P. Kacsuk, G. Sipos, A. Toth, Z. Farkas, G. Kecskemeti and G. Hermann P. Kacsuk, G. Sipos, A. Toth, Z. Farkas, G. Kecskemeti and G. Hermann MTA SZTAKI.

Slides:



Advertisements
Similar presentations
Enabling the execution of various workflows (Kepler, Taverna, Triana, P-GRADE) on EGEE Tamas Kukla, Tamas Kiss, Gabor Terstyanszky.
Advertisements

1 CEOS WGISS Meeting, May 8-12, 2006, Budapest MTA SZTAKI Computer and Automation Research Institute Hungarian Academy of Sciences
EGEE-II INFSO-RI Enabling Grids for E-sciencE EGEE and gLite are registered trademarks Introduction to EGEE hands-on Gergely Sipos.
1 P-GRADE Portal and GEMLCA Legacy Code Architecture Peter Kacsuk MTA SZTAKI
Legacy code support for commercial production Grids G.Terstyanszky, T. Kiss, T. Delaitre, S. Winter School of Informatics, University.
LPDS MTA SZTAKI Equation Solver A Grid solution Important hint: A follow up example demonstrating the Parameter Study solution for the mass calculations.
P-GRADE and WS-PGRADE portals supporting desktop grids and clouds Peter Kacsuk MTA SZTAKI
Introduction to Grids and Grid applications Gergely Sipos MTA SZTAKI
06/08/10 PBS, LSF and ARC integration Zoltán Farkas MTA SZTAKI LPDS.
MTA SZTAKI Hungarian Academy of Sciences Grid Computing Course Porto, January Introduction to Grid portals Gergely Sipos
WS-PGRADE: Supporting parameter sweep applications in workflows Péter Kacsuk, Krisztián Karóczkai, Gábor Hermann, Gergely Sipos, and József Kovács MTA.
1 MTA SZTAKI Hungarian Academy of Sciences Grid application support by the P-GRADE Portal Peter Kacsuk.
Porto, January Grid Computing Course Summary of day 2.
1 portal.p-grade.hu További lehetőségek a P-GRADE Portállal Gergely Sipos MTA SZTAKI Hungarian Academy of Sciences.
SCI-BUS is supported by the FP7 Capacities Programme under contract nr RI WS-PGRADE/gUSE Supporting e-Science communities in Europe Zoltan Farkas.
INFSO-RI SZTAKI’s Exploitation plan AHM meeting Budapest, 23 June 2009 Peter Kacsuk, Robert Lovas MTA SZTAKI.
1 portal.p-grade.hu Further information on P-GRADE Gergely Sipos MTA SZTAKI Hungarian Academy of Sciences.
EGEE-II INFSO-RI Enabling Grids for E-sciencE Grid application development with gLite and P-GRADE Portal Miklos Kozlovszky MTA SZTAKI.
SCI-BUS is supported by the FP7 Capacities Programme under contract nr RI Creating the Autodock gateway from WS-PGRADE/gUSE and making it cloud-enabled.
From P-GRADE to SCI-BUS Peter Kacsuk, Zoltan Farkas and Miklos Kozlovszky MTA SZTAKI - Computer and Automation Research Institute of the Hungarian Academy.
INFSO-RI Enabling Grids for E-sciencE Supporting legacy code applications on EGEE VOs by GEMLCA and the P-GRADE portal P. Kacsuk*,
Introduction to WS-PGRADE and gUSE Tutorial Akos Balasko 04/17/
Supported by EU projects 12/12/2013 Athens, Greece Open Data in Agriculture Hands-on with data infrastructures that can power your agricultural data products.
1 Advanced features of the P-GRADE portal Peter Kacsuk, Gergely Sipos Peter Kacsuk, Gergely Sipos MTA.
Grid Execution Management for Legacy Code Applications Grid Enabling Legacy Code Applications Tamas Kiss Centre for Parallel.
EGEE-III INFSO-RI Enabling Grids for E-sciencE Training services offered by SZTAKI for EGEE and EGI Gergely Sipos MTA SZTAKI (Hungarian.
MTA SZTAKI Hungarian Academy of Sciences Introduction to Grid portals Gergely Sipos
P-GRADE and GEMLCA.
1 P-GRADE Portal: a workflow-oriented generic application development portal Peter Kacsuk MTA SZTAKI, Hungary Univ. of Westminster, UK.
Grid Execution Management for Legacy Code Applications Grid Enabling Legacy Applications.
