June 21, PROOF - Parallel ROOT Facility Maarten Ballintijn, Rene Brun, Fons Rademakers, Gunter Roland Bring the KB to the PB not the PB to the KB

June 21, PROOF in a Slide Interactive Physics Analysis of Large Data Sets using Parallel Processing and I/O Transparency, Adaptability, Scalability Integrated into ROOT, Known Paradigm Adapt to Network and System Performance, support Heterogeneous systems Efficiency and Reliability Multi Tier architecture, Data Locality WAN Ready and GRID compatible Internet Master Slave User

June 21, PROOF Features Selector framework Transparent way to program analysis Universally applicable, local, PROOF, batch Extensible, combine with TTask ? TDSet data description Lightweight, easily created from CLI Versatile

June 21, PROOF Features Packages Extend and customize environment Efficient and heterogeneous Feedback Simple progress bar Flexible feedback mechanism

June 21, PROOF in the Pipeline Continuing Grid Integration Authentication ready, Catalogs, Resource Broker Dynamic Session Configuration Plugin Requested Data Set, Resource Availability Feature additions and Improvements TTree::Draw(), Friend Trees, Event lists Tuning and improved error handling

June 21, PROOF and Condor COD, Computing On Demand Batch and Interactive coexist Explicit scheduling Better Interactive Response Optimize resource usage Resource broker Allocate Compute resources Allocate Data Storage resources

June 21, PROOF and COD Condor Slave Batch Master Condor SlaveBatch Condor Batch Condor

June 21, Software Architecture Philosophy General principles remain valid even as bandwidth, latency and capacity grow We must benefit from what we and others (!) have learned Models of usage Silver bullets do not exist Methodology, Environments, Languages Prototype is easy, production quality is hard