The schedulability of systems using fixed priority pre-emptive scheduling can be improved by the use of non-pre-emptive regions at the end of each task's execution, an approach referred to as deferred pre-emption. Choosing the appropriate length for the final non-pre-emptive region of each task is a trade-off between improving the worst-case response time of the task itself and increasing the amount of blocking imposed on higher priority tasks. In this paper we present an optimal algorithm for determining both the priority ordering of tasks and the lengths of their final non-pre-emptive regions. This algorithm is optimal for fixed priority scheduling with deferred pre-emption, in the sense that it is guaranteed to find a schedulable combination of priority ordering and final non-pre-emptive region lengths if such a schedulable combination exists.
Optimal Fixed Priority Scheduling with Deferred Preemptions / Davis, Rob; Bertogna, Marko. - STAMPA. - (2012), pp. 39-50. (Intervento presentato al convegno 33rd IEEE Real-Time Systems Symposium (RTSS 2012) tenutosi a San Juan, Puerto Rico nel 4-7 Dec. 2012).
Optimal Fixed Priority Scheduling with Deferred Preemptions
BERTOGNA, Marko
2012
Abstract
The schedulability of systems using fixed priority pre-emptive scheduling can be improved by the use of non-pre-emptive regions at the end of each task's execution, an approach referred to as deferred pre-emption. Choosing the appropriate length for the final non-pre-emptive region of each task is a trade-off between improving the worst-case response time of the task itself and increasing the amount of blocking imposed on higher priority tasks. In this paper we present an optimal algorithm for determining both the priority ordering of tasks and the lengths of their final non-pre-emptive regions. This algorithm is optimal for fixed priority scheduling with deferred pre-emption, in the sense that it is guaranteed to find a schedulable combination of priority ordering and final non-pre-emptive region lengths if such a schedulable combination exists.Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris