Processor Capacity Reserves for Multimedia Operating Systems

  title={Processor Capacity Reserves for Multimedia Operating Systems},
  author={C. W. Mercer and Stefan Savage and Hideyuki Tokuda},
Multimedia applications have timing requirements that cannot generally be satisfied using time-sharing scheduling algorithms and system structures. To effectively support these types of programs, operating systems must support processor capacity reservation. A capacity reservation and enforcement mechanism isolates programs from the timing and execution characteristics of other programs in the same way that a memory protection system isolates programs from memory access by other programs. In… 

Figures from this paper

Processor capacity reserves: an abstraction for managing processor usage
The reservation mechanism provides a way for application programs to specify their reservation requests and incorporates a scheduling framework which supports an admission control policy and the scheduler enforces reservations by relegating reserves to a time-sharing pool after their reservations have been consumed.
On Predictable Operating System Protocol Processing
This work explored the use of a resource reservation mechanism in the operating system with the idea that this mechanism can be used to support higher level quality of service management policies, and implemented this mechanism using the Real-Time Mach operating system as a base.
Operating system resource reservation for real-time and multimedia applications
This dissertation presents an enforced operating system resource reservation model for the design and implementation of predictable real-time programs and an implementation of processor reserves in Real-Time Mach shows that reserved multimedia applications can achieve predictablereal-time performance.
Requirements of a real-time multiprocessor operating system for multimedia applications
This paper focuses on identifying the requirements of a real-time operating system capable of fulfilling the needs of the multimedia applications typically executed on multiprocessor, mobile-oriented systems such as the Movidius platform.
Operating System Support for Coexistence of Real-Time and Conventional Scheduling
The scheduler of the Mach 3.0 Microkernel has been rewritten to allow a wide spectrum of scheduling policies, from real-time through time-sharing to background, to be selected simultaneously for different tasks executing on the same processor.
Slotted priorities: supporting real-time computing within general-purpose operating systems
A software architecture, called slotted priorities, is developed that is a way to add support for real-time computation to existing general-purpose operating systems for uniprocessor machine architectures.
Memory Resource Management for Real-Time Systems
An approach to dynamic memory management for real-time systems that allows adaptive allocation of memory resources to applications involving both periodic or aperiodic tasks and demonstrates the suitability of the proposed mechanism.
Providing Memory QoS Guarantees for Real-Time Applications
This paper focuses on a dynamic approach of QoS management for memory resource allocation based on the Skip-Over model and shows how it improves the service of task memory requests while providing them guarantees.
A Resource-Centric Approach To Multimedia Operating Systems
Fundamental drawbacks of the static pre-defined approach have led to the recent advocacy of dynamic, adaptive system designs which can dynamically adapt the Quality of Service (QoS) guarantees available to the system user.


Scheduling and IPC mechanisms for continuous media
This work proposes split-level CPU scheduling of lightweight processes in multiple address spaces, and memory-mapped streams for data movement between address spaces that can reduce scheduling and I/O overhead by a factor of 4 to 6.
The Role of Performance, Scheduling and Resource Reservation in Multimedia Systems
  • R. Herrtwich
  • Business
    Operating Systems of the 90s and Beyond
  • 1991
The relation between performance, scheduling, and reservation in multimedia systems is identified and it is concluded that performance alone will not be a solution in building multimedia platforms.
Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment
The problem of multiprogram scheduling on a single processor is studied from the viewpoint of the characteristics peculiar to the program functions that need guaranteed service. It is shown that an
The UNIX system: The fair share scheduler
  • G. J. Henry
  • Computer Science
    AT&T Bell Laboratories Technical Journal
  • 1984
This paper discusses the concepts of a fair share scheduler, the motivation for and history behind FSS, some practical FSS applications, the user and administrator interfaces to F SS, and the design philosophy of FSS.
Tutorial: Computer System Monitors
  • G. Nutt
  • Computer Science
  • 1975
The most important questions to be answered before attempting to monitor a machine are what to measure and why the measurement should be taken. There is no general answer to these questions, although
SRP: A Resource Reservation Protocol for Guaranteed-Performance
This report describes the Session Reservation Protocol (SRP), SRP is defined in the DARPA Internet family of protocols, it allows communicating peer entities to reserve the resources necessary to achieve given performance objectives (delay and throughput).
A scheduling philosophy for multiprocessing systems
A collection of basic ideas is presented, which have been involved by various workers over the past four years to provide a suitable framework for the design and analysis of multiprocessing systems.
UNIX as an Application Program
The implementation of Unix as a multithreaded application program running on the Mach kernel is described and the rationale, design, implementation history and performance of the system is presented.
Support for continuous media in the DASH system
The DASH resource model is defined as a basis for reserving and scheduling resources (disk, CPU, network, etc.) involved in end-to-end handling of continuous-media (information flowing continuously
Designing file systems for digital video and audio
A model that relates disk and device characteristics to the recording rate, and derive storage granularity and scattering parameters that guarantee continuous access is presented, which serves as a testbed for experimenting with policies and algorithms for multimedia storage.