1. Pegasus: Mapping complex applications onto the Grid Ewa Deelman Center for Grid Technologies USC Information Sciences Institute

2. Ewa DeelmanInformation Sciences Institute Pegasus Acknowledgements l Ewa Deelman, Carl Kesselman, Saurabh Khurana, Gaurang Mehta, Sonal Patil, Gurmeet Singh, Mei-Hui Su, Karan Vahi (Center for Grid Computing, ISI) l James Blythe, Yolanda Gil (Intelligent Systems Division, ISI) l http://pegasus.isi.edu http://pegasus.isi.edu l Research funded as part of the NSF GriPhyN, NVO and SCEC projects.

3. Ewa DeelmanInformation Sciences Institute Outline l The GriPhyN project and Puppy Applications l Workflow Management in Puppies l Pegasus, Planning for Execution in Puppies u Framework Description u Generation of Executable Workflows l Applications Using Pegasus l Future Research Directions

4. Ewa DeelmanInformation Sciences Institute iVDGL: Integrated CPU usage (CPU-days) during the 30 day running for SC2003, by VO.

5. Ewa DeelmanInformation Sciences Institute CMS cumulative use of Grid2003. The chart plots the distribution of usage (in CPU-days) by site in Grid2003 over a 150 day period beginning in November 2003.

6. Ewa DeelmanInformation Sciences Institute Distribution of the number of jobs run on Grid3 by month starting from October 2003.

7. Ewa DeelmanInformation Sciences Institute

8. GriPhyN Data Grid Challenge l Provide a framework that enables Virtual Organizations around the world to perform computationally demanding analysis of large, geographically distributed datasets. l The Virtual Organizations are large and highly distributed l The datasets are large, currently on the order of Terabytes and expected to grow to the level of 100s of Petabytes in the next decade l Provide a seamless access to data: experimental raw data or processed data products l Enable a user/application to ask for any domain-specific data, whether computed or not Concept of Virtual Data

9. Ewa DeelmanInformation Sciences Institute Grid Applications l Increasing in the level of complexity l Use of individual application components l Reuse of individual intermediate data products (files) l Description of Data Products using Metadata Attributes l Execution environment is complex and very dynamic u Resources come and go u Data is replicated u Components can be found at various locations or staged in on demand l Separation between u the application description u the actual execution description

10. Ewa DeelmanInformation Sciences Institute

11. Generating an Abstract Workflow l Available Information u Specification of component capabilities u Ability to generate the desired data products Select and configure application components to form an abstract workflow u assign input files that exist or that can be generated by other application components. u specify the order in which the components must be executed u components and files are referred to by their logical names l Logical transformation name l Logical file name l Both transformations and data can be replicated

12. Ewa DeelmanInformation Sciences Institute Generating a Concrete Workflow l Information u location of files and component Instances u State of the Grid resources l Select specific u Resources u Files u Add jobs required to form a concrete workflow that can be executed in the Grid environment l Data movement u Data registration u Each component in the abstract workflow is turned into an executable job

13. Ewa DeelmanInformation Sciences Institute Why Automate Workflow Generation? l Usability: Limit User’s necessary Grid knowledge l Monitoring and Directory Service l Replica Location Service l Complexity: u User needs to make choices l Alternative application components l Alternative files l Alternative locations u The user may reach a dead end u Many different interdependencies may occur among components l Solution cost: u Evaluate the alternative solution costs l Performance l Reliability l Resource Usage l Global cost: u minimizing cost within a community or a virtual organization u requires reasoning about individual user’s choices in light of other user’s choices

14. Ewa DeelmanInformation Sciences Institute GriPhyN’s Executable Workflow Construction l Build an abstract workflow based on VDL descriptions (Chimera) l Build an executable workflow based on the abstract workflows (Pegasus) l Execute the workflow (Condor’s DAGMan) VDL

15. Ewa DeelmanInformation Sciences Institute Chimera: Creating Abstract Workflows l Developed at ANL (Foster, Voeckler, Wilde) l Chimera’s Virtual Data Language (VDL) allows for the description of an abstract workflow l Transformations: u general description of the transformation applied to data, use logical transformation name TRgalMorph( in redshift, in pixScale, in zeroPoint, in Ho, in om, in flat, in image, out galMorph ) { … }

16. Ewa DeelmanInformation Sciences Institute Chimera : Creating Abstract Workflows l Derivations are instantiations of TRs u Identify particular logical input and output file names u Identify actual parameters DV d1->galMorph( redshift="0.027886", image=@{in:"NGP9_F323-0927589.fit"}, pixScale="2.831933107035062E-4", zeroPoint="0", Ho="100", om="0.3", flat="1", galMorph=@{out:"NGP9_F323-0927589.txt"} );

