No Slide Title

Download Report

Transcript No Slide Title

CEOS GRID
PROTOTYPING PROJECT
Presentation to Internet2 Member Meeting
Spring 2003
Marriott Crystal Gateway
April 9, 2003
Richard desJardins ([email protected])
NASA Research and Education Network
Kenneth McDonald ([email protected])
NASA Goddard Space Flight Center
Yonsook Enloe ([email protected])
SGT, Inc.
Allan Doyle ([email protected])
International Interfaces
April 2003
1
Summary of CEOS Grid Presentation &
Points of Contact (POCs)
•
CEOS, WGISS Background
– POC: [email protected]
•
CEOS Grid Prototyping Project
– POC: Yonsook Enloe ([email protected])
•
Network Team
– POC: [email protected]
•
Tech Team
– POC: Allan Doyle ([email protected])
•
Main Issues
– POC: Yonsook Enloe ([email protected])
•
Applications
–
–
–
–
–
–
April 2003
USGS Data Delivery – POC: Stu Doescher ([email protected])
NOAA NOMADS – POC: [email protected]
ESA Data Integration – POC: [email protected]
GSFC Advanced Data Grid – POC: [email protected]
GSFC/GMU EOSDIS Data Pools – POC: [email protected]
UAH Scientific Data Mining – POC: Sara Graves ([email protected])
2
Committee on Earth Observation Satellites
(CEOS)
• Committee on Earth Observation Satellites (CEOS) consists of world's
government agencies responsible for civil Earth observation (EO)
satellite programs, along with agencies that receive and process data
acquired remotely from space.
• Main goal of CEOS is to ensure that critical scientific questions related
to Earth observation and global change are covered, and that satellite
missions do not unnecessarily overlap each other.
• CEOS specific objectives:
– Cooperate in mission planning and in development of compatible data
products, services, applications, and policies.
– Provide focal point for international coordination of space-related EO
activities.
– Exchange policy and technical information to encourage complementarity
and compatibility of observation and data exchange systems.
• URL: www.ceos.org
• POC: [email protected]
April 2003
3
CEOS Working Group on Information
Systems and Services (WGISS)
•
•
WGISS Goal: To stimulate and coordinate the development of member
agency systems and services which manage and supply the data and
information from participating agency Earth observation (EO) missions.
WGISS specific objectives:
– Assist EO data provider agencies to maximize the usefulness, easy access and
application of EO data they gather and provide to diverse users worldwide.
– Address needs of EO data and information users by aiding development of
services that provide simpler and wider access to EO resources.
– Emphasis is on using demonstration projects involving user groups to identify
and solve critical interoperability issues associated with achievement of global
services.
•
•
•
April 2003
WGISS has developed tools, standards and services to assist access to and
use of EO data resources available online worldwide.
URL: wgiss.ceos.org
POC: [email protected]
4
WGISS - New Structure
Current Tasks:
WGISS
Technology
and Services
Subgroup
Current Tasks:
April 2003
International Directory
Network
CEOS Interoperable Catalog
System
Data Services
Networks
Archive
EOGEO Workshop
GRID
Developing Countries CD-ROM
CEOS Information Infrastructure
WGISS Test Environment
Projects and
Applications
Subgroup
Current Tasks:
Global Datasets
Global Mapping Book
WTF CEOP
WTF Core Sites (WGCV)
5
CEOS Grid Prototyping Project
• Oct 2002-March 2003: Phase 1
Establish CEOS Grid Technology Core Testbed
– Objectives:
• Establish an immediate Grid capability base within participating
CEOS agencies:
–
–
–
–
Grid software
Access to existing Grids
Pilot applications
Knowledgeable people
• April 2003-Sept 2003: Phase 2
Demonstrate CEOS Grid-enabled Applications
– Objectives:
• Demonstrate Grid-enabled applications, each involving at least two
CEOS agency sites.
• Show proof of concept.
• Evaluate benefits.
• Obtain lessons learned from infusion of Grid technologies from the
Technology Core into real CEOS agency information systems and
applications.
April 2003
6
CEOS Grid Prototyping Project, Cont’d.
• Fall 2003: Presentation to WGISS for approval to
continue project into second year
– Objectives:
• Report to WGISS on accomplishments and "So what?" from first
year.
