Download - What is a Grid? - ITU
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
International Telecommunication UnionITU-T
What is a Grid?What is a Grid?
Dave BerryDeputy Director, Research & E-
infrastructure DevelopmentNational e-Science Centre, UK
2
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Computing as a Commodity
o From hand-built research computers…
o From individual computers…o From specialist
supercomputers…o From proprietary formats…o From individual servers…
o From applications…o From ownership…o From silos…
o to PC’s, PDAs and mobile phones
o to the Internet and the WWWo to clusters and cycle-
scavengingo to standards and ontologieso to virtualised, dynamically
provisioned server farmso to serviceso to computing-on-demando to Grids
3
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
What is a Grid?
o A grid is a system consisting of• Distributed but connected resources and • Software and/or hardware that provides and manages
logically seamless access to those resources to meet desired objectives
LicenseLicense
PrinterPrinter
R2AD
DatabaseDatabase
WebserverWeb
server
Data CenterCluster
Handheld Supercomputer
Workstation
Server
4
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Grids vs. Distributed Computing
o Existing distributed applications:• Tend to be specialised systems• Intended for a single purpose or user group
o Grids go further and take into account:• Different kinds of resources• Different kinds of interactions• Dynamic nature
5
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Ideas and Forms
o Key ideas• Virtualised resources• Secure access• Dynamic provisioning
o Many forms• Cycle stealing• Linked supercomputers• Distributed data management• Commercial data centres• Utility computing• Collaboration Grids
62006/10/19
Grids In Use: E-Science Examples
• Data sharing and integration− Life sciences, sharing standard data-sets, combining
collaborative data-sets− Medical informatics, integrating hospital information
systems for better care and better science− Sciences, high-energy physics
• Data sharing and integration− Life sciences, sharing standard data-sets, combining
collaborative data-sets− Medical informatics, integrating hospital information
systems for better care and better science− Sciences, high-energy physics
• Capability computing− Life sciences, molecular modeling, tomography− Engineering, materials science− Sciences, astronomy, physics
• Capability computing− Life sciences, molecular modeling, tomography− Engineering, materials science− Sciences, astronomy, physics
• High-throughput, capacity computing for − Life sciences: BLAST, CHARMM, drug screening− Engineering: aircraft design, materials, biomedical− Sciences: high-energy physics, economic modeling
• High-throughput, capacity computing for − Life sciences: BLAST, CHARMM, drug screening− Engineering: aircraft design, materials, biomedical− Sciences: high-energy physics, economic modeling
• Simulation-based science and engineering− Earthquake simulation
• Simulation-based science and engineering− Earthquake simulation
Slide from Hiro Kishimoto’s GGF17 Keynote
climateprediction.net and GENIE
• Largest climate model ensemble • >45,000 users, >1,000,000
model years
10K2KResponse of Atlantic circulation to freshwater forcing
8
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Large Hadron Collider
o The most powerful instrument ever built to investigate elementary particle physics
o 10 Petabytes/year of data
o Simulation, reconstruction, analysis:• Requires computing power
equivalent to ~100,000 of today's fastest PC processors
92006/10/19
Grids In Use: E-Business Examples
• High-throughput computing− Aircraft design− Drug discovery− Electronic design automation
• High-throughput computing− Aircraft design− Drug discovery− Electronic design automation
• Enterprise Information Integration (EII)− Banking− Drug discovery− Collaborative engineering
• Enterprise Information Integration (EII)− Banking− Drug discovery− Collaborative engineering
• Financial services− Portfolio modeling− Data integration
• Financial services− Portfolio modeling− Data integration
• Large-scale collaboration− Aircraft design− Automobile design
• Large-scale collaboration− Aircraft design− Automobile design
Slide from Hiro Kishimoto’s GGF17 Keynote
10
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
“Gridified” Infrastructure
FinancialServices
DerivativesAnalysis
Statistical Analysis
Portfolio Risk
Analysis
DerivativesAnalysis
Statistical Analysis
Portfolio Risk
Analysis
Manufacturing
Mechanical/ Electronic
Design
Process Simulation
FiniteElement Analysis
Failure Analysis
Mechanical/ Electronic
Design
Process Simulation
FiniteElement Analysis
Failure Analysis
LS / Bioinformatics
Cancer Research
Drug Discovery
Protein Folding
Protein Sequencing
Cancer Research
Drug Discovery
Protein Folding
Protein Sequencing
Other
Web Applications
Weather Analysis
Code Breaking/ Simulation
Academic
Web Applications
Weather Analysis
Code Breaking/ Simulation
Academic
Sources: IDC
Grid
Mar
ket O
ppor
tuni
ty 2
005
Energy
Seismic Analysis
Reservoir Analysis
Seismic Analysis
Reservoir Analysis
Entertainment
Digital Rendering
Digital Rendering
Massive Multi-Player
Games
Massive Multi-Player
Games
Streaming Media
Streaming Media
Leading Grid Application Domains
11
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Grids straddle disciplines
o A company working on the placement of a new factory needs financial forecasting combined with mining of proprietary historical data
o An industrial consortium work on the feasibility study for a new airliner
o A crisis management team reacts to a chemical spill using soil and weather models, demographic information, and productivity tools for emergency teams
Sources: Anatomy of the Grid, Foster et al.
