SlideShare une entreprise Scribd logo
1  sur  27
Télécharger pour lire hors ligne
A Chemistry-Inspired Workflow Management
System for Scientific Applications in Clouds
          7th IEEE International Conference on e–Science
                          Stockholm 2011




         Hector Fernandez, Cedric Tedeschi and Thierry Priol   00 MOIS 2011
Context

               • Scientific applications developed as workflows demanding more computational power.
                        Demand for deployment on Grids or Clouds.

               • Scientific workflow management systems (WMS):
Introduction




                        Implicit parallelism.
                        Data-driven coordination.
                        Support for the execution on Grids.

               • Examples of Scientific WMS: Taverna, Pegasus, Triana and Kepler.

               • Requirements of next generation Scientific WMS:
                  • Management of high degree of parallelism and distribution.
                  • No single point of failure.
                  • Scalability.
                  • Dynamicity.


                                                                                                2
Objectives

               • Ensure a workflow execution:
                   • Decentralized.
                   • Loosely coupled (coordination mechanism).
Introduction




                   • Dynamic.
                   • Autonomous.


               “Nature-inspired metaphors have been shown to be of high interest
                                   for service coordination.”
                                       [Viroli et al., 2009].


               ➔
                   Evaluate the viability of a nature-inspired scientific workflow system.




                                                                                             3
Chemical Programing Model (I)
                               • A program can be seen as a chemical solution:
Chemical Programing paradigm




                                   • Data: “floating” molecules in the solution.
                                   • Computation: chemical reactions between the molecules.

                               • Implicit parallelism and autonomy of reactions until inertia.
                                   • Expression of dynamicity.

                               • Data structure: Multiset (blackboard).
                                  • Containing all data molecules.
                                  • Reaction rules re-writing the multiset.

                               • Languages:
                                   • Gamma (Pioneered model) [Banâtre et al.,1990].
                                   • HOCL ( High-Order model) [Radenac, 2007].



                                                                                                 4
Chemical Programing Model (II)
Chemical Programing paradigm




                               • Example:
                                   • A reaction rules is written
                                                         replace-one P by M if C
                                     where P is a pattern which matches the required molecule, C is the reaction
                                    condition and M the result of the reaction.




                                                                                                             5
HOCL-based Workflow System




                             6
Chemical Coordination: Workflow Definition
                              • Express all data and control dependencies (reaction rules and molecules).
Chemical Coordination Model




                              • Molecular composition to express the logic of a workflow.




                                                             MULTISET



                                                                                                            7
Chemical Coordination: Generic Rules
                              • Independent from any chemical workflow representation.
Chemical Coordination Model




                              • Used by chemical engines.

                              • Common tasks during a workflow execution:
                                  • Service invocation rule.




                                  • Control and data transfer rule.




                                                                                         8
Chemical Coordination: Workflow Patterns
                              • Control flow can be expressed using some generic rules.
Chemical Coordination Model




                                  • Molecular composition of composed generic rules, reactions triggering reactions.




                                                                 Discriminator pattern




                              • More patterns: parallel split, synchronization, exclusive choice, synchronization merge, cancel
                                activity or simple merge.


                                                                                                                              9
Architectures
• Coordination mechanism built upon HOCL.

• Two possible architectures for our workflow system:
    • Centralized.
    • Decentralized.




                                                        10
Centralized Architecture
                           • Central node coordinates all data and control flow between the Web services.
Chemical Workflow System




                              • A chemical encapsulation per Web service participating in the workflow.
                              • Multiset as storage space containing the workflow definition.
                              • Chemical engine processing the content of the multiset.




                                                                                                            11
Decentralized Architecture (I)
                           • Nodes communicating through a shared address space.
Chemical Workflow System




                               • Persistent.
                               • Fault-tolerant.



                           • Workflow executed in parts corresponding with each Web service.
                              • Data and control transfer through this shared space.
                              • Each node is co-responsible of the execution.




                                                                                               12
Decentralized Architecture (III)
                           • Multiset, dynamic and decentralized coordination mechanism.
                               • Acts as a shared address space containing both control and data flows.
Chemical Workflow System




                               • ChWSes communicate through the multiset. (reading and writing)
                               • Physically distributed over ChWSes storage spaces.