• Present specific proposed project plan and get approval to continue to
second year.
• Oct 2003-Sept 2004: Phase 3
Create persistent CEOS Grid within WTFs
– Objectives:
• Infuse applicable Grid technologies into selected CEOS agency
information systems and WTFs, to create a persistent CEOS Grid that
would be available to support future CEOS agency initiatives.
April 2003
7
CEOS Grid Prototyping Project, Cont’d.
10/02
Techno logy C ore
Test Suite
April 2003
04/03
10/03
NOMADS
NOAA
Data Delivery
USGS
Data Integration
ESA
Advanced Data Grid
GSFC
EOSDIS
Data Pools
Scientific Data Mining
UAH
Pilot Apps
Full Apps
04/04
10/04
WTFs
Full Grid
8
CEOS Grid Prototyping Project, Cont’d.
NOAA NCDC
USGS EDC
UAH
April 2003
NASA GSFC
ESA ESRIN
GSFC/GMU
9
CEOS Grid Prototyping Project
Organization Chart
Technology and Services
SG
Wyn Cudlip
Network
Task Team (TT)
CEOS Grid Prototyping
TT
Jeff Smith
Yonsook Enloe
negotiated relationships
network support
Engineering and
Technical
Allan Doyle
USGS Data
Delivery
Stu Doescher
NOMADS
ESA Data
Integration
Glenn Rutledge
GSFC/GMU
EOSDIS Data Pools
Liping Di
April 2003
Existing Grids
• Information Power Grid
• Earth Systems Grid
• EU Data Grid and Data TAG
Ivan Petiteville
GSFC Advanced
Data Grid
Debbie Ladwig
UAH Scientific
Data Mining
Sara Graves
10
CEOS Grid Prototyping Project
Network Team
• Led by Goddard Space Flight Center (GSFC), supported by Ames
Research Center (ARC) NASA Research and Education Network
(NREN).
• "Virtual" CEOS Grid Prototyping Network is actually made up of
connectivity from several High Performance Research and Education
Networks (HPRENs), e.g., NASA Research and Education Network
(NREN), Energy Science Network (ESnet), Internet2 Abilene, European
HPRENs.
• Network team works to ensure adequate connectivity between testbed
nodes:
– Identify connectivity requirements (testbed network map).
– Perform network performance testing.
– Work to solve specific network connectivity problems as needed.
• Developed CEOS Grid Firewall Best Common Practices (BCP)
Document:
– Working with USGS to implement, test and refine document.
• POCs: [email protected], Dave Hartzell
([email protected])
April 2003
11
CEOS Grid Prototyping Project
Tech Team
• Focus is on:
– Establishing CEOS Grid Technology Core Testbed, including
defining, establishing, extending and documenting a base level of
functionality at each participating testbed node and organization.
• Summary Technical Work Plan:
– Carry out regular technical coordination via weekly telecons,
information exchange Web site, and
"[email protected]" email list.
– Learn from existing Grid contacts.
– Download free Grid software and install in testbed nodes.
– Define "template" for specifications and activities needed to
configure CEOS Grid core sites and partner sites.
– Connect testbed nodes into Initial CEOS Grid Virtual Organization
(VO).
April 2003
12
CEOS Grid Prototyping Project
Tech Team
• Summary Technical Work Plan, Continued:
– Define and execute core technology interoperability test suite
(automated for regular testing and measurement).
– Provide CEOS Grid Virtual Organization certificates to participants
(certificates will be supplied by NASA Information Power Grid),
and help applications negotiate access agreements with existing
Grid VOs.
– Assist application team leads to interconnect and interoperate their
application sites with existing Grid VOs and CEOS partner sites.
– Identify representatives to attend:
• Global Grid Forum (GGF) Applications and Testbeds Research Group
• OGC EO WG and Architecture SIG (which is beginning to focus on
Grid)
• APAN (Grid WG and Earth Monitoring WG)
April 2003
13
CEOS Grid Prototyping Project Main Issues
• POC: Yonsook Enloe ([email protected])
• CEOS Grid issues:
– Six application projects with widely differing application areas.
– Many issues are common to all six projects.
– Project team is working together to gain insight into these common
problems.
