A Unifying Response Time Analysis Framework for Dynamic Self-Suspending Tasks

Abstract

For real-time embedded systems, self-suspending behaviors can cause substantial performance/schedulability degradations. In this paper, we focus on preemptive fixed-priority scheduling for the dynamic self-suspension task model on uniprocessor. This model assumes that a job of a task can dynamically suspend itself during its execution (for instance, to wait for shared resources or access co-processors or external devices). The total suspension time of a job is upper-bounded, but this dynamic behavior drastically influences the interference generated by this task on lower-priority tasks. The state-of-the-art results for this task model can be classified into three categories (i) modeling suspension as computation, (ii) modeling suspension as release jitter, and (iii) modeling suspension as a blocking term. However, several results associated to the release jitter approach have been recently proven to be erroneous, and the concept of modeling suspension as blocking was never formally proven correct. This paper presents a unifying response time analysis framework for the dynamic self-suspending task model. We provide a rigorous proof and show that the existing analyses pertaining to the three categories mentioned above are analytically dominated by our proposed solution. Therefore, all those techniques are in fact correct, but they are inferior to the proposed response time analysis in this paper. The evaluation results show that our analysis framework can generate huge improvements (an increase of up to 50% of the number of task sets deemed schedulable) over these state-of-the-art analyses.A Unifying Response Time Analysis Framework for Dynamic Self-Suspending TasksJian-Jia Chen * , Geoffrey Nelissen § , Wen-Hung Huang * * TU Dortmund University, Germany § CISTER/INESC-TEC, ISEP, Polytechnic Institute of Porto, Portugal Emails: {jian-jia.chen, wen-hung.huang}@tu-dortmund.de, grrpn@isep.ipp.pt Abstract-For real-time embedded systems, self-suspending behaviors can cause substantial performance/schedulability degradations. In this paper, we focus on preemptive fixed-priority scheduling for the dynamic self-suspension task model on uniprocessor. This model assumes that a job of a task can dynamically suspend itself during its execution (for instance, to wait for shared resources or access co-processors or external devices). The total suspension time of a job is upper-bounded, but this dynamic behavior drastically influences the interference generated by this task on lower-priority tasks. The state-of-the-art results for this task model can be classified into three categories (i) modeling suspension as computation, (ii) modeling suspension as release jitter, and (iii) modeling suspension as a blocking term. However, several results associated to the release jitter approach have been recently proven to be erroneous, and the concept of modeling suspension as blocking was never formally proven correct. This paper presents a unifying response time analysis framework for the dynamic self-suspending task model. We pr...

Many suspensions, many problems: a review of self-suspending tasks in real-time systems

“…-If x i is 1 for task τ i , then the release jitter of task τ i is 6 ≤ t 32 Table 4: A dynamic self-suspending task set used in Example 6, originally presented in [CNH16]. Detailed procedure for deriving the upper bound of R 3 , with R 1 − C 1 = 5 and R 2 − C 2 = 9.…”

“…(3) is based on a careful revision of the critical instant theorem to include the self-suspension time into the window of interest. The dominance over the other existing (correct) schedulability tests and response time analyses was also demonstrated in [CNH16]. To obtain the tightest (but not necessarily exact) worst-case response time of task τ k in their framework, we should consider all the 2 k−1 possible combinations of x, implying exponential time complexity.…”

“…However, there is no formal proof in [Dev03]. The proof made by Chen et al in [CHN16,CNH16] for fixed-priority scheduling cannot be directly extended to EDF scheduling. The correctness of Theorem 8 in [Dev03, Section 4.5] should be supported with a rigorous proof, since selfsuspension behavior has induced several non-trivial phenomena.…”

The SRP Resource Sharing Protocol for Self-Suspending Tasks

“…No information is assumed about the actual task structure, therefore suspensions can occur at any time during the execution of a job. In the related literature, the model described above is known as the dynamic self-suspending task model [12]. The only restriction we pose on the tasks' dynamic selfsuspension behavior is that tasks cannot self-suspend within critical sections 2 .…”

“…Suspension oblivious analysis. This approach [12] models suspension time as execution time. Each task τ i is replaced by an artificial task τ ′ i with WCET C ′ i = C i + S i and suspension time S ′ i = 0.…”