17. Ewa DeelmanInformation Sciences Institute Abstract Workflow Generation l Definitions for transformations and derivations are stored in Chimera’s Database l Database can be browsed l User queries Chimera giving it a logical filename

18. Ewa DeelmanInformation Sciences Institute VDL and Abstract Workflow VDL descriptions User request data file “c” Abstract Workflow

19. Ewa DeelmanInformation Sciences Institute Condor’s DAGMan l Developed at UW Madison (Livny) l Executes a concrete workflow l Makes sure the dependencies are followed l Executes the jobs specified in the workflow u Execution u Data movement u Catalog updates l Provides a “rescue DAG” in case of failure

20. Ewa DeelmanInformation Sciences Institute Pegasus: Planning for Execution in Grids l Maps from abstract to concrete workflow u Algorithmic and AI-based techniques l Automatically locates physical locations for both components (transformations) and data l Finds appropriate resources to execute l Reuses existing data products where applicable l Publishes newly derived data products u Chimera virtual data catalog u Provides provenance information

21. Ewa DeelmanInformation Sciences Institute

22. Information Components Used by Pegasus l Globus Monitoring and Discovery Service (MDS) u Locates available resources u Finds resource properties l Dynamic: load, queue length l Static: location of gridftp server, RLS, etc l Globus Replica Location Service u Locates data that may be replicated u Registers new data products l Transformation Catalog u Locates installed executables

23. Ewa DeelmanInformation Sciences Institute Example Workflow Reduction l Original abstract workflow l If “b” already exists (as determined by query to the RLS), the workflow can be reduced

24. Ewa DeelmanInformation Sciences Institute Mapping from abstract to concrete l Query RLS, MDS, and TC, schedule computation and data movement

25. Ewa DeelmanInformation Sciences Institute Applications Using Chimera, Pegasus and DAGMan l GriPhyN applications: u High-energy physics: Atlas, CMS (many) u Astronomy: SDSS (Fermi Lab, ANL) u Gravitational-wave physics: LIGO (Caltech, UWM) l Astronomy: u Galaxy Morphology (NCSA, JHU, Fermi, many others, NVO-funded) l Biology u BLAST (ANL, PDQ-funded) l Neuroscience u Tomography for Telescience(SDSC, NIH-funded)

26. Ewa DeelmanInformation Sciences Institute Pegasus interfaces l Main interface: command-line interface l Applications can also be integrated with a portal environment l Demonstrated the portal at SC 2003 u LIGO-gravitational-wave physics u Montage-astronomy l Much of the portal is application- independent

27. Ewa DeelmanInformation Sciences Institute Montage l Montage (NASA and NVO) u Deliver science-grade custom mosaics on demand u Produce mosaics from a wide range of data sources (possibly in different spectra) u User-specified parameters of projection, coordinates, size, rotation and spatial sampling. Mosaic created by Pegasus based Montage from a run of the M101 galaxy images on the Teragrid.

28. Ewa DeelmanInformation Sciences Institute Small Montage Workflow ~1200 nodes

29. Ewa DeelmanInformation Sciences Institute Montage Acknowledgments l Bruce Berriman, John Good, Anastasia Laity, Caltech/IPAC l Joseph C. Jacob, Daniel S. Katz, JPL l http://montage.ipac. caltech.edu/ http://montage.ipac l Testbed for Montage: Condor pools at USC/ISI, UW Madison, and Teragrid resources at NCSA, PSC, and SDSC. Montage is funded by the National Aeronautics and Space Administration's Earth Science Technology Office, Computational Technologies Project, under Cooperative Agreement Number NCC5-626 between NASA and the California Institute of Technology.

30. Ewa DeelmanInformation Sciences Institute

35. Conclusions l Pegasus maps complex workflows onto the Grid l Uses Grid information services to find resources, data and executables l Reduces the workflow based on existing intermediate products l Used in many applications l Part of GriPhyN’s Virtual Data Toolkit

36. Ewa DeelmanInformation Sciences Institute Future Directions l Incorporate AI-planning technologies in production software (Virtual Data Toolkit) l Investigate various scheduling techniques l Investigating fault tolerance issues u Selecting resources based on their reliability u Responding to failures l http://pegasus.isi.edu l http://www.griphyn.org/chimera l http://www.ivdgl.org