Post on 29-Dec-2015
www.see-grid.eu
SEE-GRID-SCI
The SEE-GRID-SCI initiative is co-funded by the European Commission under the FP7 Research Infrastructures contract no. 211338
Introduction of Grid Computing
ASNET-AM Annual Report,Yerevan, Armenia, 17 December 2008
Hrachya AstsatryanInstitute for Informatics and Automation Problems
National Academy of Sciences of the Republic of Armeniahrach@sci.am
Outline
Definition of Grid computing
Grid Computing Components
E-Infrastructures
Grid Monitoring & Information Services
Grid Definition: Word Meaning
The term Grid computing or Grid suggest a computing paradigm similar to an electric power grid - a variety of resources contribute power into a shared "pool" for many consumers to access on an as-needed basis.
Grid Definition (2)
In 1998 Ian Foster and Carl Kesselman (The Grid: Blueprint for a New Computing Infrastructure)“A computational grid is a hardware and software infrastructure that provides dependable, consistent, pervasive, and inexpensive access to high-end computational capabilities.”
In 2002 Ian Foster (What is the Grid? A Three-Point Checklist) A Grid is a system thatcoordinates resources that are not subject to centralized controlusing standard, open, general-purpose protocols and interfacesto deliver nontrivial qualities of service.”
Grid Definition (3): A Working Definition
A distributed computing environment that coordinates Computational jobs Data placement Information management
Scales from one computer to thousands
Capable of working across many administrative domains
Outline
Definition of Grid computing
Grid Computing Components
E-Infrastructures
Grid Monitoring & Information Services
Distributed People Research communities who need to share data, or
codes, or computers, or equipment to work on and understand common problems
Example: Astrophysics Network: relativists, astrophysicists, computer scientists, mathematicians, experimentalists, data analysts.
Distributed Resources Computers: supercomputers, clusters, workstations Storage devices, databases, networks Experimental equipment: telescopes/interferometers
Grid Computing Components
Software infrastructure Links all these together Low level: security, information, communication, … Middleware: data management, resource brokers, web portals,
monitoring, workflow, …
Examples Globus Condor Glite
Grid Computing Components (2)
Groups of organizations that use the Grid to share resources for specific purposes
Support a single community
Deploy compatible technology and agree on working policies Security policies – difficult
Deploy different network accessible services: Grid Information Grid Resource Brokering Grid Monitoring Grid Accounting
Grid Computing Components (3)Virtual Organizations
MIDDLEWARE
Visualization
User
Access
Suprecomputers, clusters
Internet, networks
Experiments, sensors, etc..
Grid Computing Components (10)
Hardware Components: Brief History of Computing
1980: "DOS addresses only 1 Megabyte of RAM because we cannot imagine any applications needing more." -Microsoft on the development of DOS.
1981: "640k ought to be enough for anybody." -Bill Gates
0
2000
4000
6000
8000
10000
12000
14000
1960 1970 1980 1990 2000 2010
MIPS
Series2
Distributed systems built from Computing elements (processors) Communication elements (networks) Storage elements (disk, attached or networked)
New elements Visualization/interactive devices Experimental and operational devices
Hardware Components (2):Basic Elements
Definition of supercomputer Machine on Top500.org? Machine costing over $1M? Most powerful machines One-of-a-kind
Top 1 (Latest 2008) Roadrunner - BladeCenter QS22 (US) 1026TFTop 1 (November 2006)
IBM Blue Gene/L (US) 131k procs, 280 TFTop 1 (2003)
Earth Simulator (JAPAN) 5K procs/36 TF (6)
Hardware Components (4):Basic Elements
Supercomputers
Outline
Definition of Grid computing
Grid Computing Components
E-Infrastructures
Grid Monitoring & Information Services
E-Infrastructures: network layer
E-Infrastructures (2): Grid layer
Standards
OGF
E-Infrastructures (3): Data layer
E-Infrastructures (4): Global perspective
Potential for linking ~80 countries by 2008
E-Infrastructures (5): Grid Examples
Applicationsimproved services for academia,
industry and the public
Support Actionskey complementary functions
Infrastructuresgeographical or thematic coverage
E-Infrastructures (6): Collaborating Projects
SEE GRID SCI Project
ContractorsGRNET GreeceCERN SwitzerlandSZTAKI Hungary IPP-BAS BulgariaICI RomaniaTUBITAK TurkeyASA/INIMA AlbaniaUoBL Bosnia-HerzegovinaUKIM FYR of MacedoniaUOB SerbiaUoM MontenegroRENAM MoldovaRBI CroatiaIIAP-NAS-RA ArmeniaGRENA Georgia
Third Party ssociate universities / research centres
GRNET.gr
SEE-GRID-SCI partnership
MTA SZTAKI .hu
IPP .bg
ICI .ro
TUBITAK.tr
UPT.al
UKIM.mk
UoBL.ba
RBI.hr
UOB.rs
RENAM.md
UOM.me
GRENA.ge
IIAP-NAS-RA.am
The SEE-GRID-SCI initiative is co-funded by the European Commission under the FP7 Research Infrastructures contract no. 211338
SEE GRID SCI: converged communication and service infrastructure for SEE
GRNET.gr
MTA SZTAKI .hu
IPP .bg
ICI .ro
TUBITAK.tr
UPT.al
UKIM.mk
UoBL.ba
RBI.hr
UOB.rs
RENAM.md
UOM.me
GRENA.ge
IIAP-NAS-RA.am
SEEFIRE + Geant Support
SEE-GRID
SeismologyVO
MeteorologyVO
EnvironmentalVO
SeismologyVO
MeteorologyVO
EnvironmentalVO
SEE-SCI
e-Infrastru
cture
The SEE-GRID-SCI initiative is co-funded by the European Commission under the FP7 Research Infrastructures contract no. 211338
SEE GRID SCI Open Applications: Earthquake
SEE GRID SCI Open Applications: Meteorology
Advances in numerical weather prediction (NWP) has been always very closely related with advances in computing sciences as NWP requires numerical calculations that are also parallelizable.
