Chapter10-OS7el - Operating Systems Internals and Design...

Info iconThis preview shows pages 1–14. Sign up to view the full content.

View Full Document Right Arrow Icon
Chapter 10 Multiprocessor  and Real-Time  Scheduling n Seventh Edition By William Stallings Operating  Systems: Internals  and  Design  Principles
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Operating Systems: Internals and Design Principles Bear in mind, Sir Henry, one of the phrases in that  queer old legend which Dr. Mortimer has read to us,  and avoid the moor in those hours of darkness when  the powers of evil are exalted. —  THE HOUND OF THE BASKERVILLES,  Arthur Conan Doyle
Background image of page 2
Classifications of  Multiprocessor Systems
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Synchronization  Granularity  and Processes
Background image of page 4
Independent Parallelism n No explicit synchronization  among processes n each represents a separate,  independent application or  job n Typical use is in a time-sharing  system
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Coarse and Very  Coarse-Grained Parallelism n Synchronization among processes, but at a very gross level n Good for concurrent processes running on a multiprogrammed  uniprocessor n can be supported on a multiprocessor with little or no change to user  software
Background image of page 6
Medium-Grained  Parallelism n Single application can be effectively implemented as a collection of  threads within a single process n programmer must explicitly specify the potential parallelism of an  application n there needs to be a high degree of coordination and interaction among the  threads of an application, leading to a medium-grain level of  synchronization n Because the various threads of an application interact so frequently,  scheduling decisions concerning one thread may affect the performance  of the entire application
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Fine-Grained Parallelism n Represents a much more complex use of parallelism than is found in the  use of threads n Is a specialized and fragmented area with many different approaches
Background image of page 8
Design Issues n The approach taken will  depend on the degree of  granularity of  applications and the  number of processors  available
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Assignment of  Processes to Processors n A disadvantage of static assignment is that one processor can be idle,  with an empty queue, while another processor has a backlog n to prevent this situation, a common queue can be used n another option is dynamic load balancing
Background image of page 10
Assignment of Processes to Processors n Both dynamic and static methods require some  way of assigning a process to a processor n Approaches: n Master/Slave n Peer
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Master/Slave Architecture n Key kernel functions always run on a particular processor n Master is responsible for scheduling n Slave sends service request to the master n Is simple and requires little enhancement to a uniprocessor  multiprogramming operating system n Conflict resolution is simplified because one processor has control of all  memory and I/O resources
Background image of page 12
Peer Architecture n Kernel can execute on any processor n Each processor does self-scheduling from the pool of available processes
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 14
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 12/14/2011 for the course CS 490 taught by Professor Weisskop during the Fall '11 term at University of Alabama - Huntsville.

Page1 / 65

Chapter10-OS7el - Operating Systems Internals and Design...

This preview shows document pages 1 - 14. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online