-
Journal of Systems and Software. 01/2011; 84:2324-2333.
-
[show abstract]
[hide abstract]
ABSTRACT: It is widely assumed that scheduling real-time tasks becomes more difficult as their deadlines get shorter. With deadlines shorter, however, tasks potentially compete less with each other for processors, and this could produce more contention-free slots at which the number of competing tasks is smaller than or equal to the number of available processors. This paper presents a policy (called CF policy) that utilizes such contention-free slots effectively. This policy can be employed by any work-conserving, preemptive scheduling algorithm, and we show that any algorithm extended with this policy dominates the original algorithm in terms of schedulability. We also present improved schedulability tests for algorithms that employ this policy, based on the observation that interference from tasks is reduced when their executions are postponed to contention-free slots. Finally, using the properties of the CF policy, we derive a counter-intuitive claim that shortening of task deadlines can help improve schedulability of task systems. We present heuristics that effectively reduce task deadlines for better scheduability without performing any exhaustive search.
17th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2011, Chicago, Illinois, USA, 11-14 April 2011; 01/2011
-
Proceedings of the 31st IEEE Real-Time Systems Symposium, RTSS 2010, San Diego, California, USA, November 30 - December 3, 2010; 01/2010
-
Proceedings of the 10th International conference on Embedded software, EMSOFT 2010, Scottsdale, Arizona, USA, October 24-29, 2010; 01/2010
-
Real-Time Systems. 01/2009; 43:25-59.
-
[show abstract]
[hide abstract]
ABSTRACT: Compositional schedulability analysis of hierarchical scheduling frameworks is a well studied problem, as it has wide-ranging applications in the embedded systems do- main. Several techniques, such as periodic resource model based abstraction and composition, have been proposed for this problem. However these frameworks are sub-optimal because they incur bandwidth overhead. In this work, we introduce the Explicit Deadline Periodic (EDP) resource model, and present compositional analysis techniques un- der EDF and DM. We show that these techniques are band- width optimal, in that they do not incur any bandwidth over- head in abstraction or composition. Hence, this framework is more efficient when compared to existing approaches.
Real-Time Systems Symposium, 2007. RTSS 2007. 28th IEEE International; 01/2008
-
[show abstract]
[hide abstract]
ABSTRACT: Conditional real-time task models, which are generalizations of periodic, sporadic, and multi-frame tasks, represent real world applications more accurately. These models can be classified based on a tradeoff in two dimensions – expressivity and hardness of schedulability analysis. In this work, we introduce a class of conditional task models and derive efficient schedulability analysis techniques for them. These models are more expressive than existing models for which efficient analysis techniques are known. In this work, we also lay the groundwork for schedulability analysis of hierarchical scheduling frameworks with conditional task models. We propose techniques that abstract timing requirements of conditional task models, and support compositional analysis using these abstractions.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: Existing verification and validation methodologies can detect software violations very effectively but fail to provide any mechanism for correcting faults once they are detected. Detection of faults, their diagnosis and corrective actions are all essential components of any software rectification framework. In this paper, we propose a framework for correction of violations in software systems ensuring that the desired goals of the system are achieved. We describe a stochastic finite state machine used to abstract a software system along with the uncertainty in its operating environment. Safety property violations and satisfaction of functionalities are abstracted using penalties and rewards on the states, respectively. Rectification of software is then formulated as a stochastic optimal control problem over this abstraction. Algorithms polynomial in the size of the abstraction have been developed for solving this optimization problem exactly. The paper also applies the developed framework to a variety of examples from different domains.
Technical Reports (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: It has been widely studied how to schedule real-time tasks on multiprocessor platforms. Several studies find optimal scheduling policies for implicit deadline task systems, but it is hard to understand how each policy utilizes the two important aspects of scheduling real-time tasks on multiprocessors: inter-job concurrency and job urgency. In this paper, we introduce a new scheduling policy that considers these two properties. We prove that the policy is optimal for the special case when the execution time of all tasks are equally one and deadlines are implicit, and observe that the policy is a new concept in that it is not an instance of Pfair or ERfair. It remains open to find a scheduliability condition for general task systems under our scheduling policy.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: Embedded systems are complex as a whole but consist of smaller independent modules minimally interacting with each other. This structure makes embedded systems amenable to compositional system design. Compositional design of real-time embedded systems can be done using hierarchical systems which consist of real-time components arranged in a scheduling hierarchy. Each component consists of a real-time workload and a scheduling policy for the workload. To simplify schedulability analysis of hierarchical systems, analysis can be done compositionally using interfaces that abstract the timing requirements of components. Associative composition will facilitate analysis of systems in which components are modified on the fly. In this paper, we propose efficient algorithms to abstract the resource requirements of components in the form of periodic resource models. Each component interface consists of a set of periodic resource models for different values of period, which allows the selection of a periodic interface that minimizes the collective real-time requirements of hierarchical components. We also describe an interface composition algorithm which accounts for context switch overheads incurred by components and is associative.