Presentation is loading. Please wait.

Presentation is loading. Please wait.

Parallel Reconstruction of CLEO III Data Gregory J. Sharp Christopher D. Jones Wilson Synchrotron Laboratory Cornell University.

Similar presentations


Presentation on theme: "Parallel Reconstruction of CLEO III Data Gregory J. Sharp Christopher D. Jones Wilson Synchrotron Laboratory Cornell University."— Presentation transcript:

1 Parallel Reconstruction of CLEO III Data Gregory J. Sharp Christopher D. Jones Wilson Synchrotron Laboratory Cornell University

2 Outline Overview of CLEO reconstruction environment The problems with the old reconstruction system The solution - finer-grained parallelism The benefits

3 CLEO III Reconstruction Environment Uses a farm of more than 130 Sun Netras Sun Grid Engine ™ manages CPU allocation Events must be written to DB in event-number order Data read from & written to Objectivity/DB™ Reconstruction rate has to equal average DAQ rate

4 Former Reconstruction System Each run is processed in its entirety by a single CPU ~130 runs may be processed in parallel on the farm Up to 9 days to reconstruct a single run on a single CPU Output was written directly to the offline database All failures required operator and/or DBA intervention

5 Problems Need to maximize CPU utilization Load balancing between farms is difficult Takes a long time to stop the farm safely Output of the first few runs must be checked Debugging reconstruction code

6 More Problems Many locks held for long periods Low I/O rates to the database Large window for failures to occur Failure leaves database in an invalid state No automation of failure detection and recovery

7 The Solution Split each run into roughly equal-sized chunks Assign each chunk to a CPU Save sub-job output in intermediate binary files in event-number order Once all sub-jobs complete, collate binary files into database in event-number order

8 The Job Manager Once all reconstruction completes successfully the JM starts the collation sub-job The JM submits all the reconstruction sub-jobs and monitors their progress, retrying failures Once collation completes successfully the JM starts the merge histogram sub-job Can be restarted at any time if it dies

9 Structure Diagram

10 Automation A cron job generates status web pages Runs may be submitted automatically when SGE queue is (almost) empty JM restarts subjobs with transient failures

11 Implementation Details Written in Perl Uses Sun Grid Engine to submit and track jobs Uses CLEO III software infrastructure for reconstruction and population Uses PAW for merging histograms

12 Benefits The January ice storm Faster debugging Less operator intervention/management Increased CPU utilization, which offsets extra CPU use 20% Faster completion of reconstruction Just-in-time pre-staging of data from HSM file system

13 Future Steps Automate staging of data to cache disks Automate posting of staged runs info to Reconstruction

14 Conclusions Multiple file formats made this possible For more details: http://www.lepp.cornell.edu/~gregor/projects/parallelpass2 Substantial productivity gains Higher utilization of computing resources


Download ppt "Parallel Reconstruction of CLEO III Data Gregory J. Sharp Christopher D. Jones Wilson Synchrotron Laboratory Cornell University."

Similar presentations


Ads by Google