london e-science centre gridsam a standards based approach to job submission a. stephen m c gough...

London e-Science Centre

GridSAMGridSAMA Standards Based Approach to Job Submission

A. Stephen MCGough

Imperial College London

A Standards Based Approach to Job Submission

A. Stephen MCGough

Imperial College London

2


Common Grid SystemsCommon Grid Systems

There are many Grid Systems. Though they are not compatible.

Globus Condor gLite Grid Engine LSF PBS LoadLeveler Unicore …

• Different job description languages• Different submission interfaces

3


If all DRM systems supported the same interface…

If all DRM systems supported the same interface…

If we had: One interface definition for job submission One job description language

Then life would be easier! We’re getting there

JSDL is a proposed standard job submission description language

OGSA-BES is a proposed standard basic execution service interface

One day hopefully everyone will support this Till then…

If we had: One interface definition for job submission One job description language

Then life would be easier! We’re getting there

JSDL is a proposed standard job submission description language

OGSA-BES is a proposed standard basic execution service interface

One day hopefully everyone will support this Till then…


GridSAM Job Submission and Monitoring Web Service

GridSAM Job Submission and Monitoring Web Service

5


GridSAM OverviewGrid Job Submission and Monitoring Service


What is GridSAM? A Job Submission and Monitoring Web Service Funded by the Open Middleware Infrastructure

Institute (OMII) managed programme V2.0.0 Available as part of the OMII 2.x release Open source (BSD) One of the first system to support the GGF Job

Submission Description Language (JSDL)

What is GridSAM? A Job Submission and Monitoring Web Service Funded by the Open Middleware Infrastructure

Institute (OMII) managed programme V2.0.0 Available as part of the OMII 2.x release Open source (BSD) One of the first system to support the GGF Job

Submission Description Language (JSDL)

6


What’s not?What’s not?

GridSAM is not a scheduling service

That’s the role of the underlying launching mechanism

That’s the role of a super-scheduler that brokers jobs to a set of GridSAM services

a provisioning service GridSAM runs what’s been told to run GridSAM does not resolve software

dependencies and resource requirements

GridSAM is not a scheduling service

That’s the role of the underlying launching mechanism

That’s the role of a super-scheduler that brokers jobs to a set of GridSAM services

a provisioning service GridSAM runs what’s been told to run GridSAM does not resolve software

dependencies and resource requirements

7




What is GridSAM to the resource owners? A Web Service to expose heterogeneous

execution resources uniformly Single machine through Forking or SSH Condor Pool Grid Engine 6 through DRMAA Globus 2.4.3 exposed resources OR use our plug-in API to implement …

What is GridSAM to the resource owners? A Web Service to expose heterogeneous

execution resources uniformly Single machine through Forking or SSH Condor Pool Grid Engine 6 through DRMAA Globus 2.4.3 exposed resources OR use our plug-in API to implement …

8




What is GridSAM to end-users? A set of end-user tools and client-side APIs to

interact with a GridSAM web service Submit and Start Jobs Monitor Jobs Terminate Jobs File transfer Client-side submission scripting Client-side Java API

What is GridSAM to end-users? A set of end-user tools and client-side APIs to

interact with a GridSAM web service Submit and Start Jobs Monitor Jobs Terminate Jobs File transfer Client-side submission scripting Client-side Java API

9


Integration with OMII Distribution

Integration with OMII Distribution

10


GridSAM ImplementationGridSAM Implementation

Virtual File System API (Apache VFS) FTP / GSIFTP / HTTP / WEBDAV / SFTP

POSIX Shell API Fork / SSH

Event dispatches (OpenSymphony Quartz) Job Persistence (Hibernate - JDBC databases) Runtime Monitoring and Control (Java Management Extension)

Virtual File System API (Apache VFS) FTP / GSIFTP / HTTP / WEBDAV / SFTP

POSIX Shell API Fork / SSH

Event dispatches (OpenSymphony Quartz) Job Persistence (Hibernate - JDBC databases) Runtime Monitoring and Control (Java Management Extension)

11


Example Pipeline: Condor

GridSAM ArchitectureGridSAM Architecture

A staged event-driven architecture* Submission pipeline is constructed as a network

of stages connected by event queues Each stage perform specific action upon incoming

events

A staged event-driven architecture* Submission pipeline is constructed as a network

of stages connected by event queues Each stage perform specific action upon incoming

events *M. Welsh and D. Culler and E. Brewer. Seda: An architecture for well-connected scalable internet

services. In Eighteenth Symposium on Operating Systems Principles (SOSP-18), October 2001.

12


Deployment Scenario: ForkingDeployment Scenario: Forking

HTTP + WS-Sec./ HTTPS + WS-Sec. /

HTTPS mutual.

Local FS

Local FS

GSIFTPGSIFTPFTPFTP WEBDAVWEBDAV HTTPHTTP…

13


Deployment Scenario: Secure Shell (SSH)

Deployment Scenario: Secure Shell (SSH)

HTTP + WS-Sec./ HTTPS + WS-Sec. /

HTTPS mutual.


SFTP - FS

SFTP - FS

14


Deployment Scenario: Condor Pool

Deployment Scenario: Condor Pool

Condor command-line

wrapper

HTTP + WS-Sec./ HTTPS + WS-Sec. / HTTPS mutual.


NetworkFS

NetworkFS

15


Deployment Scenario: Globus 2.4.3

Deployment Scenario: Globus 2.4.3

16


Deployment Scenario: Grid Engine 6

Deployment Scenario: Grid Engine 6


NetworkFS

NetworkFS

17


Latest FeaturesLatest Features

Available in v2.0.0 (released 1/7/06) MPI Application through GT2 plugin

Simple non-standard JSDL extension <mpi:MPIApplication/> that extends <posix:POSIXApplication/> with a <mpi:ProcessorCount/> element

Authorisation based on JSDL structure Allow / deny submission based on a set of XPath rules and the

identities of the submitter (e.g. distinguished name).

Prototype Basic Execution Service (ogsa-bes) interface Demonstrated in the mini face-to-face in London last December Shown interoperability with the Uni. Of Virginia BES (.NET

based) implementation.

Available in v2.0.0 (released 1/7/06) MPI Application through GT2 plugin

Simple non-standard JSDL extension <mpi:MPIApplication/> that extends <posix:POSIXApplication/> with a <mpi:ProcessorCount/> element

Authorisation based on JSDL structure Allow / deny submission based on a set of XPath rules and the

identities of the submitter (e.g. distinguished name).

Prototype Basic Execution Service (ogsa-bes) interface Demonstrated in the mini face-to-face in London last December Shown interoperability with the Uni. Of Virginia BES (.NET

based) implementation.

18


Upcoming FeaturesUpcoming Features

New DRMConnectors PBS, EGEE, LSF, CCS

GridBS Using the Condor matchmaker with

GridSAM With Oxford University

Basic Execution Service Continue tracking the changes in the ogsa-

bes specification Support dual submission WS-interfaces

New DRMConnectors PBS, EGEE, LSF, CCS

GridBS Using the Condor matchmaker with

GridSAM With Oxford University

Basic Execution Service Continue tracking the changes in the ogsa-

bes specification Support dual submission WS-interfaces

19


GridSAM deploymentGridSAM deployment

UK NGS Supported by the Belfast e-Science Centre

UCL Newcastle Reading University Imperial College London … JSDL Portlet from DL

UK NGS Supported by the Belfast e-Science Centre

UCL Newcastle Reading University Imperial College London … JSDL Portlet from DL

20


GridSAM and AHEGridSAM and AHE

The Application Hosting Environment (AHE) uses GridSAM for deploying their application wrappers to resources on the Grid.

