T. P. Baker. Stack-based scheduling of real-time processes. Real-Time Systems Journal, 3(1):67--99, March 1991.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....scheduling algorithms is that only independent tasks that do not synchronize or share resources have been considered. In contrast, tasks in real systems usually are not independent. Synchronization entails additional overhead, which must be taken into account when determining system feasibility [2, 6, 18, 19, 20, 22]. Unfortunately, prior work on real time synchronization has been directed at uniprocessor systems, or systems implemented using non fair scheduling algorithms (or both) and thus cannot be directly applied in fair scheduled multiprocessor systems. Indeed, synchronization issues in fair scheduled ....

T. Baker. Stack-based scheduling of real-time processes. Real-Time Systems, 3(1):67--99, March 1991.

....carefully controlled in a hard real time system, it may be difficult or impossible to ensure that task deadlines are always met. For this reason, substantial effort has been devoted to the problem of bounding the duration of priority inversions in real time systems either by using kernel support [19, 26, 44, 69, 71] or byusing scheduling techniques [29, 65, 83] Because techniques based on the former approach are very relevant to this dissertation, they are briefly described below. All of these techniques are described in detail in Chapter 2. Typically, when priority inversion is controlled using kernel ....

....expensive, the PCP can result in loss of predictability because the currently known scheduling analysis [71] for the PCP ignores the effect of these extra context switches. Furthermore, these additional context switches can significantly increase blocking factors. The stack resource policy (SRP) [19] eliminates additional context switches by delaying the execution of a task until all required resources become available. Unlike the PIP PCP, the SRP differentiates between prioritylevels and preemption levels. The notion of preemption levels is based on the relative deadlines of tasks# it is ....

[Article contains additional citation context not shown here]

T. P. Baker. Stack-based scheduling of real-time processes. Real-Time Systems, 3(1):67--99, March1991.

....pre run time schedulability test (16) valid for non pre emptive, independent and periodic tasks, for which the relativedeadline is equal to the period. i i (16) Inequality (16) can be easily updated to include blocking periods due to the non independence of the tasks. In [7], the author updated inequality (16) to: N i i i i i i i B T , 1 (17) where B i is the maximum blocking a task i can suffer, considering the stack resource protocol (SRP) The key idea behind the SRP is that when a job needs a resource which is not available, it is blocked at the ....

....tasks, dispatched according to the EDF scheme. Similarly to the updating of (8) to (10) 17) can be updated to a simpler (but more pessimistic) test: 1 max i N i i N i i B T (18) where B i is defined as: j i j i C B = max (19) Another relevant result from [7] is that (17) can also be extended to task sets with relative deadlines smaller than periods: N i i i i i i B D , 1 (20) 7 As a corollary, inequality (16) can be extended for task sets with D i T i : i i (21) These simple utilisation based tests ( 18) and (20) are ....

Baker, T. (1991). Stack-Based Scheduling of Real-Time Processes. In Real-Time Systems, Vol. 3, No. 1, pp. 67-99.

.... all the operations have the same release time [1 precedence minimize the maximum lateness] Lawler gives the first to last rule which is optimal [6, 7] If the operations do not have the same release time we obtain a NP hard problem [8] but if preemption is allowed the problem is polynomial [9]. Also, for the problem [1 precedence, D ] Blazewicz gives an polynomial solution [10] In the general case of systems for which all the operations may have precedence, latency and also periodicity constraints, to our best knowledge, there is no result for the problem with one operator. 3 The ....

T.P. Baker. Stack-based scheduling of realtime processes. The Journal of Real-time Systems, 1991.

....the NASA Mars Pathfinder rover [2] when priority inversion caused repeated system resets and drastically limited its ability to communicate back to the Earth. Because the negative impact of priority inversion can be significant, much work has been done to address this resource management problem [1, 3, 4, 5, 6]. The general idea behind these approaches is to boost the priority of a low priority process holding the resource so that it can run and release the resource to get out of the way of a high priority process waiting on the resource to run. However, there are four important limitations that occur ....