12
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Key Middleware Requirements
o Secure authorization, role and access privileges
oResource discovery,
monitoring & control
oData access, transfer and management
o Execute and manage
jobs/services
oInformationabout applications
& resources
Virtualized resources
Grid middleware
servicesBrokering
Service
Brokering Service
Registry Service
Registry Service
DataService
DataService
CPU Resource
CPU Resource Printer
Service
Printer Service
Job-Submit Service
Job-Submit Service
ComputeService
ComputeService
Notify
Advertise
ApplicationService
ApplicationService
13
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Collaboration Grids
o Key concept:• The ability to negotiate resource-sharing
arrangements among a set of participating parties and then to use the resulting resource pool for some purpose. (Ian Foster)
o Virtual organisations:• Combining people and resources from different
organisations to address a given problem• Enabled by Grid technology
14
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Defining a Collaboration Grid
Three aspects:1. Coordinating on-demand, secure access to
distributed and heterogeneous resources (cpu, storage, bandwidth …)
2. Using standard, open, general-purpose protocols and interfaces
3. To deliver non-trivial qualities of service
152006/10/19
SOA & Web Services
SOA• Flexible− Locate services on any server− Relocate as necessary− Prospective clients find services using
registries
• Scalable− Add & remove services as demand varies
• Replaceable− Update implementations without disruption
to users
• Fault-tolerant− On failure, clients query registry for alternate
services
SOA• Flexible− Locate services on any server− Relocate as necessary− Prospective clients find services using
registries
• Scalable− Add & remove services as demand varies
• Replaceable− Update implementations without disruption
to users
• Fault-tolerant− On failure, clients query registry for alternate
services
Web Services• Interoperable
− Growing number of industry standards• Strong industry support• Reduce time-to-value
− Harness robust development tools for Web services
− Decrease learning & implementation time• Embrace and extend
− Leverage effort in developing and driving consensus on standards
− Focus limited resources on augmenting & adding standards as needed
Web Services• Interoperable
− Growing number of industry standards• Strong industry support• Reduce time-to-value
− Harness robust development tools for Web services
− Decrease learning & implementation time• Embrace and extend
− Leverage effort in developing and driving consensus on standards
− Focus limited resources on augmenting & adding standards as needed
16
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
SOA & SOI
IT Operations Automation & Management
Operational Efficiency
Business Strategy Automation & Execution
Responsiveness to Market
IT Operations Automation & Management
Operational Efficiency
Business Strategy Automation & Execution
Responsiveness to Market
End-to-End, Dynamic
Management
Business Monitoring & Analytics
Business Process & Application Automation
Information and Data Services
Integration, Event & Deployment Services
Collaboration & Communication Services
Access & Interface Services
Service Level Management & Automation
Metering, Measurement & Charge-back
Security
Infrastructure Virtualization
Infrastructure Provisioning
Platform Management & Monitoring
Service OrientedInfrastructureInfrastructure As A Service
Service OrientedArchitectureSoftware As A Service
17
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Example: Procure to Pay Process
Change: Customer Order EntryChange: Serviced Marketing, Billing, Receivables
Change: Supplier Handles InventoryChange: Shipping by External Company
Change: Collections OutsourcedChange: Process Optimization
DivisionDivision
CustomerCustomer
Shared Shared ServiceService
SupplierSupplier
OutsourcedOutsourced
18
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Motivations for Grids
o Scale up computing and/or data setso Reduce costs via capex/opex efficiencieso Reduce time-to-resultso Provide reliability, availabilityo Support heterogeneous systems & realitieso Enable collaborationso Support a market in software services
19
ITU-T
ITU-T/OGF Workshop on Next Generation Networks and GridsGeneva, 23-24 October 2006
Questions?
o Credits:• Hiro Kishimoto, Fujitsu & OGF• Dave Snelling, Fujitsu & OGF• Franco Travostino, Nortel & OGF• Angus McCann, IBM• Ian Osborne, Grid Computing Now!• Ian Foster, ANL/Globus• IDC