Quick-release fair scheduling

Anderson, James H.; Block, Aaron; Srinivasan, Anand

doi:10.1109/real.2003.1253261

Cited by 10 publications

(35 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The primary disadvantage of this approach is that spare capacity may not always be distributed proportionally among tasks. However, experimental results presented in [2] suggest that proportional distribution occurs in all but a few pathological cases.…”

Section: Utilizing Idle Timementioning

confidence: 94%

“…Jobs (and tasks) are said to be independent when they have no critical sections. 2 Second, a job may need to suspend its execution either for a fixed period of time or until some specified event occurs. Informally, a suspension is a period of time during which the task cannot make progress by executing and hence should not be granted processor time.…”

Section: Representing Jobsmentioning

confidence: 99%

“…Recall, for instance, the web server example discussed at the start of this chapter. Research into providing such guarantees under Pfair scheduling has already produced promising results [2,61,62,63], and suggests that further attention is warranted.…”

Section: Research Goalsmentioning

confidence: 99%

“…To avoid this penalty, Anderson, Block, and Srinivasan proposed an alternative approach called quick releasing [2]. In this approach, tasks are allowed to left-shift their subtask windows so that they are released only one or two slots after a detected idle slot.…”

Section: Utilizing Idle Timementioning

confidence: 99%

“…At some point at or before the extended deadline of the last subtask dedicated to this phase, denoted t d , the suspension 7 that follows (if one indeed exists) is initiated. This suspension ends at or before time t d + T [2] .θ. Hence, the first subtask associated with J [3] should not be released before time t d + T [2] .θ to ensure that allocated processor time is not wasted.…”

Section: Lemma 36mentioning

confidence: 99%

See 4 more Smart Citations

Locking in pfair-scheduled multiprocessor systems

Holman

Anderson

23rd IEEE Real-Time Systems Symposium, 2002. RTSS 2002.

Self Cite

View full text Add to dashboard Cite

The goal of this dissertation is to extend the Pfair scheduling approach in order to enable its efficient implementation on a real-time multiprocessor. At present, Pfair scheduling is the only known means for optimally scheduling recurrent real-time tasks on multiprocessors. In addition, there has been growing practical interest in such approaches due to their fairness guarantees. Unfortunately, prior work in this area has considered only the scheduling of independent tasks, which do not communicate with each other or share resources. The work presented herein focuses both on adding support for these actions and also on developing techniques for reducing various forms of implementation overhead, including that produced by task migrations and context switches. The thesis of this dissertation is: tasks can be efficiently synchronized in Pfair-scheduled systems and overhead due to common system events, such as context switches and migrations, can be reduced.This thesis is established through research in three areas. First, the pre-existing Pfair scheduling theory is extended to support the scheduling of groups of tasks as a single entity. Second, mechanisms for supporting both lock-based and lock-free synchronization are presented. Lockbased synchronization coordinates access to shared resources through the use of semaphores.On the other hand, lock-free operations are optimistically attempted and then retried if the operation fails. Last, the deployment of Pfair scheduling on a symmetric multiprocessor is considered.

show abstract

Section: Utilizing Idle Timementioning

confidence: 94%

Section: Representing Jobsmentioning

confidence: 99%