                                                                                                          13
Implementation




                 14
Centralized Prototype
                           • Service caller
                               • Interface with all the concrete Wses.
Chemical Workflow System




                               • Implemented based on Daios framework.
                           • HOCL Interpreter
                               • Central engine.
                           • Multiset
                               • Workflow definition.
                               • Processed by the HOCL Interpreter.




                                                                         15
Decentralized Prototype
                           • Chemical Web Services (ChWS):
Chemical Workflow System




                               • Service caller
                                   Interface with one concrete WS.
                               • Local Multiset
                                   Temporary store space.
                               • HOCL Interpreter
                                   Local workflow engine.
                               • JMS publisher/subscriber
                                   Communication module with the Multiset.


                           • Multiset:
                               • Storage space containing the whole workflow.
                               • Similarities with tuplespaces.
                               • JMS publisher/subscriber
                                    Communication module with the ChWSes.



                                                                                16
Experiments




              17
Experiments (I)
                      • Objective: Establish the viability of our chemical workflow engine in comparison with four WMS.
                      • Four workflow engines:
                          • Kepler 2.0.
Performance Results




                          • Taverna Workbench 2.2.0.
                          • Centralized prototype (HOCL Cen.).
                          • Decentralized prototype (HOCL Dec.).
                      • Real scenarios:
                          • Cardiovascular image analysis workflow (CardiacAnalysis) [7].
                          • Astronomical image mosaics workflow (Montage) [8].
                          • Bio-informatics workflow (BlastReport) [9].

                                                      CardiacAnalysis     Montage      BlastReport
                                 Num. services        6                  27            5
                                 Data exchanged       High               Low           Medium
                                 Coord. Complex       High               Medium        Low

                      • Experiments conducted on the French research infrastructure Grid'5000.


                                                                                                                    18
Performance Results


                      Experiments (II)
Performance Results


                      Experiments (II)
Performance Results


                           Results




21
Centralized Experiment
                      Data and computation intensive workflows.
                        • Size and processing time increment.
Performance Results




                      Centralized coordination better for workflows with reduced computation.




                                                                                                22
Decentralized Experiment
                      Reduced computation workflows
                        • Slightly increment of time (network latency).
Performance Results




                      Data and computation-intensive workflows show the benefits of a decentralized
                      coordination.




                                                                                                  23
Conclusion
          • Chemical model is well featured for decentralized workflow execution.
                 Proof of concept of the chemical workflow system.
Summary




          • Our proposal: High-level decentralized coordination mechanism.
              • Decentralized Architecture:
                   Chemical web services working as local engines.
                   Multiset as shared communication space.
                   A High-order chemical language for workflows.
                    • Concepts for decentralized coordination.
                    • Control and data driven.




                                                                                    24
On-going Work

• Implementation of a distributed multiset.



• Workflow scheduling in Federated Clouds using the chemical model.



• Modelling Agile Service Networks using the chemical choreography
  coordination model.




                                                                      25
Questions   ?




                26
THANKS !




           27

Contenu connexe

Similaire à A Chemistry-Inspired Workflow Management System for Scientific Applications on Clouds

Ashish pandey huawei osi_days2011_cgroups_understanding_better
Ashish pandey huawei osi_days2011_cgroups_understanding_betterAshish pandey huawei osi_days2011_cgroups_understanding_better
Ashish pandey huawei osi_days2011_cgroups_understanding_bettersuniltomar04
 
Intro to Table-Grouping™ technology
Intro to Table-Grouping™ technologyIntro to Table-Grouping™ technology
Intro to Table-Grouping™ technologyDavid McFarlane
 
1112 agile approach to pci dss development
1112 agile approach to pci dss development1112 agile approach to pci dss development
1112 agile approach to pci dss developmentbezpiecznik
 