As part of the SPICE (Simulated Pore Interactive Computing Environment) demonstrator for SuperComputing’05 GridSAM (along with the AHE) was used to deploy exeutables on resources both part of the UK National Grid Service and the US TeraGrid. This helped towards SPICE winning the HPC Analytics

Challenge for demonstrating the use of innovative techniques in rigorous data analysis and high-end visualisation to solve a complex, real-world problem.

The Application Hosting Environment (AHE) uses GridSAM for deploying their application wrappers to resources on the Grid.

As part of the SPICE (Simulated Pore Interactive Computing Environment) demonstrator for SuperComputing’05 GridSAM (along with the AHE) was used to deploy exeutables on resources both part of the UK National Grid Service and the US TeraGrid. This helped towards SPICE winning the HPC Analytics

Challenge for demonstrating the use of innovative techniques in rigorous data analysis and high-end visualisation to solve a complex, real-world problem.

21


GridSAM and e-proteinGridSAM and e-protein

e-protein is performing protein annotation Using GridSAM for executing

bioinformatics jobs on the Grid

e-protein is performing protein annotation Using GridSAM for executing

bioinformatics jobs on the Grid

Web Interface

DRM

Job

Scheduler

Java ControlProgram

WorkflowPipeline

Job

3D-GENOMICS

Web Portal

DRM

Job

ControlProgram

Workflow

GridSAMGridSAM

Job

Job Descriptiondocument

Job Identifier

Sequence files

SSH tunn

el

Dasty Viewer

Level 1

Level 2

Level 3

22


GridSAM and MicroArrayGridSAM and MicroArray

Simple, robust access to up-to-date resources for microarray data storage and analysis

Distributed availability of the portal, allowing access to large compute power facilities required for microarray analysis and storage

Simple, robust access to up-to-date resources for microarray data storage and analysis

Distributed availability of the portal, allowing access to large compute power facilities required for microarray analysis and storage

Grid Compute clusterEMAAS Server

Scatter Plots

Simple Affy

PLM plots

23


GridSAM and eMineralsGridSAM and eMinerals

24


GridSAM at UCLGridSAM at UCL

GridSAMGridSAM

SGESGE ForkFork CondorCondor

ClientClient

Middle-tier

JSDLJSDLSOAP

• Integrating GridSAM with BPEL• Providing Condor WS DRMConnector

CondorCondor

Submissionmachine(s)

Schedd

SOAPClassAdClassAd

Condor-WSCondor-WS

25


GridSAM and NeuroGridGridSAM and NeuroGrid

The aim of the NeuroGrid consortium is to enhance collaboration between clinical, imaging and e-scientists to create a Grid-based network of neuroimaging centres and a neuroimaging tool-kit. Sharing data, experience and expertise will facilitate the archiving, curation, retrieval and analysis of imaging data from multiple sites and enable large-scale clinical studies.

The aim of the NeuroGrid consortium is to enhance collaboration between clinical, imaging and e-scientists to create a Grid-based network of neuroimaging centres and a neuroimaging tool-kit. Sharing data, experience and expertise will facilitate the archiving, curation, retrieval and analysis of imaging data from multiple sites and enable large-scale clinical studies.

26


GridSAM and HPCP InteropGridSAM and HPCP Interop

GridSAM was one of over 10 OGSA-BES (HPCP profile) services demonstrating interop Managed to interop with all but one other

system Profile was restrictive

Simple Security No data staging

Taking part in the SC07 interop

GridSAM was one of over 10 OGSA-BES (HPCP profile) services demonstrating interop Managed to interop with all but one other

system Profile was restrictive

Simple Security No data staging

Taking part in the SC07 interop


Questions?Questions?Official Download

http://www.omii.ac.ukProject Information and Documentation

http://gridsam.sourceforge.net

Official Downloadhttp://www.omii.ac.uk

Project Information and Documentationhttp://gridsam.sourceforge.net

london e-science centre gridsam a standards based approach to job submission a. stephen m c gough...

Documents