EGEE-II INFSO-RI Enabling Grids for E-sciencE EGEE and gLite are registered trademarks Status report on Application porting at SZTAKI.
Parameter Study Principles & Practices. What is Parameter Study? Parameter study is the application of a single algorithm over a set of independent inputs:
EGEE-III INFSO-RI Enabling Grids for E-sciencE EGEE and gLite are registered trademarks Services for advanced workflow programming.
1 P-GRADE Portal: An easy to use graphical interface for Globus and EGEE Grids.
1 P-GRADE Portal tutorial at EGEE’09 Introduction to hands-on Gergely Sipos MTA SZTAKI EGEE.
The SEE-GRID-SCI initiative is co-funded by the European Commission under the FP7 Research Infrastructures contract no Workflow repository, user.
1 Practical information for the GEMLCA / P-GRADE hands-on Gergely Sipos On behalf of: MTA.
1 Practical information for the GEMLCA / P-GRADE hands-on Tamas Kiss University of Westminster.
06/08/10 P-GRADE Portal and MIMOS P-GRADE portal developments in the framework of the MIMOS-SZTAKI joint project Mohd Sidek Salleh MIMOS Berhad Zoltán.
EGEE-II INFSO-RI Enabling Grids for E-sciencE Introduction to P-GRADE Portal hands-on Miklos Kozlovszky MTA SZTAKI
1 portal.p-grade.hu Workflow and parameter study management by P-GRADE Portal Gergely Sipos MTA SZTAKI Hungarian Academy of Sciences.
EGEE-II INFSO-RI Enabling Grids for E-sciencE P-GRADE overview and introduction: workflows & parameter sweeps (Advanced features)
1 Other features and next steps Gergely Sipos MTA SZTAKI Hungarian Academy of Sciences.
1 Support for Parameter Study applications in the P-GRADE Portal Cevat Şener Dept. Of Computer Engineering, METU.
1 P-GRADE Portal hands-on Gergely Sipos MTA SZTAKI Hungarian Academy of Sciences.
1 Porting applications to the NGS, using the P-GRADE portal and GEMLCA Peter Kacsuk MTA SZTAKI Hungarian Academy of Sciences Centre for.
1 Further information and next steps Further information and next steps Gergely Sipos MTA SZTAKI
EGEE-II INFSO-RI Enabling Grids for E-sciencE EGEE and gLite are registered trademarks Interfacing gLite services with the Kepler.
07/02/2012 WS-PGRADE/gUSE in use Lightweight introduction Zoltán Farkas MTA SZTAKI LPDS.
WS-PGRADE/gUSE in use Advance use of WS- PGRADE/gUSE gateway framework Zoltán Farkas and Peter Kacsuk MTA SZTAKI LPDS.
Grid Execution Management for Legacy Code Architecture Exposing legacy applications as Grid services: the GEMLCA approach Centre.
1 P-GRADE Portal and Developer Alliance Gergely Sipos MTA SZTAKI Hungarian Academy of Sciences portal.p-grade.hu.
1 Support for parameter study applications in the P-GRADE Portal Gergely Sipos MTA SZTAKI (Hungarian Academy of Sciences)
Introduction to Grid and Grid applications Peter Kacsuk MTA SZTAKI
1 Tutorial Outline 30’ From Content Management Systems to VREs 50’ Creating a VRE 80 Using a VRE 20’ Conclusions.
Exposing WS-PGRADE/gUSE for large user communities Peter Kacsuk, Zoltan Farkas, Krisztian Karoczkai, Istvan Marton, Akos Hajnal,
Tamas Kiss University Of Westminster
Flowbster: Dynamic creation of data pipelines in clouds
How to connect your DG to EDGeS? Zoltán Farkas, MTA SZTAKI
P-GRADE overview and introduction: workflows & parameter sweeps (Advanced features) Gergely Sipos MTA SZTAKI
P-GRADE Portal tutorial
Grid Application Support Group Case study Schrodinger equations on the Grid Status report 16. January, Created by Akos Balasko
Introduction to P-GRADE Portal hands-on
Peter Kacsuk MTA SZTAKI
P-GRADE and GEMLCA.
Lightweight introduction
Lightweight introduction
Application development on EGEE with P-GRADE Portal
Introduction to the SHIWA Simulation Platform EGI User Forum,
Workflow level parametric study support by the P-GRADE portal
Presentation transcript:

