manchester computing supercomputing, visualization & escience w t hewitt wednesday, april 16,...

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

W T Hewitt

Monday, April 10, 2023UCISA MeetingEdinburgh

What is e-Science & What is What is e-Science & What is the Grid?the Grid?

Supercomputing, Visualization & e-Science2 escigriducisa/03

Agenda

What is Grid & eScience?

The Global Programme

The UK eScience Programme

Impacts

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

What is e-Science & the Grid?


Why Grids?

Large-scale science and engineering are done through – the interaction of people, – heterogeneous computing resources, information systems, and instruments, – all of which are geographically and organizationally dispersed.

The overall motivation for “Grids” is to facilitate the routine interactions of these resources in order to support large-scale science and engineering.

From Bill Johnston 27 July 01


The Grid…

"…is the web on steroids." "…is Napster for Scientists" [of data grids] "…is the solution to all your problems." "…is evil." [a system manager, of Globus] "…is distributed computing re-badged." "…is distributed computing across multiple administrative

domains"– Dave Snelling, senior architect of UNICORE


[…provides] "Flexible, secure, coordinated resource sharing among dynamic collections of individuals, institutions, and resource"– From “The Anatomy of the Grid: Enabling Scalable Virtual Organizations”

"…enables communities (“virtual organizations”) to share geographically distributed resources as they pursue common goals -- assuming the absence of central location, central control, omniscience, existing trust relationships."


CERN: Large Hadron Collider (LHC)

Raw Data: 1 Petabyte / secFiltered 100Mbyte / sec = 1 Petabyte / year = 1 Million CD ROMsRaw Data: 1 Petabyte / secFiltered 100Mbyte / sec = 1 Petabyte / year = 1 Million CD ROMs

CMS Detector


Why Grids?

A biochemist exploits 10,000 computers to screen 100,000 compounds in an hour;

A biologist combines a range of diverse and distributed resources (databases, tools, instruments) to answer complex questions;

1,000 physicists worldwide pool resources for petaop analyses of petabytes of data

Civil engineers collaborate to design, execute, & analyze shake table experiments

From Steve Tuecke 12 Oct. 01


Why Grids? (contd.)

Climate scientists visualize, annotate, & analyze terabyte simulation datasets

An emergency response team couples real time data, weather model, population data

A multidisciplinary analysis in aerospace couples code and data in four companies

A home user invokes architectural design functions at an application service provider

From Steve Tuecke 12 Oct. 01


Broader Context

“Grid Computing” has much in common with major industrial thrusts– Business-to-business, Peer-to-peer, Application Service Providers, Storage

Service Providers, Distributed Computing, Internet Computing…

Sharing issues not adequately addressed by existing technologies – Complicated requirements: “run program X at site Y subject to community

policy P, providing access to data at Z according to policy Q”

– High performance: unique demands of advanced & high-performance systems


What is the Grid?

“ Grid computing [is] distinguished from conventional distributed computing by its focus on large-scale resource sharing, innovative applications, and, in some cases, high-performance orientation...we review the "Grid problem", which we define as flexible, secure, coordinated resource sharing among dynamic collections of individuals, institutions, and resources - what we refer to as virtual organizations."

From "The Anatomy of the Grid: Enabling Scalable Virtual Organizations" by Foster, Kesselman and Tuecke


New Book


What is the Grid?

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

On-demand, ubiquitous access to computing, data, and all kinds of services

New capabilities constructed dynamically and transparently from distributed services

No central location, No central control, No existing trust relationships, Little predetermination

Uniformity Pooling Resources


e-Science and the Grid

‘e-Science is about global collaboration in key areas of science, and the next generation of infrastructure that will enable it.’

‘e-Science will change the dynamic of the way science is undertaken.’

John Taylor,

Director General of Research Councils,

Office of Science and Technology


Why GRID?

VERY VERY IMPORTANT

The GRID is one way to realise the e-Science vision.

WE ARE TRYING TO DO E-SCIENCE!

