| 1. |
- Keskin, Ugur, et al.
(författare)
-
Improving the global schedulability analysis of overrun without payback
- 2010
-
Ingår i: Proceedings of the Work-In-Progress (WIP) session of the 22nd Euromicro Conference on Real-Time Systems (ECRTS'10).
-
Konferensbidrag (refereegranskat)abstract
- Overrun without payback has been proposed asa mechanism for a stack resource policy (SRP) based synchronizationprotocol for hierarchical scheduling frameworks(HSFs). In this paper we reconsider the global schedulabilityanalysis of an HSF based on two-level fixed-priority preemptivescheduling (FPPS) using overrun without payback asa mechanism. Improved analysis is presented based on theobservation that there is no need to guarantee the overrunbudget before the end of the budget period, because thatadditional amount of resources is only meant to prevent depletionof a budget during global resource access. The resultingimprovement is illustrated by means of an example. Thepossibility to discard the remainder of an overrun budget upona replenishment is briefly considered as a further improvementand its potential is shown using the same example.
|
|
| 2. |
- Van Den Heuvel, M. M. H. P., et al.
(författare)
-
Optimal and fast composition of resource-sharing components in hierarchical real-time systems
- 2014
-
Ingår i: RTCSA 2014 - 20th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications. - 9781479939534 ; , s. Article number 6910547-
-
Konferensbidrag (refereegranskat)abstract
- In this paper we consider various flavors of the stack resource policy (SRP) for arbitrating access to shared resources in a hierarchical scheduling framework (HSF) upon a uni-processor. We propose algorithms for exploring and selecting the (local) resource ceilings within components, such that it results in an optimal composition of resource-sharing components in an HSF. Existing methods are non-optimal, because (i) they optimize just the length of global non-preemptive execution of tasks and (ii) they do not detect whether or not resources are shared globally (i.e., between tasks of different components). Lifting these limitations leads to an exponential growth of the design space. This paper contributes a fast three-step methodology which lifts these limitations, i.e., we apply the SRP at each level of the HSF to just the resources being shared. Our algorithm selects those component interfaces (i.e., by fixing the local resource ceilings of each component) that minimize the system load.
|
|
| 3. |
- van den Heuvel, Martijn, et al.
(författare)
-
Opaque Analysis for Resource Sharing in Compositional Real-Time Systems
- 2011
-
Ingår i: 4th Workshop on Compositional Theory and Technology for Real-Time Embedded Systems (CRTS'11).
-
Konferensbidrag (refereegranskat)abstract
- In this paper we propose opaque analysis methods to integrate dependent real-time components into hierarchical fixed-priority scheduled systems. To arbitrate mutually exclusive resource access between components, we consider two existing protocols: HSRP - comprising overrun with and without payback - and SIRAP. An opaque analysis allows to postpone the choice of a synchronization protocol until component integration time. First, we identify the sources of pessimism in the existing analysis techniques and we conclude that both protocols assume different models in their local analysis. In particular, the compo- sitional analysis for overrun with payback (OWP) is not opaque and is pessimistic. The latter makes OWP expensive compared to its counter part without a payback mechanism (ONP). This paper presents an opaque and less pessimistic OWP analysis. Secondly, SIRAP requires more timing information to perform a task-level schedulability analysis. In many practical situations, however, detailed timing characteristics of tasks are hard to obtain. We introduce an opaque analysis for SIRAP using the analysis of ONP to reduce the required timing information during the local analysis. We show that the analysis for ONP cannot deem systems schedulable which are infeasible with SIRAP. The SIRAP analysis may therefore reduce the required system resources of a component by sacrificing the choice for an arbitrary synchronization protocol at system integration time.
|
|
| 4. |
|
|
