LHC Experiments Grid Integration Plans C Grandi INFN

LHC Experiments Grid Integration Plans C. Grandi INFN - Bologna Claudio Grandi INFN Bologna 9/16/2020

Introduction What do LHC experiments have to do: Build a distributed computing system for the experiment Test the prototypes: tools evaluation data challenges: tests with big data flows What do LHC experiments have today: Software • EDG release 1. 1 (1. 2 coming) • VDT release 1. 0 (includes Globus, Condor-G, GDMP, …) • Other tools for distributed computing (e. g. Web services, …) Test facilities • EDG test bed • EDT supported experiment test beds • US Gri. Phy. N/PPDG/i. VDGl experiment test beds Claudio Grandi INFN Bologna 9/16/2020 2

ALICE: Overview Job submission/control/monitoring: Application: Ali. Root Data Persistency: Root Ali. En Data Catalogue: Ali. En Job parallelisation: Root/PROOF ROOT Ali. Root Ali. En API/PROOF IVDGL EDT Ali. En Services By P. Cerello Claudio Grandi INFN Bologna 9/16/2020 3

ALICE: Sites Houston Univ. - Texas OSU/OSC - Ohio LBL - California CERN - CH INFN Cagliari/Catania/ CNAF/Salerno/Torino - I NIKHEF - NL (? ) By P. Cerello Claudio Grandi INFN Bologna 9/16/2020 4

ALICE: Integration Items Job submission: EDG/Resource Broker as an Ali. En client Condor-G as an Ali. En client Data Management: register/access the Ali. En Data Catalogue from an EDG/i. VDGL/. . . Job Meta. Data Catalogue: implement a Job Meta. Data Catalogue Test multiple accesses and concurrent updates Evaluate Spitfire to manage it Spawn PROOF sub-jobs on any GRID By P. Cerello Claudio Grandi INFN Bologna 9/16/2020 5

ALICE: Integration Plans Ali. En Job Meta. Data Catalogue EDG RB Ali. En Job EDG CE Alice Farm Ali. En Job Condor-G EDG WN I-LFN Ali. En Job O-PFN Ali. En Job EDG SE Ali. En Data Catalogue Alice User O-LFN, O-PFN I-PFN By P. Cerello Claudio Grandi INFN Bologna 9/16/2020 6

ALICE: Integration Plans I-LFN(s) Meta. Data Catalogue I-LFN(s) EDG WN Ali. En Data Catalogue I-PFN(s) I-PFN 3 I-PFN 2 PROOF I-PFN 1 EDG SE 1 O-PFN 1 Claudio Grandi INFN Bologna EDG CE 2 EDG CE 3 EDG SE 2 EDG SE 3 O-PFN 2 O-PFN 3 By P. Cerello 9/16/2020 7

ATLAS: DC 1 & 2 DC 1/1: simulation of 10**7 evts for HLT TDR started 15 April. Bulk of production will start after 15 June DC 1/2: stress is on new software (20 -9 till Xmas) Use of currently avalable Grid tools favoured but not mandatory: start with EDG 1. 2 in EU and VDT 1. 0 in US: Some US sites deploy EDG software and vice-versa. Integration of Magda (US data catalog+some replica management) with EDG RC Critical issue the EDG stability and reliability DC 2: start spring 03 Use EDG release 2 Grid API to be inserted in ATHENA framework Magda and WP 2 convergency plan to be detailed and executed Integrate VDT components Claudio Grandi INFN Bologna 9/16/2020 8

ATLAS: Overview Main tools for data management on the grid: Magda - MAnager for Grid Data GANGA - Gaudi and Grid Alliance (with LHCb) Other tools in development: – Grid. View - simple script tool to monitor status of testbed (Java version being developed) – Gripe - unified user accounts – Pacman - package management and distribution tool – Grappa - web portal based on active notebook tech. – GRAT (GRid Application Toolkit): distribution of ATLAS software on the Grid Integration with EDG is being discussed Claudio Grandi INFN Bologna 9/16/2020 9

ATLAS: Magda: MAnager for Grid-based Data MA Deliverable for the Particle Physics Data Grid My. SQL database at the core of the system User interaction via command line and web interface File replication via GSIFtp Currently in use for ATLAS distributed data management prototyping and design 260 k files, ~11 TB cataloged at present Synchronization between Magda & EDG catalogues ATLAS applications query Magda’s My. SQL catalogue; EDG Resource Broker queries the Globus Replica Catalog. By D. Rebatto Claudio Grandi INFN Bologna 9/16/2020 10

ATLAS: Magda Host A Host B Magda My. SQL catalog Magda GDMP Local Catalogue my_file Export Catalogue Import Catalogue my_file GSIFtp Globus replica catalog Magda GDMP_STAGE_TO_MSS GDMP Local Catalogue Export Catalogue Import Catalogue my_file USER GDMP A: B: B: A gdmp_publish_catalogue A: gdmp_replicate_get gdmp_host_subscribe gdmp_register_local_file magda_putfile my_file -rat--registeronly host_b -p Amy_file -p <p> file named my_file is created Host By D. Rebatto Claudio Grandi INFN Bologna 9/16/2020 11