[EN] Club Automation presentation "Quality Model for Industrial Automation", ...
[EN] Club Automation presentation "Quality Model for Industrial Automation", ...[EN] Club Automation presentation "Quality Model for Industrial Automation", ...
[EN] Club Automation presentation "Quality Model for Industrial Automation", ...Itris Automation Square
 
Modelling and Managing Ambiguous Context in Intelligent Environments
Modelling and Managing Ambiguous Context in Intelligent EnvironmentsModelling and Managing Ambiguous Context in Intelligent Environments
Modelling and Managing Ambiguous Context in Intelligent EnvironmentsAitor Almeida
 
Oracle Crystal Ball Screens
Oracle Crystal Ball ScreensOracle Crystal Ball Screens
Oracle Crystal Ball ScreensDave Maskell
 
Mas overview dirks at cni dec11b
Mas overview dirks at cni   dec11bMas overview dirks at cni   dec11b
Mas overview dirks at cni dec11bLee Dirks
 
Using Database Constraints Wisely
Using Database Constraints WiselyUsing Database Constraints Wisely
Using Database Constraints Wiselybarunio
 
Dynamics NAV, Windows Azure & Windows Phone 7, Eric Wauters
Dynamics NAV, Windows Azure & Windows Phone 7, Eric WautersDynamics NAV, Windows Azure & Windows Phone 7, Eric Wauters
Dynamics NAV, Windows Azure & Windows Phone 7, Eric Wautersdynamicscom
 
Cloud Computing with InduSoft
Cloud Computing with InduSoftCloud Computing with InduSoft
Cloud Computing with InduSoftAVEVA
 
Getting started with Cloud Foundry
Getting started with Cloud FoundryGetting started with Cloud Foundry
Getting started with Cloud FoundryLode Vermeiren
 
Getting started with Cloud Foundry
Getting started with Cloud FoundryGetting started with Cloud Foundry
Getting started with Cloud FoundryLode Vermeiren
 
A short introduction to the cloud
A short introduction to the cloudA short introduction to the cloud
A short introduction to the cloudLaurent Eschenauer
 

Similaire à A Chemistry-Inspired Workflow Management System for Scientific Applications on Clouds (20)

Use case+2-0
Use case+2-0Use case+2-0
Use case+2-0
 
Ashish pandey huawei osi_days2011_cgroups_understanding_better
Ashish pandey huawei osi_days2011_cgroups_understanding_betterAshish pandey huawei osi_days2011_cgroups_understanding_better
Ashish pandey huawei osi_days2011_cgroups_understanding_better
 
Intro to Table-Grouping™ technology
Intro to Table-Grouping™ technologyIntro to Table-Grouping™ technology
Intro to Table-Grouping™ technology
 
1112 agile approach to pci dss development
1112 agile approach to pci dss development1112 agile approach to pci dss development
1112 agile approach to pci dss development
 
[EN] Club Automation presentation "Quality Model for Industrial Automation", ...
[EN] Club Automation presentation "Quality Model for Industrial Automation", ...[EN] Club Automation presentation "Quality Model for Industrial Automation", ...
[EN] Club Automation presentation "Quality Model for Industrial Automation", ...
 
MUGGES: User-aware Semantic Location Models for Service Provision
MUGGES: User-aware Semantic Location Models for Service ProvisionMUGGES: User-aware Semantic Location Models for Service Provision
MUGGES: User-aware Semantic Location Models for Service Provision
 
SOA OSB BPEL BPM Presentation
SOA OSB BPEL BPM PresentationSOA OSB BPEL BPM Presentation
SOA OSB BPEL BPM Presentation
 
Modelling and Managing Ambiguous Context in Intelligent Environments
Modelling and Managing Ambiguous Context in Intelligent EnvironmentsModelling and Managing Ambiguous Context in Intelligent Environments
Modelling and Managing Ambiguous Context in Intelligent Environments
 
SOAR 2009 (Cuesta)
SOAR 2009 (Cuesta)SOAR 2009 (Cuesta)
SOAR 2009 (Cuesta)
 
Oracle Crystal Ball Screens
Oracle Crystal Ball ScreensOracle Crystal Ball Screens
Oracle Crystal Ball Screens
 