The computer resources needed for NWP applications are important both in terms of CPU usage and disk storage. Although many institutions are working/ have experience on NWP, they may not have access to the necessary computer resources for operational implementation of such applications or for large experiments.
So the porting of any NWP application to the grid is a natural choice.
SEE GRID SCI Open Applications: Meteorology
•The REFS application will allow the meteorological entities participating in the project to assess the probability of a particular weather event to occur and to provide this information to the authorities, the general public, etc, in order to help them make the necessary decisions based on this probabilistic information.
•The WRF-ARW application will permit the entities participating in the project to improve the quality of the forecasts of the airflow over regions characterised by complex terrain with a positive impact to related applications such as air-pollution dispersion modelling.
SEE GRID SCI Open Applications: Environment
•The aim of the Monte Carlo Sensitivity Analysis for Environmental Systems application is to develop an efficient Grid implementation of a Monte Carlo technique for sensitivity studies in the domains of Environmental modeling and Environmental security. The developed application will be applied for studying the damaging effects that can be caused by high pollution levels (especially effects on human health), when the main tool will be the Danish Eulerian Model (DEM).
Multi-Scale Atmospheric Composition Modelling. Atmospheric composition directly affect many aspects of life. AQ studies are fundamental for the future orientation of national, regional and Europe’s Sustainable Development strategy. Expected results and their consequences
•high quality scientifically robust assessments of the air pollution and its origin from urban to local to regional (Balkan) scales•Determination of the main pathways and processes that lead to atmospheric composition formation in different scales
Armenian National Grid Initiative
The Armenian National Grid Initiative (ArmNGI) represents an effort to establish a sustainable grid infrastructure in Armenia. The establishment of ArmNGI foundation is in process. Main aims of the initiative are;
•create a national GRID development policy •to build up the national grid infrastructure •to expand the high performance computing resources with collaboration of academic and commercial participants •to give the information to the national user community about high performance computing, grid infrastructure and international grid projects •to improve national applications •to take place the international grid projects actively
Armenian National Grid Initiative
•State Scientific Committee of the Ministry of Education and Science of the Republic of Armenia
•National Academy of Sciences of the Republic of Armenia
•State Engineering University of Armenia
•Yerevan State University
•Yerevan Physics Institute after A. Alikhanian
•Institute for Informatics and Automation Problems of the National Academy of Sciences of the Republic of Armenia
•Armenian e-Science Foundation
European Commission
“…for Grids we would like to see the move towards
long-term sustainable initiatives less dependent upon
EU-funded project cycles”
Viviane Reding, Commissioner, European Commission, at the EGEE’06 Conference,
September 25, 2006
European Grid Initiative
Goal: Creating a long-term sustainability of grid
infrastructures in Europe
Approach: Establishment of a new federated model bringing
together National Grid Initiatives (NGIs) to build the EGI Organisation
Characteristics of NGIs
Each NGI … should be a recognized national body
with a single point-of-contact … should mobilise national funding and resources … should operate the national e-Infrastructure … should support user communities (application
independent, and open to new user communities and resource providers)
… should contribute and adhere to international standards and policies
Responsibilities between NGIs and EGI are split to be federated and complementary
www.eu-egi.org
38 National Grid Initiatives
European Grid Initiative
EGI Organisation:Coordination and operation of a common multi-national, multi-disciplinary Grid infrastructure To enable and support international Grid-based collaboration To provide support and added value to NGIs To liaise with corresponding infrastructures outside Europe
Outline
Definition of Grid computing
Grid Computing Components
E-Infrastructures
Grid Monitoring & Information Services
Monitoring provides information for several purposes
Operation of Grid Monitoring and testing Grid
Deployment of applications What resources are available to me? (Resource discovery) What is the state of the grid? (Resource selection) How to optimize resource use? (Application configuration and
adaptation)
Information for other Grid Services to use
Grid Monitoring
Monitoring information is either static or dynamic, broadly.
Static information about a site: Number of worker nodes, processors Storage capacities Architecture and Operating systems
Dynamic information about a site Number of jobs running on each site CPU utilization of different worker nodes Overall site “availability”
Time-varying information is critical for scheduling of grid jobs
More accurate info costs more: it’s a tradeoff.
Grid Monitoring (2)
Status of resource on gridUp/down?How much load?
DiscoveryStart with a task to perform on the gridFor example, want to perform run a simulationHow do we find resources to use?How do we choose which resource to use?
Grid Monitoring (7): Monitoring Grid Resources