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

Grid Middleware

Diverse global services

Gridservices

Local OS


Common principles

Single sign-on– Often implying Public Key Infrastructure (PKI)

Standard protocols and services Respect for autonomy of resource owner Layered architectures Higher-level infrastructures hiding heterogeneity of lower

levels Interoperability is paramount


Grid Middleware

Middleware Globus UNICORE Legion and Avaki

Scheduling Sun Grid Engine Load Sharing Facility (LSF)

– from Platform Computing

OpenPBS and PBS(Pro)– from Veridian

Maui scheduler Condor

– could also go under middleware

Data Storage Resource Broker (SRB) Replica Management OGSA-DAI

Web services (WSDL, SOAP, UDDI) IBM Websphere Microsoft .NET Sun Open Net Environment (Sun

ONE)

PC Grids

Peer-to-Peer computing

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

Data-oriented Grids


Data-oriented middleware

Wide-area distributed file systems (e.g. AFS) Storage Resource Broker (SRB)

– UCSD and SDSC– Provide transparent access to data storage– Centralised architecture– Motivated by experiences of HPC users, not database users– Little enthusiasm from UK e-Science programme

OGSA-DAI– Database Access and Integration– Strategic contribution of UK e-Science programme– Universities of Edinburgh, Manchester, Newcastle; IBM, Oracle– Alpha release January 2003

Globus Replica Management software– Next up!


Data Grids forHigh Energy Physics

Tier2 Centre ~1 TIPS

Online System

Offline Processor Farm

~20 TIPS

CERN Computer Centre

FermiLab ~4 TIPSFrance Regional Centre

Italy Regional Centre

Germany Regional Centre

InstituteInstituteInstituteInstitute ~0.25TIPS

Physicist workstations

~100 MBytes/sec

~100 MBytes/sec

~622 Mbits/sec

~1 MBytes/sec

There is a “bunch crossing” every 25 nsecs.

There are 100 “triggers” per second

Each triggered event is ~1 MByte in size

Physicists work on analysis “channels”.

Each institute will have ~10 physicists working on one or more channels; data for these channels should be cached by the institute server

Physics data cache

~PBytes/sec

~622 Mbits/sec or Air Freight (deprecated)




Caltech ~1 TIPS

~622 Mbits/sec

Tier 0Tier 0

Tier 1Tier 1

Tier 2Tier 2

Tier 4Tier 4

1 TIPS is approximately 25,000

SpecInt95 equivalents


Data Intensive Issues Include …

Harness [potentially large numbers of] data, storage, network resources located in distinct administrative domains

Respect local and global policies governing what can be used for what

Schedule resources efficiently, again subject to local and global constraints

Achieve high performance, with respect to both speed and reliability

Catalog software and virtual data


Desired Data Grid Functionality

High-speed, reliable access to remote data Automated discovery of “best” copy of data Manage replication to improve performance Co-schedule compute, storage, network “Transparency” wrt delivered performance Enforce access control on data Allow representation of “global” resource allocation

policies


Grid Standards

Grid Standards Bodies:– IETF: Home of the Network Infrastructure Standards

– W3C: Home of the Internet

– GGF: Home of the Grid

GGF Defines the Open Grid Services Architecture– OGSI is the Infrastructure part of OGSA

– OGSI Public comment draft submitted 14 February 2003

Key OGSA Areas of Standards Development– Job management interfaces

– Resources & Discovery

– Security

– Grid Economy and Brokering


What is OGSA?

““Web ServicesWeb Serviceswith Attitude!”with Attitude!”

Also known as

"Open Grid Services Architecture"


Aside: What are Web Services?

Loosely Coupled Distributed Computing– Think Java RMI or C remote procedure call

Text Based Serialization– XML: “Human Readable” serialization of objects

IBM and Microsoft lead– Web Services Description Language (WSDL)

– W3C Standardization

Three Parts– Messages (SOAP)

– Definition (WSDL)

– Discovery (UDDI)


Web Services in Action

UDDI

Publish/WSDLSearch

Client https/SOAP

Java/C/Browser

LegacyEnterprise

Application

Database ...

WSPlatform

InterStage, WebSphere, J2EE, GLUE, SunOne, .NET

Any protocol


Enter Grid Services

Experiences of Grid computing (and business process integration) suggest similar extensions to Web Services

State– Service Data Model

Persistence and Naming– Two Level Naming (GSH, GSR)– Allows dynamic migration and QoS adaptation

Lifetime Management– Self healing and ‘soft’ garbage collection.