Mas overview dirks at cni dec11b
Mas overview dirks at cni   dec11bMas overview dirks at cni   dec11b
Mas overview dirks at cni dec11b
 
C. Fornadley UCLA Collab Hosting of Moodle-v2
C. Fornadley UCLA Collab Hosting of Moodle-v2C. Fornadley UCLA Collab Hosting of Moodle-v2
C. Fornadley UCLA Collab Hosting of Moodle-v2
 
Using Database Constraints Wisely
Using Database Constraints WiselyUsing Database Constraints Wisely
Using Database Constraints Wisely
 
Ubiquisys at Femtocells Americas 11
Ubiquisys at Femtocells Americas 11Ubiquisys at Femtocells Americas 11
Ubiquisys at Femtocells Americas 11
 
Dynamics NAV, Windows Azure & Windows Phone 7, Eric Wauters
Dynamics NAV, Windows Azure & Windows Phone 7, Eric WautersDynamics NAV, Windows Azure & Windows Phone 7, Eric Wauters
Dynamics NAV, Windows Azure & Windows Phone 7, Eric Wauters
 
Cloud Computing with InduSoft
Cloud Computing with InduSoftCloud Computing with InduSoft
Cloud Computing with InduSoft
 
Ipanema
IpanemaIpanema
Ipanema
 
Getting started with Cloud Foundry
Getting started with Cloud FoundryGetting started with Cloud Foundry
Getting started with Cloud Foundry
 
Getting started with Cloud Foundry
Getting started with Cloud FoundryGetting started with Cloud Foundry
Getting started with Cloud Foundry
 
A short introduction to the cloud
A short introduction to the cloudA short introduction to the cloud
A short introduction to the cloud
 

Dernier

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDropbox
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Bhuvaneswari Subramani
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Orbitshub
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...apidays
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Jeffrey Haguewood
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdfSandro Moreira
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontologyjohnbeverley2021
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 

Dernier (20)

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
DBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor PresentationDBX First Quarter 2024 Investor Presentation
DBX First Quarter 2024 Investor Presentation
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 

A Chemistry-Inspired Workflow Management System for Scientific Applications on Clouds