....However, priority ceilings assume that the resources required by all processes are known in advance before the execution of any process starts. This assumption holds for some real time embedded systems, but does not hold for general purpose systems. Other approaches such as preemption ceilings [4] can also be used in real time embedded systems but also make assumptions about system operation that do not hold for general purpose systems. Like priority inheritance, priority ceilings typically assume static priorities to minimize overhead and does not address the issue of determining resource ....

T. Baker, "Stack-based scheduling of real-time processes, " Real-Time Systems, vol. 3, Mar. 1991.

....Sections (NCSs) 5] can be used in tasks for the use of shared resources. What we need to do is to specify NCSs and their durations. NCSs in combination with inheritance have been used in other protocols such as the well known Priority Ceiling (PC) protocol [6] and the Stack Resource protocol [7]. An in depth overview is given by Rajkumar [8] Sha et al. [9] give an overview of how to generalise PC for DM under blocking and they present how to use this protocol for a practical system implementation. The protocol we present in this chapter has similarities with PC and SR. PC is from the ....

....It asks as input a task specification according to table 2 and it produces a graphical output according to figure 4. The tool can also handle analysis of resource using task sets scheduled with other protocols like Rate Monotonic [1] Deadline Monotonic [4] and the Stack Resource protocol [7]. These protocols are beyond the scope of this paper. Currently we have three EDFI implementations: in Linux RT, in Plan 9 and in RTY. They have in common that one timer controls the RT portion of the scheduler: the Release Timer goes o# when a task in the Wait Queue must be released. If that ....

T. P. Baker, "Stack-based scheduling of real-time processes," The journal of real-time systems, vol. 3, no. 1, pp. 67--99, 1991.

....given that it is the only task running in the system. A preemption level ### # is associated with each task # . The essential property of preemption levels is that if a job # h preempts a job # l then ### h # #### l #. The relative deadline of a job can be used to define the preemption levels [2]. Each invocation of the task is called a job. A priority function P #J# is associated with each job such that if job J has a higher priority than J then P #J# #P#J . Under EDF scheduling, shorter the absolute deadline higher the priority. The system has a set of shared resources. Access to ....

....First scheduler. The problem of scheduling tasks in the presence of resource sharing is NP hard [8] Resource access protocols have been designed to bound the blocking times and sufficient schedulability tests have been given in the presence of maximum blocking times. The Stack Resource Protocol [2] has been designed to handle tasks scheduled under EDF policy. Our work is based on the use of Stack Resource protocol to manage the access to the resources. Let B i be the maximum blocking time for task # i based on the SRP. 3.1 EDF Scheduling Let , f# 1 ; ###;# n g be the tasks in the system ....

[Article contains additional citation context not shown here]

T. P. Baker. Stack-based scheduling of realtime processes. In RealTime Systems Journal, pages 67--99, 1991.

....of maximum blocking times. Resource access protocols such as priority inheritance protocol, priority ceiling protocol and priority limit protocol [21] deal with the case of fixed priority scheduling. Dynamic Priority Ceilings [4] Stack Resource Protocol and Minimal Stack Resource Protocol [3] have been designed to handle tasks with dynamic priorities which encompasses EDF scheduling. Any resource management protocol can be used to manage the access to the resource. Let B i be the maximum blocking time for task t i under the given resource access protocol. 4 3.1 EDF Scheduling Let G ....

T. P. Baker. Stack-based scheduling of realtime processes. In RealTime Systems Journal, pages 67--99, 1991.

....a particular resource. Blocking of tasks can cause priority inversion [19] and result in deadline misses. Resource access protocols such as priority inheritance protocol [19] priority ceiling protocol [19] priority limit protocol [19] stack resource protocol and minimal stack resource protocol [3] have been studied to minimize the blocking time of tasks. Any resource management protocol can be used to manage the access to the resource. Let B i be the maximum blocking time for task i under the given resource management protocol. Lehoczky et al. 10] showed that the schedulability analysis ....