• Issue 1: Lack of Grid software how-to install and use documents:
– Team is producing how-to documentation: Grid Cookbook pages.
– 1st cookbook page: How to install and configure Globus 2.2.
– 2nd cookbook page: How to install and configure GridFTP with multiple
hosts and multiple clients.
– 3rd cookbook page (in progress): How to put simple applications on the
Grid.
• Issue 2: Lack of Grid expertise by participants:
– Grid Experts (IPG, . . .) are acting as consultants on various specialty
topics.
– Formed Tech Team to help each other and help later participants.
April 2003
14
Main Issues, Cont’d.
• Issue 3: Most agencies have firewalls. How to deal with these and how
to configure to allow access?
– Network Team is gathering requirements for firewalls and is drafting a
"CEOS Grid Firewall Best Practices" document.
– Technical POCs interested in this issue will review document with their
firewall administrators and will iterate on the document.
• Issue 4: Grid Monitoring:
– Network bandwidth performance testing and checkout of network routing
is being performed between testbed nodes.
– Several Grid Monitoring tools (Map Center, Ganglia, NWS) are being
studied and tried out.
– Map Center monitoring tool can monitor host machine ports and perform
process level monitoring.
– CEOS Grid application sites are linking to this tool to try it out (work in
progress).
April 2003
15
Main Issues, Cont’d.
•
Issue 5: Certificate Authority (CA): How should host and user certificates be
implemented in an international multi-agency consortium?
– Small tiger team formed to study issue with Grid expert.
– Procedure for CA has been drafted and is being reviewed.
– Planning to use certificates from multiple sources (work in progress).
•
Issue 6: Catalog Issues: Because EO data have huge volumes from many
sources, need a product catalog that is searchable and scalable. What kinds of
catalog components are available on the Grid and do these components have
the necessary capabilities for CEOS catalogs?
– Grid experts on SDSC SRB/MCAT and Globus MCS invited to give presentations
to entire team.
– Catalog Tiger team formed (small team to study and analyze catalog issues and
report back to the main team) (work in progress).
•
Issue 7: Putting EO applications on the Grid:
– Small tiger team formed to study this issue and prototype at least one approach.
– Prototyping OGC Web Map Server (WMS) and Web Coverage Server (WCS) on
the Grid.
– Will generate Cookbook page on putting WMS and WCS on the Grid.
April 2003
16
Application: USGS Data Delivery
• Led by USGS EROS Data Center (EDC) in Sioux Falls SD.
• Goal: Explore use of GRID technologies (primarily GridFTP and
Certificate Authority) for the delivery and reception of earth science
data.
• Application focus:
– Delivery of earth science data from EDC to scientific user community.
– Receiving data into the archive from producer/reception sites.
• Explore how Grid technologies would replace current technologies
being used:
– Physical media (tape cartridges, CD/ROMs), primitive network protocols
(semi-anonymous FTP and limited FTP push).
– Security is major concern.
• URL: Web site under development.
• POC: Stu Doescher ([email protected])
April 2003
17
Application: NOAA NOMADS
• NOAA Operational Model Archive and Distribution System
(NOMADS) goals:
– Develop distributed Grid framework, promoting standards across
multiple institutions.
– Provide access to climate and numerical weather prediction (NWP)
models for analysis and intercomparison.
– Foster research within geoscience communities to study complex earth
systems using multiple collections of distributed data.
• Led by National Climatic Data Center (NCDC), with support from
National Center for Environmental Prediction (NCEP), Geophysical
Fluid Dynamics Laboratory (GFDL), and over a dozen other major
collaborators.
• Grid technologies: GridFTP, Grid Information Service (GIS),
Certificates.
• URL: www.ncdc.noaa.gov/oa/climate/nomads/nomads.html
• POC: [email protected]
April 2003
18
Application: ESA Data Integration
• Led by European Space Agency (ESA) European Space Research
Institute (ESRIN).
• Developing Grid Portal for Earth Science Applications Browser:
– Interfacing to EU DataGrid, DOE Earth System Grid, other data warehouses,
OpenGIS Consortium (OGC) Web Services (OWS).