Standard PortTypes– Guarantee of minimal level of service– Beyond P2P is Federation through Mediation

Explicit Semantics– Grid Services specify semantics on top of Web Service syntax.– PortType Inheritance

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

If one GRID is good then Many GRIDS must be better


US Grid Projects

NASA Information Power Grid DOE Science Grid NSF National Virtual

Observatory NSF GriPhyN DOE Particle Physics Data Grid NSF DTF TeraGrid DOE ASCI DISCOM Grid

DOE Earth Systems Grid DOE FusionGrid NEESGrid NIH BIRN NSF iVDGL


National Grid Projects

Japan – Grid Data Farm, ITBL Netherlands – VLAM, DutchGrid Germany – UNICORE, Grid proposal France – Grid funding approved Italy – INFN Grid Eire – Grid-Ireland Poland – PIONIER Grid Switzerland - Grid proposal Hungary – DemoGrid, Grid proposal ApGrid – AsiaPacific Grid proposal


EU GridProjects

DataGrid (CERN, ..) EuroGrid (Unicore) DataTag (TTT…) Astrophysical Virtual

Observatory GRIP (Globus/Unicore) GRIA (Industrial applications) GridLab (Cactus Toolkit) CrossGrid (Infrastructure

Components) EGSO (Solar Physics) COG (Semantic Grid)

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

UK e-Science Programme


£80m Collaborative projects

E-ScienceSteering

Committee

DG Research Councils

Director Director’s

Management RoleDirector’s

Awareness and Co-ordination Role

Generic Challenges EPSRC (£15m), DTI (£15m)

Industrial Collaboration (£40m)

Academic Application SupportProgramme

Research Councils (£74m), DTI (£5m)

PPARC (£26m) BBSRC (£8m) MRC (£8m) NERC (£7m) ESRC (£3m) EPSRC (£17m) CLRC (£5m)

Grid TAG

From Tony Hey 27 July 01

UK e-Science Programme


Key Elements

Development of Generic Grid Middleware Network of Grid Core Programme e-Science Centres

– National Centre http://www.nesc.ac.uk– Regional Centres http://www.esnw.ac.uk/

Grid IRC Grand Challenge Project Support for e-Science Pilots Short term funding for e-Science demonstrators Grid Network Team Grid Engineering Team Grid Support Centre Task Forces

– Database lead by Norman Paton– Architecture lead by Malcolm Atkinson

International Involvement

Adapted from Tony Hey 27 July 01


Cambridge

Newcastle

Edinburgh

Oxford

Glasgow

Manchester

Cardiff

Southampton

London

Belfast

DL

RALHinxton

National & Regional Centres

Centres donate equipment to make a Grid


e-Science Demonstrators

Dynamic Brain Atlas Biodiversity Chemical Structures Mouse Genes Robotic Astronomy Collaborative Visualisation Climateprediction.com Medical Imaging/VR


Grid Middleware R&D

£16M funding available for industrial collaborative projects £11M allocated to Centres projects plus £5M for ‘Open

Call’ projects Set up Task Forces

– Database Task Force

– Architecture Task Force

– Security Task Force


Grid Network Team

Expert group to identify end-to-end network bottlenecks and other network issues

– e.g. problems with multicast for Access Grid

Identify e-Science project requirements Funding £0.5M traffic engineering/QoS project with PPARC, UKERNA and

CISCO– investigating MPLS using SuperJANET network

Funding DataGrid extension project investigating bandwidth scheduling with PPARC

Proposal for ‘UKLight’ lambda connection to Chicago and Amsterdam


UK e-Science Pilot Projects

GRIDPP (PPARC) ASTROGRID (PPARC) Comb-e-Chem (EPSRC) DAME (EPSRC) DiscoveryNet (EPSRC) GEODISE (EPSRC) myGrid (EPSRC) RealityGrid (EPSRC)

Climateprediction.com (NERC) Oceanographic Grid (NERC) Molecular Environmental Grid

(NERC) NERC DataGrid (+ OST-CP) Biomolecular Grid (BBSRC) Proteome Annotation Pipeline