T. P. Baker. Stack-based scheduling of realtime processes. In RealTime Systems Journal, pages 67--99, 1991.

....consumption in a system consisting of periodic tasks with blocking sections. In the static scheme, the processor voltage is changed only when a new task arrives or when an existing task terminates. The Stack Resource Policy (SRP) was proposed by Baker to schedule tasks with shared resources [13]. The core idea is that a job is allowed to preempt a lower priority job only if all the resources it needs are available. The feasibility condition of the SRP was also derived and is listed in Theorem 1: Theorem 1 [13] Suppose n periodic tasks are sorted by their periods. They are schedulable by ....

....Policy (SRP) was proposed by Baker to schedule tasks with shared resources [13] The core idea is that a job is allowed to preempt a lower priority job only if all the resources it needs are available. The feasibility condition of the SRP was also derived and is listed in Theorem 1: Theorem 1 [13] Suppose n periodic tasks are sorted by their periods. They are schedulable by the earliest deadline first (EDF) algorithm with the SRP if D i D k # 1, where B i is the maximum length that a job in T i can be blocked. Note that if there are multiple blocking sections in the same ....

[Article contains additional citation context not shown here]

T. P. Baker. "Stack-based scheduling of real-time processes". In Advances in Real-Time Systems. IEEE Computer Society Press, 1993.

....the lock holder does not make progress due to its low priority. This is such a serious issue that many algorithms have been developed to limit the effects of priority inversion, including the priority inheritance protocol, the priority ceiling protocol, and the immediate priority ceiling protocol [3, 28, 29]. Furthermore, providing real time execution guarantees becomes more difficult. The simple, classical real time analysis techniques [21] assume independently executing tasks, which is clearly violated when locks are used. More complex analysis [29] may be used to provide real time guarantees by ....

T. P. Baker. Stack-based scheduling of realtime processes. RTSYSTS: Real-Time Systems, 3, 1991.

No context found.

T. P. Baker. Stack-based scheduling of real-time processes. Real-Time Systems Journal, 3(1):67--99, March 1991.

No context found.

Baker, T.P., "Stack-Based Scheduling of Realtime Processes", Real-Time Systems Journal, Vol. 3, No. 1, pp. 67-99, Mar 1991

No context found.

T. P. Baker. Stack-based scheduling of real-time processes. Advances in Real-Time Systems, pages 64--96, 1993.

No context found.

T. P. Baker. Stack-based scheduling of real-time processes. Journal of Real-Time Systems, 3(1):67--99, March 1991.

No context found.

Baker, T. P. Stack-based scheduling of realtime processes. Journal of RealTime Systems 3, 1 (Mar. 1991), 67-99.

No context found.

T. P. Baker, "Stack-based scheduling of realtime processes, " The Journal of Real-Time Systems, vol. 3, pp. 67--100, 1991.

No context found.

T. P. Baker. Stack-based scheduling of realtime processes. Journal of Real-Time Systems, 3(1):67-- 99, 1991.

No context found.

Ted Baker. Stack-Based Scheduling of Real-Time Processes. Real-Time Systems, 3(1), March 1991.

No context found.

T.P. Baker. "Stack-Based Scheduling of Realtime Processes." The Journal of Real-Time Systems. 3, 1991, pages 67--99.

No context found.

T. P. Baker, "Stack-based scheduling of real-time processes," Journal of Real-Time Systems, Vol. 3, No. 1, pp. 67-99, March 1991.

No context found.

Baker, T. P., "Stack-based scheduling of realtime processes," The Journal of Real-Time Systems, Vol. 3, pp. 67--100, 1991.

No context found.

T. P. Baker. Stack-based scheduling of realtime processes. Journal of Real-Time Systems, pages 67--99, 1991.

No context found.

T.P.Baker, \Stack-based scheduling of real-time processes", The Real-Time Systems Journal 3,1 (March1991.

No context found.

Baker, T.P., "Stack-Based Scheduling of Real-Time Processes," The Journal of Real-Time Systems 3(1), 1991, pp. 67--100.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC