Some Grid ExperiencesLaura Pearlman
USC Information Sciences Institute
ICTP Advanced Training Workshop on Scientific Instruments on the Grid
*Most of these slides are from Lee Liming’s GlobusWorld 2006 presentation “A Globus® Primer: What is the Grid and How Do I Use
It?”
GlobusWORLD 2006 Globus Primer 2
To be Covered
I. Grid computing problems
II. Some notable U.S. Grids
III. How grids are built and used in real life
GlobusWORLD 2006 Globus Primer 3
Grid Computing Problems Scientific problems that are big enough that they require
people in several organizations to collaborate and share computing resources, data, and instruments.
Interactive simulation (climate modeling) Very large-scale simulation and analysis (galaxy formation, gravity
waves, battlefield simulation) Engineering (parameter studies, linked component models) Experimental data analysis (high-energy physics) Image and sensor analysis (astronomy, climate study, ecology) Online instrumentation (microscopes, x-ray devices, etc.) Remote visualization (climate studies, biology) Engineering (large-scale structural testing, chemical engineering) Biomedical applications
GlobusWORLD 2006 Globus Primer 4
Some Core Problems - Heterogeneity Different authentication mechanisms across institutions Different mechanisms for monitoring system and
application status across institutions Different ways to submit jobs Different ways to store & access files and data Different ways to keep track of data Different preferences in programming languages and
environments Difficulty in tracking the causes of failures Conflicting requirements among groups that need to
interoperate
GlobusWORLD 2006 Globus Primer 5
Some Core Problems - Trust
Rigid use policies (authorization, QoS) vs rigid application assumptions.
Authorization needs to happen at many levels (communities, organizations, resource owners, etc.).
Complicated social structures exceed the abilities of simple authorization systems.
GlobusWORLD 2006 Globus Primer 7
Earth System Grid
Goal: Give climate scientists easier access to the distributed data and resources that they require to perform their research.
Developed new technologies for (1) creating and operating "filtering servers" capable of performing sophisticated analyses, and (2) delivering results to users.
GlobusWORLD 2006 Globus Primer 8
Collaborative Engineering: NEES
2
Network for Earthquake Engineering Simulation
Field Equipment
Laboratory Equipment
Remote Users
Remote Users: (K-12 Faculty and Students)
High-Performance Network(s)
Instrumented Structures and Sites
Leading Edge Computation
Curated Data Repository
Laboratory Equipment (Faculty and Students)
Global Connections(fully developed
FY 2005 –FY 2014)
(Faculty, Students, Practitioners)
U.Nevada Reno
www.neesgrid.org
GlobusWORLD 2006 Globus Primer 9
UCSD UT
UC/ANL
NCSA
PSC
ORNL
PU
IU
A National Science Foundation Investment in Cyberinfrastructure
$100M 3-year construction (2001-2004)$150M 5-year operation &
enhancement (2005-2009)
NSF’s TeraGrid*
TeraGrid DEEP: Integrating NSF’s most powerful computers (60+ TF)
2+ PB Online Data Storage National data visualization facilities World’s most powerful network (national
footprint)TeraGrid WIDE Science Gateways:
Engaging Scientific Communities 90+ Community Data Collections Growing set of community partnerships
spanning the science community. Leveraging NSF ITR, NIH, DOE and other
science community projects. Engaging peer Grid projects such as Open
Science Grid in the U.S. as peer Grids in Europe and Asia-Pacific.
Base TeraGrid Cyberinfrastructure:Persistent, Reliable, National
Coordinated distributed computing and information environment
Coherent User Outreach, Training, and Support Common, open infrastructure services
* Slide courtesy of Ray Bair, Argonne National Laboratory
GlobusWORLD 2006 Globus Primer 10
Open Science Grid $30M over five years for effort to
sustain and evolve the distributed facility, bring on board new communities & capabilities, educate & train.
OSG hardware resources, applications and many other contributions come from OSG consortium members.
OSG technical work is performed together with collaborators & external projects
OSG has partners in Africa, Asia, Europe, North and South America.
Text for this slide courtesy of Ruth Pordes
GlobusWORLD 2006 Globus Primer 11
OSG Partners Autralian Partnerships for Advanced Computing (APAC) Data Intensive Science University Network (DISUN) Enabling Grids for E-SciencE (EGEE) Grid Laboratory of Wisconsin (GLOW) Grid Operations Center at Indiana University Grid Research and Education Group at Iowa (GROW) Nordic Data Grid Facility (NorduGrid) Northwest Indiana Computational Grid (NWICG) New York State Grid (NYSGrid) (in progress). TeraGrid Texas Internet Grid for Research and Education (TIGRE) TWGrid (from Academica Sinica Grid Computing) Worldwide LHC Computing Grid Collaboration (WLCG)
Slide courtesy of Ruth Pordes, OSG All Hands Meeting 2007
GlobusWORLD 2006 Globus Primer 12
100 Resources across
production & integration infrastructures
!ncrease in ~15 since Seattle
27 Virtual Organizations (+ 3 operations VOs)
25% non-physics.
~20,000 cores (from 30 to 4000 cores per cluster)
~6 PB accessible Tapes
~4 PB Shared Disk
Sustaining through OSG submissions:
Measuring ~180K CPUhours/day.
~Factor of 50% more (being measured) than in Seattle
Using production & research networks
OSG Snapshot
Slide courtesy of Ruth Pordes, OSG All Hands Meeting 2007
GlobusWORLD 2006 Globus Primer 15
Methodology Building a Grid system or application is currently an
exercise in software integration. Define user requirements Derive system requirements or features Survey existing components Identify useful components Develop components to fit into the gaps Integrate the system Deploy and test the system Maintain the system during its operation
This should be done iteratively, with many loops and eddies in the flow.
GlobusWORLD 2006 Globus Primer 16
What End Users NeedSecure, reliable, on-demand access to data,software, people, and other resources(ideally all via a Web Browser!)
GlobusWORLD 2006 Globus Primer 17
How it Happens
WebBrowser
ComputeServer
DataCatalog
DataViewer
Tool
Certificateauthority
ChatTool
CredentialRepository
WebPortal
ComputeServer
Resources implement standard access & management interfaces
Collective services aggregate &/or
virtualize resources
Users work with client applications
Application services organize VOs & enable
access to other services
Databaseservice
Databaseservice
Databaseservice
SimulationTool
Camera
Camera
TelepresenceMonitor
RegistrationService
GlobusWORLD 2006 Globus Primer 18
How it Happens
Implementations are provided by a mix of Application-specific code “Off the shelf” tools and services Tools and services from the Grid community
(Globus + others using the same standards) Glued together by…
Application development System integration
GlobusWORLD 2006 Globus Primer 19
The Importance of Community All Grid technology is evolving rapidly.
Web services standards Grid interfaces Grid implementations Grid resource providers (ASP, SSP, etc.)
Community is important! Best practices (OGF, OASIS, etc.) Open source (Linux, Axis, Globus, etc.)
Application of community standards is vital. Increases leverage Mitigates (a bit) effects of rapid evolution Paves the way for future integration/partnership