(BBSRC) High-Throughput Structural

Biology (BBSRC) Global Biodiversity (BBSRC)

RASMOL


e-Science Centres of Excellence

Birmingham/Warwick – Modelling Bristol – Media UCL – Networking White Rose Grid – Leeds, York, Sheffield Lancaster – Social Science Leicester – Astronomy Reading - Environment


Cambridge

Newcastle

Edinburgh

Oxford

Glasgow

Manchester

Cardiff

Soton

London

BelfastDL

RL Hinxton

UK e-Science Grid


UK e-Science Funding

First Phase: 2001 –2004 Application Projects

– £74M

– All areas of science and engineering

Core Programme– £15M + £20M (DTI)

– Collaborative industrial projects

Second Phase: 2003 –2006

Application Projects– £96M– All areas of science and

engineering

Core Programme– £16M – Core Grid Middleware– DTI follow-on?


EPSRC: Computer Science for e-Science– £9M, 18 projects so far

ESRC: National e-Social Science Centre + 3 hubs– ~£6M

PPARC MRC BBSRC


Core Programme: Phase 2

UK e-Science Grid/Centres and e-Science Institute Grid Operation Centre and Network Monitoring Core Middleware engineering National Data Curation Centre e-Science Exemplars/New Opportunities Outreach and International involvement


Other Activities

Security Task Force– Joint fund key security projects with EPSRC & JCSR and coordinated effort

with NSF NMI Internet2 projects

– JCSR £2M call in preparation

UK Digital Curation Centre– £3M, Core e-Science + JCSR

JCSR– £3M per annum


SR2004 – e-Science Infrastructure

Persistent UK e-Science Research Grid Grid Operations Centre UK Open Middleware Infrastructure Institute National e-Science Institute UK Digital Curation Centre AccessGrid Support Service e-Science/Grid collaboratories Legal Service International Standards Activity

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

Conclusions


Today’s Grid

A Single System Image Transparent wide-area access to

large data banks Transparent wide-area access to

applications on heterogeneous platforms

Transparent wide-area access to processing resources

Security, certification, single sign-on authentication, AAA

– Grid Security Infrastructure,

Data access,Transfer & Replication – GridFTP, Giggle

Computational resource discovery, allocation and process creation

– GRAAM, Unicore, Condor-G


Reality Checks!!

The Technology is Ready– Not true — its emerging

• Building middleware, Advancing Standards, Developing, Dependability

• Building demonstrators.

• The computational grid is in advance of the data intensive middleware

• Integration and curation are probably the obstacles

• But!! It doesn’t have to be all there to be useful.

We know how we will use grid services– No — Disruptive technology

• Lower the barriers of entry.


Grid Evolution

1st Generation Grid– Computationally intensive, file access/transfer– Bag of various heterogeneous protocols & toolkits– Recognises internet, Ignores Web– Academic teams

2nd Generation Grid– Data intensive -> knowledge intensive– Services-based architecture– Recognises Web and Web services– Global Grid Forum– Industry participation

We are here!


Impacts

It's all about interoperability, really. Web & Grid Services are creating a new marketplace for

components If you're concerned with systems integration or internet

delivery of services, embrace Web Services technologies now. You'll be ready for Grid Services when they're ready for you.– If you're a developer, get Web Services on your CV

– If you're an IT manager, collect Web Service expertise through hiring or training

Software license models must adapt


I don't want to share!Do I need a grid?


In conclusion

The GRID is not, and will not, be free– must pay for resources

What have we to show for £250M?


Acknowledgements

Carole Goble Stephen Pickles Paul Jeffreys

University of Manchester Academic collaborators

Industrial collaborators

Funding Agencies: DTI, EPSRC, NERC, ESRC, PPARC

Man

ch

este

r C

om

pu

tin

gSup

erc

om

puti

ng,

Vis

ualiz

ati

on &

eSci

ence

World Leading Supercomputing Service, Support and Research

Bringing Science and Supercomputers Together

www.man.ac.uk/[email protected]

SVE @ Manchester ComputingSVE @ Manchester Computing

manchester computing supercomputing, visualization & escience w t hewitt wednesday, april 16,...

Documents

grid escience

escience vision

tuecke slide

grid escience

technology slide

grid problem

largescale science

way science