design and implemention of a plugin scheduler for diet
play

Design and Implemention of a Plugin Scheduler for DIET March 11, - PowerPoint PPT Presentation

Background on DIET Plugin Scheduler Design and Implemention of a Plugin Scheduler for DIET March 11, 2005 Design and Implemention of a Plugin Scheduler for DIET Background on DIET Plugin Scheduler Outline Background on DIET 1


  1. Background on DIET Plugin Scheduler Design and Implemention of a Plugin Scheduler for DIET March 11, 2005 Design and Implemention of a Plugin Scheduler for DIET

  2. Background on DIET Plugin Scheduler Outline Background on DIET 1 Computational Grid Computing DIET Framework Motivation for Plugin Scheduler Plugin Scheduler 2 Design Implementation Current Status (Near-)Future Work Design and Implemention of a Plugin Scheduler for DIET

  3. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Outline Background on DIET 1 Computational Grid Computing DIET Framework Motivation for Plugin Scheduler Plugin Scheduler 2 Design Implementation Current Status (Near-)Future Work Design and Implemention of a Plugin Scheduler for DIET

  4. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler The Computational Grid and DIET Grid platforms heterogeneous computational resources irregular network topologies dynamic resource performance DIET philosophy and design principles server and broker agent model hierarchical organization flexible deployment options Design and Implemention of a Plugin Scheduler for DIET

  5. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler DIET Overview Basic progress of a DIET call: DIET hieararchy: MA . . . LA 1 . . . SeD 1 SeD 2 SeD 3 Design and Implemention of a Plugin Scheduler for DIET

  6. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler DIET Overview Basic progress of a DIET call: Client requests service from the DIET hieararchy: Master Agent (MA) MA . . . LA 1 . . . SeD 1 SeD 2 SeD 3 Design and Implemention of a Plugin Scheduler for DIET

  7. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler DIET Overview Basic progress of a DIET call: Client requests service from the DIET hieararchy: Master Agent (MA) The MA interrogates the DIET MA hierarchy . . . LA 1 . . . SeD 1 SeD 2 SeD 3 Design and Implemention of a Plugin Scheduler for DIET

  8. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler DIET Overview Basic progress of a DIET call: Client requests service from the DIET hieararchy: Master Agent (MA) The MA interrogates the DIET MA hierarchy Each Server Daemon (SeD) . . . responds with an execution time LA 1 estimate E 2 E 3 . . . E 1 SeD 1 SeD 2 SeD 3 Design and Implemention of a Plugin Scheduler for DIET

  9. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler DIET Overview Basic progress of a DIET call: Client requests service from the DIET hieararchy: Master Agent (MA) The MA interrogates the DIET MA hierarchy Each Server Daemon (SeD) [ ] E 3 E 1 E 2 . . . responds with an execution time LA 1 estimate Each Local Agent (LA) compiles . . . and sorts the responses by SeD 1 SeD 2 SeD 3 execution time Design and Implemention of a Plugin Scheduler for DIET

  10. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler DIET Overview Basic progress of a DIET call: Client requests service from the DIET hieararchy: Master Agent (MA) [ ] E 3 E 1 E 5 The MA interrogates the DIET MA hierarchy Each Server Daemon (SeD) . . . responds with an execution time LA 1 estimate Each Local Agent (LA) compiles . . . and sorts the responses by SeD 1 SeD 2 SeD 3 execution time MA returns a list of servers to the client Design and Implemention of a Plugin Scheduler for DIET

  11. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler DIET Overview Basic progress of a DIET call: Client requests service from the DIET hieararchy: Master Agent (MA) The MA interrogates the DIET MA hierarchy Each Server Daemon (SeD) . . . responds with an execution time LA 1 estimate Each Local Agent (LA) compiles . . . and sorts the responses by SeD 1 SeD 2 SeD 3 execution time MA returns a list of servers to the client Client launches service directly on SeD Design and Implemention of a Plugin Scheduler for DIET

  12. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Some Implementation Details Three primary components of the DIET system: Design and Implemention of a Plugin Scheduler for DIET

  13. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Some Implementation Details Three primary components of the DIET system: Agents (MA and LA) implemented in C++ scope: DIET internal at runtime, assembled top-down Design and Implemention of a Plugin Scheduler for DIET

  14. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Some Implementation Details Three primary components of the DIET system: Agents (MA and LA) implemented in C++ scope: DIET internal at runtime, assembled top-down Servers (SeD) implemented in either C or C++ scope: application service developer API hierarchy must exist Design and Implemention of a Plugin Scheduler for DIET

  15. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Some Implementation Details Three primary components of the DIET system: Agents (MA and LA) implemented in C++ scope: DIET internal at runtime, assembled top-down Servers (SeD) implemented in either C or C++ scope: application service developer API hierarchy must exist Client implemented in either C or C++ scope: application developer or user uses services existing at execution time Design and Implemention of a Plugin Scheduler for DIET

  16. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Some Implementation Details Three primary components of the DIET system: Agents (MA and LA) implemented in C++ scope: DIET internal at runtime, assembled top-down Servers (SeD) implemented in either C or C++ scope: application service developer API hierarchy must exist Client implemented in either C or C++ scope: application developer or user uses services existing at execution time Communication infrastructure CORBA-based model omniORB implementation Design and Implemention of a Plugin Scheduler for DIET

  17. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Advantages and Limitations Advantages: scalability: hierarchy enables parallel server interrogation and distributed scheduling of requests straighforward interface: just the name and the correct number of arguments are needed abstraction: distributed platform details are largely hidden Design and Implemention of a Plugin Scheduler for DIET

  18. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Advantages and Limitations Advantages: scalability: hierarchy enables parallel server interrogation and distributed scheduling of requests straighforward interface: just the name and the correct number of arguments are needed abstraction: distributed platform details are largely hidden Limitations: deployment of appropriate hierarchies for a given grid platform is non-obvious limited consideration of inter-task factors non-standard application-specific performance measures Design and Implemention of a Plugin Scheduler for DIET

  19. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Advantages and Limitations Advantages: scalability: hierarchy enables parallel server interrogation and distributed scheduling of requests straighforward interface: just the name and the correct number of arguments are needed abstraction: distributed platform details are largely hidden Limitations: deployment of appropriate hierarchies for a given grid platform is non-obvious limited consideration of inter-task factors non-standard application-specific performance measures Design and Implemention of a Plugin Scheduler for DIET

  20. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Application-specific Performance Use Case Motivation DIET hieararchy: basic DIET deployment MA . . . LA 1 . . . SeD 1 SeD 2 SeD 3 Design and Implemention of a Plugin Scheduler for DIET

  21. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Application-specific Performance Use Case Motivation DIET hieararchy: basic DIET deployment client application with data MA dependencies . . . LA 1 . . . SeD 1 SeD 2 SeD 3 Design and Implemention of a Plugin Scheduler for DIET

  22. Computational Grid Computing Background on DIET DIET Framework Plugin Scheduler Motivation for Plugin Scheduler Application-specific Performance Use Case Motivation DIET hieararchy: basic DIET deployment client application with data MA dependencies . . . LA 1 . . . SeD 1 SeD 2 SeD 3 Design and Implemention of a Plugin Scheduler for DIET

Recommend


More recommend