CMS: Overview Build a unique CMS-GRID framework (EU+US) EU and US grids not interoperable today Help from Data. TAG-i. VDGL-GLUE Work in parallel in EU and US Main US activities: MOP Virtual Data System Interactive Analysis CMS Production Framework Main EU activities: Integration of IMPALA with EDG WP 1+WP 2 sw. Batch Analysis: user job submission & analysis farm Claudio Grandi INFN Bologna 9/16/2020 12

CMS: Schedule 2000 -01: A few sites in production. Some grid tools used “in production” (GDMP). 2002: World-Wide productions. Prototypes of “distributed” production sites deployed in US and EU. DAQ TDR. 2003: Integration activities: US/EU grid interoperability. First grid-enabled sites used “in production”. 2004: 5% data challenge. Deployment of delivered LCG prototypes. CCS TDR. 2005: preparation for 20% data challenge. Build "final" computing environment. Physics TDR. Long term schedule being revised now! Claudio Grandi INFN Bologna 9/16/2020 13

CMS: EU-US integration 02 Reference DB Physics Data Production & Analysis Portal Planner (uses CMS production SW) job job Data Management components -Replica Manager -Virtual Data Catalogue -Replica Catalogue -… EDG SW job Computing Element Storage Element Local analysis tools with plugin to access remote data Claudio Grandi INFN Bologna = data flow or invocation = read data from = contains reference to = active component = catalog or database 9/16/2020 14

CMS: EDG integration 02 = data flow or invocation = read data from = contains reference to Reference DB Production portal has all information needed by IMPALA to generate a dataset Replica Catalogue Maps each logical file name to one or more physical file names IMPALA = active component = catalog or database Get request for a production Create location independent jobs Worker nodes BOSS CMSIM ORCA job Computing Element Job Submission Service User Interface job Resource Broker Finds suitable Location for execution Condor-G GRAM job Information Services LDAP server Resource information Claudio Grandi INFN Bologna Local Scheduler Storage Element Local Objy FDDB 9/16/2020 Local Storage 15

LHCb: Overview GANGA (Gaudi and Grid Alliance) : In collaboration with Atlas developing user interface for all levels of user (physicist, production manager, developer) Control and Monitoring system for distributed data production: Using PVSS today Data challenges: DC 1: 3 -30 june + 26 august -22 september 2002 DC 2: 2003 DC 3: 2004 DC 4: 2005 Claudio Grandi INFN Bologna 9/16/2020 16

LHCb: DC 1 Computing tests – prototype of new data management databases – configuration of LHCb environment at remote sites and installation kits – monitoring and control with PVSS – integrability of EDG testbed into our production system – data quality checking, evaluate Da. Vinci based tools – use "push" MC job submission initially, perhaps test first version of pull mechanism during second half – executables to be tested in production: sicbmc, Brunel, Da. Vinci Data production Produce useful data, for example for Physics studies with this facility, if the software is ready… Resources: 100 – 150 CPU at CERN & ~300 -350 CPUs outside (Bologna, IN 2 P 3, RAL, Oxford, Bristol, Edinburgh, Nikhef, Cambridge, Barcelona, By J. Closier Moscow, Amsterdam VU? ) Claudio Grandi INFN Bologna 9/16/2020 17

LHCb: DC 2 (2003) Computing tests – production version of new data management databases – implementation of "pull" MC job submission system, exploiting EDG resource broker – stress test Grid "philosophy" of submitting jobs without worrying where the job will run and where the output will be stored – monitoring and control, evaluate EDG middleware (how does it work with PVSS? can it replace it? ) – make job submission tools independent of remote sites – test of first Ganga prototype – test of some Gaudi-Grid interfaces e. g. event selector – test of automatic data quality histogram creation and checking in production – executables to be tested: (sicbmc), Gauss, Brunel, Da. Vinci, Gaudi Resources Same sites as DC 1 + Switzerland, Germany, Poland Claudio Grandi INFN Bologna By J. Closier 9/16/2020 18

LHCb: DC 3&4 (2004/5) Computing tests for DC 3 – test of first prototype of the analysis model (display events that were analysed on the grid) – test of Ganga production version – full use of Grid in production – further tests of Gauss in production – tests of data quality checking in production – executables to be tested: Gauss, Brunel, Da. Vinci, Gaudi Computing tests for DC 4 test of production analysis model the other points also mentioned previously Claudio Grandi INFN Bologna By J. Closier 9/16/2020 19

Summary Experiments are integrating Grid tools in their computing environment Most of the experiments are using Grid tools delivered by more than one Grid Project Most of the experiments are not planning to use the tools out of the box but to adapt them to their needs Need help by middleware experts for interoperability Need non-standard facilities to develop and test the experiment computing environment. Help by middleware experts is needed for that too Claudio Grandi INFN Bologna 9/16/2020 20