International Grid Communities

1
International Grid Communities

• Dr. Carl Kesselman
• carl_at_isi.edu
• Information Sciences Institute
• University of Southern California

2
The Grid Problem

• Resource sharing coordinated problem solving
  in dynamic, multi-institutional virtual
  organizations

3
Enabling International Cooperation

• International cooperation valuable, because
• Scale of Grid problem is large
• Expertise on both sides of Atlantic Pacific
• Important international applications
• Cost of noncooperation can be high
• Useful cooperation will not just happen but must
  be explicitly encouraged
• Substantial testbed application projects,
  jointly sponsored by EU, US, others
• Transatlantic Terabit Testbed, etc.
• International Virtual Data Grid Laboratory

4
Grid Forum

• IETF like body to codify standard practice
• Two meetings held so far, next in April
• European Grid forum established to address Europe
  specific issues

5
Layered Grid Architecture(By Analogy to Internet
Architecture)
Application
6
The Grid Physics Network

• Petabyte-scale computational environment for data
  intensive science
• CMS and Atlas Projects of the Large Hadron
  Collider
• Laser Interferometer Gravitational-Wave
  Observatory
• Sloan Digital Sky Survey (200 million objects
  each with 100 attributes)

7
Data Grids

• Integrate data archives into a distributed data
  management and analysis Grid
• More than storage network, also e.g.
• Caching and mirroring to exploit locality
• Intelligent scheduling to determine appropriate
  replica, site for (re)computation, etc.
• Coordinated resource management for performance
  guarantees
• Embedded security, policy, agent technologies for
  effective distributed analysis

8
Virtual Data Grids

• Only raw data must exist
• Dynamic data production
• Large extent and scale
• national or worldwide, multiple distance scales
• large numbers of resources
• Sophisticated new services
• Coordinated use of remote resources
• Transparency in data-handling and processing
• Optimize for cost, time, policy constraints,

9
Grid Communities ApplicationsData Grids for
High Energy Physics
Image courtesy Harvey Newman, Caltech
10
GriPhyn Architecture
Production Team
Individual Investigator
Other Users
Interactive User Tools
Virtual Data Tools
Request Planning and Scheduling Tools
Request Execution Management Tools
Other Grid Services
Resource Management Services
Security and Policy Services
Raw data source
Distributed resources (code, storage,computers,
and network)
11
GriPhyn Usage Scenario
Major Archive Facilities
Network caches regional centers
Local sites
?
12
iVDGL

• International Virtual-Data Grid Laboratory
• A place to conduct Data Grid tests at scale
• Concrete manifestation of world-wide grid
  activity
• Continuing activity that will drive Grid
  awareness
• A basis for further funding
• Scale of effort
• For national, intl scale Data Grid tests,
  operations
• Computationally and data intensive computing
• Fast networks
• Who
• Initially US-UK-EU Japan, Australia
• Other world regions later
• Discussions w/ Russia, China, Pakistan, India,
  South America

13
Structure of the iVDGL
14
iVDGL Architecture
Application Experiments
iGOC
Experiment Management
Experiment Scheduler
Experiment Data Collection
iVDGL Configuration Information
Health and Status Monitoring
iGLS
Access Control and Policy Services
iVDGL Monitoring Interface
iVDGL Mgmt. Interface
iVDGL Control Interface
Local Management Interface Interface
Compute Platform
Storage Platform
15
iVDGL Map Circa 2003-2004
16
iVDGL as a Laboratory

• Grid Exercises
• Easy, intra-experiment tests first (10-20,
  national, transatlantic)
• Harder wide-scale tests later (50-100 of all
  resources)
• Local control of resources vitally important
• Experiments, politics demand it
• Strong interest from other disciplines
• HEP NP experiments
• Virtual Observatory (VO) community in Europe/US
• Gravity wave community in Europe/US/(Japan?)
• Earthquake engineering
• Bioinformatics
• Computer scientists (wide scale tests)

17
Conclusions

• Application communities for major Grid
  experiments are international
• More communities then those mentioned
• International testbeds are coming
• Wires are only part of the solution
• Common middleware archecture enabling technology