1 / 10

LCG-1 and EDG 2.0 Tests for LHCb: Results, Next Steps, and LCG-2 Integration

This document provides an overview of the LHCb setup and tests conducted on the LCG-1 platform and EDG 2.0. It discusses the use of DIRAC for computing resources and the testing of new software packaging and installation tools for LCG-2. The results of the tests and the next steps for LHCb are also presented, including the integration of LCG-2 into the production system for DC 2004.

bseal
Download Presentation

LCG-1 and EDG 2.0 Tests for LHCb: Results, Next Steps, and LCG-2 Integration

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. LHCb – first tests of the LCG-1 A.Tsaregorodtsev, CPPM, Marseille LCG Internal Review, 17 November 2003 LCG internal review, 17 November 2003, CERN

  2. Outline • LHCb setup on the LCG-1 platform • LCG-1 tests • Next steps LCG internal review, 17 November 2003, CERN

  3. DIRAC use of computing resources • DIRAC design goals to facilitate operation in various environments: • Scheduling jobs to “any grid” computing resources: • “native” sites, running DIRAC Agents; • EDG/LCG grid as a whole, passing through RB; • EDG/LCG CE’s and SE’s as DIRAC resources. • Flexibility in software installation: • Software preinstalled by grid site managers (rpms, etc); • Software preinstalled on the sites by the LHCb managers; • Software installation on the flight by a running job • Using “any grid” storage resources: • Data Management component to be able to replicate data between LCG and DIRAC storage elements; LCG internal review, 17 November 2003, CERN

  4. DIRAC WMS architecture Production manager Task queue Job DB LHCb CE/PBS LHCb CE/LSF DIRAC distributed WMS EDG CE1 Agent Agent EDG RB EDG CE2 Agent EDG CE3 Agent LCG CE1 Agent LCG1 RB LCG CE2 Agent LCG CE3 LCG internal review, 17 November 2003, CERN

  5. EDG 2.0 tests • So far most of the tests were done on the EDG 2.0 testbed: • Direct scheduling to the CE; • Job deploys a DIRAC agent on the WN which: • Installs software on the fly on the WN; • From the LHCb http server; • Cleaned up in the end of job; • Steers the job execution; • Steers transfers of the resulting data. • Using Replica Manager tools to deliver Input/Output sandboxes and datasets; • Jobs reporting their status to the Job Monitoring Service via XML-RPC messages. LCG internal review, 17 November 2003, CERN

  6. EDG 2.0 tests (2) • Results: • LHCb production jobs are properly running if no system failures; • Short jobs (2 events); • In bunches of ~50 jobs. • Very unstable R-GMA based Information System: • Screws up job submission but also Replica Manager tools which we heavily rely upon; • No large scale production yet done with EDG 2.0: • 300K events production with EDG 1.4 in Feb 2003 • Tests continue LCG internal review, 17 November 2003, CERN

  7. LCG tests (1) • New software packaging in rpms ; • Testing the new LCG-2 proposed software installation tools; • New generation software to run: • Gauss/Geant4+Boole+Brunel+… • Using the LCG Resource Broker • Unlike direct scheduling to a CE in the EDG 2.0 tests; • Direct scheduling if necessary. LCG internal review, 17 November 2003, CERN

  8. LCG tests (2) • Tests of the basic functionality • LHCb software correctly installed from rpms ; • Tests with standard LHCb production jobs: • 4 steps – 3 simulation datasets, 1 reconstructed dataset; • Low statistics – 2 events per step; • Applications run OK ; • Produced datasets are properly uploaded to a SE and registered in the LCG catalog; • Produced datasets are properly found and retrieved for the subsequent use. LCG internal review, 17 November 2003, CERN

  9. LCG tests – next steps • Long jobs: • 500 events ; • 24-48 hours depending on CPU ; • Large number of jobs to test the scalability: • Limited only by the resources available. • LCG-2 should bring important improvements for LHCb which we will try as soon as they will be available: • Experiment driven software installation; • Testing now on the “installation” testbed. • Access to MSS (at least Castor/CERN) LCG internal review, 17 November 2003, CERN

  10. LCG tests – next steps • LCG-2 seen as an integral part of the LHCb production system for the DC 2004 (Feb 2004) • Necessary conditions : • The availability of major non LHC dedicated centers both through usual and LCG workload management system; • E.g CC/IN2P3, Lyon. • The LCG Data Management tools accessing to major MSS (Castor/CERN, HPSS/IN2P3, FZK, CNAF, RAL); • The overall stability and efficiency (>90%) of the system. LCG internal review, 17 November 2003, CERN

More Related