P. Kacsuk, G. Sipos, A. Toth, Z. Farkas, G. Kecskemeti and G. Hermann P. Kacsuk, G. Sipos, A. Toth, Z. Farkas, G. Kecskemeti and G. Hermann MTA SZTAKI Defining and Running Parametric Study Workflow Applications by the P-GRADE Portal

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 2 Outline of the talk 1.Introduction to P-GRADE portal 2.PS-extension motivations 3.Principles of the PS-portal 4.Usage of the PS-portal 5.Distributing workflows among different Grid resources 6.Conclusions

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 3 Proxy management P-GRADE portal in a nutshell Definition of Grid resources Workflow creation Job mapping to Grid resources Workflow management and execution visualization

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 4 References P-GRADE Portal service is available for –Central European VO of EGEE –GILDA: Training VO of EGEE –HUNGRID VO of EGEE –SEE-GRID infrastructure –GIN VO –National Grids (UK National Grid Service, HunGrid, etc.) Under preparation for –US Open Science Grid, TeraGrid –Economy-Grid, Swiss BioGrid, Bio and Biomed EGEE VOs, BioInfoGrid, BalticGrid –Many national Grids

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 5 User’s feedback Users want parameter study (PS) support at workflow level It means: –If the user has an existing workflow in a repository, he would like to run the same workflow (without any change) with many different parameters

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 6 Related research 1.PS at job level – main subject is scheduling 2.PS at workflow level – The workflow description supports the creation of PS runs 3.What our users want: executing workflows stored in workflow repositories with many inputs as PS

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 7 Principles of the PS-portal 1. Take the existing workflow as a black box 2. Modify only the external input ports to accept many input files 3. Create the cross-product of the input files and run the workflow with all combinations 4. Because of the large number of files both PS inputs and outputs are stored in the Grid! Storage elements 4 input files 3 input files 12 output files

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 8 Generating cross products and executable workflows (e-WFs) PS port: 4 instances of the input file PS port: 3 instances of the input file = 4 x 3 normal workflow execution 1 PS workflow execution

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 9 Steps of creating a PS-workflow 1. Start from a tested Workflow

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies Define the PS Port(s) Any external input port can be defined as PS- port

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 11 3.Define Subdirectory of Inputs PS port is represented by a directory and not by a single file

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies Define target Grid and subdirectory for the results

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies PS Workflow ready to Submit

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 14 Progress of submissions in PS detailed view Total = Init + Submitted + Rescue + Error + Finished

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 15 How to distribute workflows among different Grid resources? PS port: 4 instances of the input file PS port: 3 instances of the input file = Goal: Assign the 24 jobs to 24 different Grid resources 1 PS workflow execution

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 16 Single-Grid, Static Assignment PS port: 4 instances of the input file PS port: 3 instances of the input file = Assigns the 24 jobs to 2 Grid Resources within 1 Grid 1 PS workflow execution Assign resource A in Grid X Assign resource B in Grid X A A AA A A AA A A A A B B BB B B BB B B BB

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 17 Single-Grid, Dynamic Assignment via Broker PS port: 4 instances of the input file PS port: 3 instances of the input file = 1 PS workflow execution Assign to broker of Grid X Assign to broker of Grid X A B CD I J KL R S T V E F GH M N OP U X YZ Assigns the 24 jobs to 24 Grid Resources within 1 Grid

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 18 P-GRADE-Portal London Rome Athens TeraGrid (GT2/GT4) SEE-Grid (glite) P-GRADE portal is a multi-Grid portal

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 19 Static Multi-Grid Assignment PS port: 4 instances of the input file PS port: 3 instances of the input file = 1 PS workflow execution Assign to broker of Grid X Assign to broker of Grid Y XA XB XCXD XI XJ XKXL XR XS XT XV YE YF YGYH YM YN YOYP YU YX YYYZ Assigns the 24 jobs to 24 Grid Resources within 2 Grids

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 20 Dynamic Multi-Grid Assignment PS port: 4 instances of the input file PS port: 3 instances of the input file = 1 PS workflow execution Assign to meta-broker Assign to meta-broker XA XB YCXD YI XJ XKXL XR XS XT YV YE XF YGXH YM XN YOYP YU YX YYXZ Assigns the 24 jobs to 24 Grid Resources within 2 Grids

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 21 Conclusions Our solution: 1.Keeps both the workflow GUI and the parameter study support concept as simple as possible. 2.Enables run any existing workflow with different parameter sets without modifying the structure of the workflow. 3.Manages the execution of the workflows on as many Grid resources as possible. 4.Enables the collection of Grid resources from several Grids even if they are based on different Grid technology.

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 22 Thanks for your attention ? Further information:

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 23 Distributing workflows among different Grid resources 1.Single-Grid, Static Assignment: Statically assigning each node of the workflow to different resources in the same Grid (done) 2.Single-Grid, Dynamic Assignment: Dynamically assigning each node of the workflow to different resources in the same Grid using the broker of the Grid (done) 3.Static multi-Grid Assignment: Statically assigning different Grids to different nodes (done) 4.Dynamic multi-Grid Assignment: Dynamically assigning the nodes to different Grids using a meta-broker (under investigation)

European Research Network on Foundations, Software Infrastructures and Applications for large scale distributed, GRID and Peer-to-Peer Technologies 24 Multi-Grid portals with meta-broker EGEE Grid UK NGS Broker Broker Meta- Broker Selects Grid for each node of the PS workflow Provides the largest achievable parallelism for PS workflows