMoose.jdl

grid1> more Moose.jdl Executable ="Moose.csh";InputSandbox ={"Moose.csh",".cshrc","config.csh"};StdOutput ="Moose.txt";StdError ="Moose.log";OutputSandbox ={"Moose.txt","Moose.log"};

General environment configurations

Config file for BaBar.Similar to SP standard

scripts

Similar to SP standard scripts (Job.Xsh)

[…]tar -czvf run${RUNNUM}.tar.gz *.rootglobus-url-copy -vb file://`pwd`/run${RUNNUM}.tar.gz \gsiftp://grid2.fe.infn.it/flatfiles/SE00/enrica/run${RUNNUM}.tar.gz

Globus command:To copy output files from WN to SE

Page 7: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 7

grid1> more launch #!/bin/tcsh -v

@ num_f = $1@ fin = $2

while ( $num_f <= $fin )

####build the run directories[…]####build a config.csh with the appropriate environment variablesecho "#\!/bin/tcsh -v" > config.csh[…]#### now run the jobdg-job-submit -o run$num_f.jobid -r \grid0.fe.infn.it:2119/jobmanager-pbs-long Moose.jdl

cd ..@ num_f++end

The launch scriptThe launch script

A config file is created for each

run

EDG job submission command

Range of runs to submit

For each run a job is created runtime

Page 8: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 8

Job SubmissionJob Submission

grid1> ls1962016 1962017 Moose.csh Moose.jdl config.csh launch monitor retrieve

grid1> ./launch 1962016 1962017[…]dg-job-submit -o run$num_f.jobid -r grid0.fe.infn.it:2119/jobmanager-pbs-long Moose.jdl

Connecting to host grid009g.cnaf.infn.it, port 7771Logging to host grid009g.cnaf.infn.it, port 15830

================== dg-job-submit Success ================ The job has been successfully submitted to the Resource Broker. Use dg-job-status command to check job current status. Your job identifier (dg_jobId) is: https://grid009g.cnaf.infn.it:7846/193.206.188.102/104224188091275?grid009g.cnaf.infn.it:7771 The dg_jobId has been saved in the following file: /home/enrica/stress/1962016/run1962016.jobid[…]

grid1> ls 1962016/Moose.csh Moose.jdl config.csh run1962016.jobid

grid1> ls 1962017/Moose.csh Moose.jdl config.csh run1962017.jobid

Range of runs to submit

Job ID

CNAF RB

Page 9: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 9

grid1> ./monitor 1962016 1962017Run 1962016 is Status = Scheduled Status Reason = initial Run 1962017 is Status = Scheduled Status Reason = initial

grid1> ./monitor 1962016 1962017Run 1962016 is Status = Running StatusRun 1962017 is Status = Running Status

The monitor scriptThe monitor script

grid1> ./monitor 1962016 1962017Run 1962016 is Status = Ready Status Reason = job acceptedRun 1962017 is Status = Ready Status Reason = job accepted

grid1> more monitor#!/bin/tcsh

@ num_f = $1@ fin = $2

while ( $num_f <= $fin )echo Run $num_f is `dg-job-status -i \ $num_f/run$num_f.jobid | grep Status`

@ num_f++end

EDG command

grid1> ./monitor 1962016 1962017Run 1962016 is Status = OutputReady Status Reason = terminated Run 1962017 is Status = OutputReady Status Reason = terminated

Page 10: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 10

The retrieve scriptThe retrieve scriptgrid1> more retrieve #!/bin/tcsh -v@ num_f = $1@ fin = $2while ( $num_f <= $fin )cd $num_f#### get logfilesdg-job-get-output -i run$num_f.jobid --dir $PWD#### get rootfilesglobus-url-copy \ gsiftp://grid2.fe.infn.it/flatfiles/SE00/enrica/run$num_f.tar.gz \ file://`pwd`/run$num_f.tar.gz

tar -xzvf run$num_f.tar.gzrm -f run$num_f.tar.gz#### delete rootfiles form SEglobus-job-run grid2.fe.infn.it /bin/rm \/flatfiles/SE00/enrica/run$num_f.tar.gzcd ..@ num_f++end

EDG command

Globus command:Direct copy of file from SE to UI

Globus command:delete file fromSE

Page 11: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 11

Retrieving OutputRetrieving Output

grid1> ls1962016 1962017 Moose.csh Moose.jdl config.csh launch monitor retrieve

grid1> ls 1962016/150546318633191 Moose.jdl rootdef-tru.root Moose.csh config.csh run1962016.jobidrootdef-tag.root rootdef-aod.root

grid1> ls 1962017/150551318931039 Moose.jdlMoose.csh config.csh run1962017.jobidrootdef-tru.root rootdef-tag.root rootdef-aod.root

grid1> ls 1962016/150546318633191/Moose.log Moose.txt

grid1> ls 1962017/150551318931039/Moose.log Moose.txt

Page 12: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 12

Work in progressWork in progress

We are now trying to copy files to the SE through the

Manchester Replica Catalog.

We are checking package dependencies (e.g. flat files,

shared libraries) to build a Moose RPM to be

automatically installed on Grid machines.

We are testing the special tag of ProdTools which

includes an option to create and submit Moose jobs to

the Grid resources.

Page 13: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 13

Future PlansFuture Plans

Data serverData server

Lock serverLock server

Objectivity DBObjectivity DBRBRB(UK)(UK)

Ferrara

MOOSEMOOSERPM

RPM

3) Install Objy DB on the SE

2) MOOSE in RPM format

1) Use of IC RB and others

Integration of MooseIntegration of Moose Application withApplication with

EDG software releasesEDG software releases

SPGrid Farm

Management

LCFGServer

SESE

CE-WNCE-WN

UIUI

Page 14: INFN - Ferrara BaBarGrid Meeting SPGrid Efforts in Italy BaBar Collaboration Meeting - SLAC December 11, 2002 Enrica Antonioli - Paolo Veronesi

SLAC - December 11, 2002 14

SummarySummary

In order to be integrated with the Grid we need: To produce RPM packages for Moose Application.

To install OBJY DB on the SE.

To submit the resulting RPMs to the EDG Integration

Team. After that we will be able to install and manage

Simulation Production software and environment on

EDG farms via LCFG server.

Thanks to Peter Elmer, Alessandra Forti, Douglas Smith, Matthias Steinke and Steve Traylen for their collaboration.