  • 1. A Chemistry-Inspired Workflow Management System for Scientific Applications in Clouds 7th IEEE International Conference on e–Science Stockholm 2011 Hector Fernandez, Cedric Tedeschi and Thierry Priol 00 MOIS 2011
  • 2. Context • Scientific applications developed as workflows demanding more computational power.  Demand for deployment on Grids or Clouds. • Scientific workflow management systems (WMS): Introduction  Implicit parallelism.  Data-driven coordination.  Support for the execution on Grids. • Examples of Scientific WMS: Taverna, Pegasus, Triana and Kepler. • Requirements of next generation Scientific WMS: • Management of high degree of parallelism and distribution. • No single point of failure. • Scalability. • Dynamicity. 2
  • 3. Objectives • Ensure a workflow execution: • Decentralized. • Loosely coupled (coordination mechanism). Introduction • Dynamic. • Autonomous. “Nature-inspired metaphors have been shown to be of high interest for service coordination.” [Viroli et al., 2009]. ➔ Evaluate the viability of a nature-inspired scientific workflow system. 3
  • 4. Chemical Programing Model (I) • A program can be seen as a chemical solution: Chemical Programing paradigm • Data: “floating” molecules in the solution. • Computation: chemical reactions between the molecules. • Implicit parallelism and autonomy of reactions until inertia. • Expression of dynamicity. • Data structure: Multiset (blackboard). • Containing all data molecules. • Reaction rules re-writing the multiset. • Languages: • Gamma (Pioneered model) [Banâtre et al.,1990]. • HOCL ( High-Order model) [Radenac, 2007]. 4
  • 5. Chemical Programing Model (II) Chemical Programing paradigm • Example: • A reaction rules is written replace-one P by M if C where P is a pattern which matches the required molecule, C is the reaction condition and M the result of the reaction. 5
  • 7. Chemical Coordination: Workflow Definition • Express all data and control dependencies (reaction rules and molecules). Chemical Coordination Model • Molecular composition to express the logic of a workflow. MULTISET 7
  • 8. Chemical Coordination: Generic Rules • Independent from any chemical workflow representation. Chemical Coordination Model • Used by chemical engines. • Common tasks during a workflow execution: • Service invocation rule. • Control and data transfer rule. 8
  • 9. Chemical Coordination: Workflow Patterns • Control flow can be expressed using some generic rules. Chemical Coordination Model • Molecular composition of composed generic rules, reactions triggering reactions. Discriminator pattern • More patterns: parallel split, synchronization, exclusive choice, synchronization merge, cancel activity or simple merge. 9
  • 10. Architectures • Coordination mechanism built upon HOCL. • Two possible architectures for our workflow system: • Centralized. • Decentralized. 10
  • 11. Centralized Architecture • Central node coordinates all data and control flow between the Web services. Chemical Workflow System • A chemical encapsulation per Web service participating in the workflow. • Multiset as storage space containing the workflow definition. • Chemical engine processing the content of the multiset. 11
  • 12. Decentralized Architecture (I) • Nodes communicating through a shared address space. Chemical Workflow System • Persistent. • Fault-tolerant. • Workflow executed in parts corresponding with each Web service. • Data and control transfer through this shared space. • Each node is co-responsible of the execution. 12
  • 13. Decentralized Architecture (III) • Multiset, dynamic and decentralized coordination mechanism. • Acts as a shared address space containing both control and data flows. Chemical Workflow System • ChWSes communicate through the multiset. (reading and writing) • Physically distributed over ChWSes storage spaces. 13
  • 15. Centralized Prototype • Service caller • Interface with all the concrete Wses. Chemical Workflow System • Implemented based on Daios framework. • HOCL Interpreter • Central engine. • Multiset • Workflow definition. • Processed by the HOCL Interpreter. 15
  • 16. Decentralized Prototype • Chemical Web Services (ChWS): Chemical Workflow System • Service caller  Interface with one concrete WS. • Local Multiset  Temporary store space. • HOCL Interpreter  Local workflow engine. • JMS publisher/subscriber  Communication module with the Multiset. • Multiset: • Storage space containing the whole workflow. • Similarities with tuplespaces. • JMS publisher/subscriber  Communication module with the ChWSes. 16
  • 18. Experiments (I) • Objective: Establish the viability of our chemical workflow engine in comparison with four WMS. • Four workflow engines: • Kepler 2.0. Performance Results • Taverna Workbench 2.2.0. • Centralized prototype (HOCL Cen.). • Decentralized prototype (HOCL Dec.). • Real scenarios: • Cardiovascular image analysis workflow (CardiacAnalysis) [7]. • Astronomical image mosaics workflow (Montage) [8]. • Bio-informatics workflow (BlastReport) [9]. CardiacAnalysis Montage BlastReport Num. services 6 27 5 Data exchanged High Low Medium Coord. Complex High Medium Low • Experiments conducted on the French research infrastructure Grid'5000. 18
  • 19. Performance Results Experiments (II)
  • 20. Performance Results Experiments (II)
  • 21. Performance Results Results 21
  • 22. Centralized Experiment Data and computation intensive workflows. • Size and processing time increment. Performance Results Centralized coordination better for workflows with reduced computation. 22
  • 23. Decentralized Experiment Reduced computation workflows • Slightly increment of time (network latency). Performance Results Data and computation-intensive workflows show the benefits of a decentralized coordination. 23
  • 24. Conclusion • Chemical model is well featured for decentralized workflow execution.  Proof of concept of the chemical workflow system. Summary • Our proposal: High-level decentralized coordination mechanism. • Decentralized Architecture:  Chemical web services working as local engines.  Multiset as shared communication space.  A High-order chemical language for workflows. • Concepts for decentralized coordination. • Control and data driven. 24
  • 25. On-going Work • Implementation of a distributed multiset. • Workflow scheduling in Federated Clouds using the chemical model. • Modelling Agile Service Networks using the chemical choreography coordination model. 25
  • 26. Questions ? 26
  • 27. THANKS ! 27