PRAGMA: Cyberinfrastructure, Applications, People

Yoshio Tanaka (AIST, Japan)Peter Arzberger (UCSD, USA)

PRAGMA’s Founding Motivations

• The grid is transforming computing and collaboration

• The problem remains that the grid is too hard to use

• Middleware software needs to interoperate

• Science is an intrinsically global activity

IVOA

Overarching GoalsEstablish sustained collaborations

and

Advance the use of the grid technologies for applications

among a community of investigators working with leading institutions around the Pacific

Rim

PRAGMA

Working closely with established activities that promote grid activities or the underlying infrastructure,

both in the Pacific Rim and globally.

PRAGMA PARTNERS

Affiliate Member

Key Activities and Outcomes

• Encourage and conduct joint (multilateral) projects that promote development of grid facilities and technologies

• Share resources to ensure project success• Conduct multi-site training• Exchange researchers

• Advance scientific applications• Create grid testbeds for regional e-science projects• Contribute to the international grid development efforts• Increase interoperability of grid middleware in Pacific

Rim and throughout the world

Act

ivit

ies

Ou

tcom

e s

Contents:2004-2005

• Overview• Accomplishments• PRIME• Working Groups• Institutions• References• Opportunities• Sponsors

http://www.pragma-grid.net

Working Groups: Integrating PRAGMA’s Diversity

• Telescience – including Ecogrid• Biological Sciences:

– Proteome Analysis using iGAP in Gfarm

• Data Computing– Online Data Processing of

KEKB/Belle Experimentation in Gfarm

• Resources– Grid Operations center

A collaborative effort in the fight against bio-terrorism

• Gfarm makes it possible to use iGAP to analyze the complete proteome (available 9/28/04) of the bacteria, Burkholderia mallei, a known biothreat agent, on distributed international resources.

• This is a collaboration under PRAGMA and the data is available through http://eol.sdsc.edu.

Source: Cindy Zheng

PRAGMA Grid Testbed – overview –

• Establish a regional wide testbed– Mainly focusing on computational Grid, later

introduce other resources– Provides an easy-access environment for

researchers, students, vendors, etc.– Testbed for software development and trial to have

evaluation of usability and to archive performance numbers

– Testbed for finding demonstrative / feasible applications

– is going to be a production Grid

PRAGMA Grid Testbed – unique features – • Truly (naturally) multi national/political/institutional VO

beyond boundaries– Not an application-dedicated testbed – general platform– Diversity of languages, culture, policy, interests, …

• Grid BYO – Grass roots approach– Each institution contributes his resources for sharing– Not a single source funded for the development

• Physical resources– Most contributed resources are small-scale clusters– Networking is there, however the bandwidth is not enough

• We can– have experiences on running international VO– verify the feasibility of this approach for the testbed development

言語と文字

Lessons Learned thru developments

• Difficulties are caused by technical problems as well as sociological/political problems

• Each site has its own policy– account management– firewalls– trusted CAs– …

• Differences in interests– Application, middleware, networking, etc.

• Differences in culture, language, etc.– Human interaction is very important

Building a Production Grid Thru Running Applications

• Routine-basis experiments– Ninf-G based TDDFT, http://pragma-

goc.rocksclusters.org/tddft/default.html– BioGrid,

http://pragma-goc.rocksclusters.org/biogrid/default.html

– iGAP over Gfarm

• Learn requirements/issues• Research/implement solutions• Improve middleware integrations

Source: Cindy Zheng

Status of Testbed in May, 2004Computational resource

26 organizations (10 countries)27 clusters (889 CPUs)Network performance is getting better.

Architecture, technologyBased on Globus Toolkit (mostly version 2)Ninf-G (GridRPC programming)Nimrod-G (parametric modeling system)SCMSWeb (resource monitoring)Grid Data FArm (Grid File System), etc.

Operation policyDistributed management (No Grid Operation Center)Volunteer-based administration

Less duty, less formality and less documents

Status of Testbed in May, 2004 (cont’d)

Questions???Ready for real science application?

Easy to use for every user?Reliable environment?Middleware stability?Plenty document?Enough security?

and etc.

Direction of PRAGMA Resource Working GroupDo “Routine-basis Experiments”

Try daily application runs for a long termFind out any problems and difficultyLearn what is necessary for the production grid

Overview of Routine-Basis Exp.Purpose

By daily runs of a sample application on PRAGMA testbed, find out and understand issues of the testbed operation for the real science application

Case study: the 1st applicationApplication

Time-Dependent Density Functional Theory (TDDFT)Software requirements of TDDFT are Ninf-G, Globus and Intel Fortran Compiler.

ScheduleJune 1, 2004 ~ August 31, 2004 (For 3 months)

Participants10 Sites (in 8 countries): AIST, SDSC, KU, KISTI, NCHC, USM, BII, NCSA, TITECH, UNAM193 CPUs (on 106 nodes)

Rough ScheduleMay June July Aug

SC’04

Sep Oct Nov

PRAGMA6

1st App. start

1st App. end

PRAGMA7

2nd App. startSetup Resource Monitor (SCMSWeb)

1. Apply account

2. Deploy application codes

3. Simple test at local site

4. Simple test between 2 sites

Join in the main executions after all’s done

2 sites 5 sites 8 sites 10 sites

2nd user start executions

Summary of the experimentNumber of executions : 43Execution time (Total) : 50.4 days (Max) : 6.8 days (Ave) : 1.2 days

Lessons Learned from the point of view of testbed operation

Need to reduce user’s effortMore documentsNeed common configurations on each clusterShould know the requirements of many applicationsMore collaboration among administrators from each site

Need to monitor site-to-site networkProblem: Very unstable network between AIST and some

sitescollaboration with networking community is important

e.g. APAN NOC

Need to monitor each cluster’s statusProblem: Don’t know maintenance? trouble? network down?

SCMSWeb will help this issue.Periodical status tests

Network Weather Maphttp://mrtg.koganei.itrc.net/mmap/grid.html

Thanks: Dr. Hirabaru and APAN Tokyo NOC team

Summary

• Dream big – build the imagination of those involved

• Start small - build trust• Stay concrete – build infrastructure• Focus on people – build community

• Opportunities: – Networking and Measurements– Testbed: Mutual learning– Applications: Geosciences, Astronomy, Ecology,

Biomedicine, …– Exchange: Undergraduates and Graduates– Participate in Meetings and between meetings

Thank you

http://www.pragma-grid.net

Office of International Science and Engineering Division of Shared Cyberinfrastructure

Division of Biological Infrastructure