• Interfaces CEOS interoperability technologies with Grid environments to
support on-demand user-driven data integration:
– Catalogue Interoperability Protocol (CIP), Web Map Server (WMS), Archive
Data Management, Selection and transfer of data, On-demand data product
generation, Data product visualization.
• HTML user interface implemented using client application with generic
functions developed in JavaScript.
• URL: giserver.esrin.esa.int
• POC: [email protected]
April 2003
19
Application: NASA GSFC Advanced Data
Grid (ADG)
•
Led by NASA Goddard Space Flight Center (GSFC):
– Systems engineering, architecture and implementation support from Aerospace
Corporation and GST Inc.
– Grid support (Certificate Authority services and Grid resources and services) from
NASA Ames Research Center (ARC) Information Power Grid.
– Relationship with EOSDIS Data Pools Project.
•
Primary Goals:
– Assess scalability of Grid architecture/implementation for Earth Science Data
Segment data life cycle management and workflow (primary focus on Data Grid
issues, not Compute Grid issues).
– Demonstrate realistic science application of relevance to NPP mission
(www.jointmission.gsfc.nasa.gov) in fully Grid-enabled environment.
•
Technologies:
– Globus Toolkit
– Storage Resource Management: SDSC SRB/MCAT, LBNL SRM, Globus MCS,
related tools. \
– Grid monitoring tools as required (e.g., ganglia).
•
Data and Metadata:
– Primarily EOS Data (MODIS) from Terra and Aqua Satellites, ECS Metadata
Schema.
•
•
April 2003
URL: Web site under development.
POC: [email protected]
20
Application: NASA GSFC/GMU EOSDIS
Data Pools
•
•
Led by NASA Earth Observing System (EOS) Data and Information System (DIS)
Project at NASA Goddard Space Flight Center (GSFC), with technology development
and testbed at George Mason University (GMU).
Goal is to demonstrate integration of Grid and OpenGIS Consortium (OGC) Web
Services (OWS):
–
–
–
•
•
•
•
April 2003
Provide interoperable, personalized, on-demand data access and services.
Initial focus is on the NASA/EOSDIS Data Pools environment at four EOS Distributed Active
Archive Centers (DAACs): Goddard Space Flight Center (GSFC), Langley Research Center
(LaRC), National Snow and Ice Data Center (NSIDC) at University of Colorado at Boulder,
EROS Data Center (EDC).
Technology development site is at GMU Laboratory for Advanced Information Technology and
Standards (LAITS).
Integrate NASA HDF-EOS (EOSDIS standard data format) Web GIS Software Suite
(NWGISS), which provides OGC web map, coverage and registries services, with Grid
technologies which provide security, resource access and management, Grid
information/monitoring, data access/transfer.
Work with Grid teams at Argonne National Laboratory (ANL) and NASA Ames Research
Center to make Globus geospatial enabled and OGC interface compatible.
URL: laits.gmu.edu
POC: [email protected]
21
Application: UAH/NSSTC Scientific Data
Mining
•
•
Led by University of Alabama in Huntsville (UAH) Information Technology and
Systems Center (ITSC) data mining tools using Earth Science data from the National
Space Science and Technology Center (NSSTC) and other data centers
Explore use of Grid software tools and resources for compute-intensive data mining and
machine learning applications in the earth sciences:
–
–
–
–
•
•
•
April 2003
Investigate Grid-enabled data mining issues, e.g., Grid resource monitoring and intelligent
scheduling, to manage distributed data and compute resources in support of scientific data
mining.
Science focus is on developing supervised classifier of storm characteristics to identify
dangerous storms with potential for heavy lightning.
Leverage substantial UAH data mining expertise and software.
Leverage ITSC testbed for NSF Middleware Initiative (NMI), to provide visibility into NMI for
CEOS Grid developers, and to provide earth science and spatial data requirements and
feedback to NMI middleware development and support team.
Grid technologies: Globus Toolkit (Globus Packaging Technology (GPT), Grid
Resource Information Service (GRIS), GridResource Allocation Manager (GRAM),
GridFTP, Monitoring and Discovery System (MDS),Grid Security Infrastructure (GSI)),
Network Weather Service (NWS), Condor-G.
URL: www.itsc.uah.edu/about.html
POC: Sara Graves ([email protected])
22