Difference between revisions of "Goals for Online Data Challenge 2013"

From GlueXWiki
Jump to: navigation, search
Line 1: Line 1:
 
Goals for the GlueX online Data Challenge 2013
 
Goals for the GlueX online Data Challenge 2013
  
7/22/2013 revised E. Wolin
+
7/22/2013 revised E. Wolin<br>
 
7/9/2013  D. Lawrence
 
7/9/2013  D. Lawrence
  

Revision as of 17:59, 22 July 2013

Goals for the GlueX online Data Challenge 2013

7/22/2013 revised E. Wolin
7/9/2013 D. Lawrence

The primary goal of the Online Data Challenge is to test the data monitoring and data flow piece that fits between the DAQ system (past the final event builder) and the tape silo. Independent DAQ group testing addresses the pieces upstream (front-end modules through event builder) while the offline Data Challenges of 2012 and 2013 address the pieces downstream.

The 2013 ODC will take place in the Hall-D counting house using whatever equipment is currently installed. Some of this is final versions while some is temporary to allow for software systems development.

The specific goals of the 2013 ODC are:

  1. Test the RootSpy system in the counting house environment:
    • run monitoring processes on multiple nodes that read events from a common ET system and create root histograms
    • view summed monitoring histograms on at least 4 separate monitors in the counting room simultaneously
    • create archive (ROOT file) of summed monitoring histograms
    • read in and compare archived histograms via overlay with "live" histograms
  2. Test data rates of EVIO formatted raw data files:
    • use bggen generated data files that have been passed through a L1 event filter and converted into EVIO format that represents what is expected for the real data.
    • events will be read from a file and placed into ET system on a node designated as the Event Builder (EB) node.
    • L3 clients running on farm nodes will read events from EB node's ET system and write them to Event Recorder node (ER) running on the RAID disk.
  3. Test data rate to tape silo:
    • Files written to RAID disk will be transported to tape silo while simultaneously writing to the RAID disk.
  4. Test prototype L3 rejection algorithm
    • Justin will provide a prototype algorithm.
  5. Monitor health of farm and DAQ system nodes (counting house only) via farm monitoring software such as Ganglia.


Additional Goals


These goals will depend on the success of the goals listed above and the state of the software development at the time of the ODC.

  1. Test deferred processing system for L3:
    • Multiple nodes pulling events from EB node and writing to local files
    • Separate process on L3 nodes detect files, read them in and write ~10% of them to ER node where they are aggregated into single a file