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: Embedded systems are complex as a whole but consist of smaller independent modules interacting with each other. This structure makes embedded systems amenable to compositional design. Real-time embedded systems consist of real-time workloads having temporal deadlines. Compositional design of real-time embedded systems can be done using systems consisting of real-time components arranged in a scheduling hierarchy. Each component consists of some real-time workload and a scheduling policy for the workload. To simplify schedulability analysis for such systems, analysis can be done compositionally using interfaces that abstract the timing requirements of components. To facilitate analysis of dynam- ically changing real-time systems, the framework must support incremental analysis. In this paper, we summarize our work [19, 6] on schedulability analysis for hierarchical real-time systems. We describe a compositional analysis technique that abstracts resource requirements of components using periodic resource models. To support incremental analysis and resource bandwidth minimization, we describe an extension to this interface model. Each extended interface consists of multiple periodic resource models for different periods. This allows the selection of a periodic model that can schedule the system using minimum bandwidth. We also account for context switch overheads in these interfaces. We then describe an associative composition technique for such interfaces that supports incremental analysis.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: When specifying system requirements, we want a language that can express the requirements in the simplest and most intuitive form. Although the MaC system provides an expressive language, called MEDL, it is generally awkward to express certain features like temporal ordering of complex events, timing constraints, and frequencies of events which are inherent in safety properties. MEDL-RE extends the MEDL language to include regular expressions to easily specify timing dependencies and timing constraints. Due to simultaneous events generated by the MaC system, monitoring regular expressions by simulating DFAs would result in a potential problem. The DFA simulations would involve concurrent multi-path simulations and result in exponential running time. To handle simultaneous events inexpensively, we generate a dependency graph to identify possible simultaneous events. Further, we augment the original DFAs with alternative transitions, which will substitute for multi-path simulations.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: Embedded systems are complex as a whole but consist of smaller independent modules interacting with each other. This structure makes them amenable to compositional design. Real-time embedded systems consist of realtime workloads having deadlines. Compositional design of such systems can be done using real-time components arranged in a scheduling hierarchy. Each component consists of some real-time workload and a scheduling policy for the workload. To simplify schedulability analysis for such systems, analysis should be done compositionally using interfaces that abstract timing requirement of components. To facilitate analysis of dynamically changing systems, the framework should also support incremental analysis. In this paper, we overview our approach to compositional and incremental schedulability analysis of hierarchical real-time systems. We describe a compositional analysis technique that abstracts resource requirement of components using periodic resource models. To support incremental analysis and resource bandwidth minimization, we describe an extension to this interface model. Each extended interface consists of multiple periodic resource models for different periods. This allows the selection of a periodic model that can schedule the system using minimum bandwidth. We also account for context switch overhead of components in these extended interfaces. We then describe an associative composition technique for such interfaces, that supports incremental analysis.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: ARINC specification 653-2 describes the interface between application software and underlying middleware in a distributed real-time avionics system. The real-time workload in this system comprises of partitions, where each partition consists of one or more processes. Processes incur blocking and preemption overheads, and can communicate with other processes in the system. In this work, we develop compositional techniques for automated scheduling of such partitions and processes. At present, system designers manually schedule partitions based on interactions they have with the partition vendors. This approach is not only time consuming, but can also result in under utilization of resources.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: Complex real-time embedded systems can be developed using component based design methodologies. Timing requirements of real-time components in the system can be modeled using hierarchical frameworks to capture resource sharing among components under different schedulers. To support component based design for real-time embedded systems, we must then address schedulability analysis of hierarchical scheduling models. In this paper, we propose a generic interface algebra for compositional schedulability analysis of such models. We also define conditions under which this algebra supports incremental analysis, dynamic adaptability, and independent implementability. Furthermore, we also propose a novel periodic resource model based framework for compositional and incremental schedulability analysis of hierarchical scheduling models. This extends our earlier proposed framework with a technique that allows periodic resource models with different periods to be composed together. We formulate this framework in our proposed algebra to demonstrate ease of use of the algebra and to identify framework properties.
Departmental Papers (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: Cyber-physical systems (CPSs) are becoming all-pervasive, and due to increasing complexity they are designed using component-based approaches. Temporal constraints of such complex CPSs can then be modeled using hierarchical scheduling frameworks. In this paper, we consider one such avionics CPS described by ARINC specification 653-2. The real-time workload in this system comprises of partitions, where each partition consists of one or more processes. Processes incur blocking and preemption overheads, and can communicate with other processes in the system. In this work, we develop techniques for automated scheduling of such partitions. At present, system designers manually schedule partitions based on interactions they have with application vendors. This approach is not only time consuming, but can also result in under utilization of resources. Hence, in this work we propose compositional analysis based scheduling techniques for partitions.
Technical Reports (CIS).
-
[show abstract]
[hide abstract]
ABSTRACT: Compositional schedulability analysis of hierarchical real-time systems is a well-studied problem. Various techniques have been developed to abstract resource requirements of com-ponents in such systems, and schedulability has been ad-dressed using these abstract representations (also called com-ponent interfaces). These approaches for compositional anal-ysis incur resource overheads when they abstract components into interfaces. In this talk, we define notions of resource schedulability and optimality for component interfaces, and compare various approaches. This research was support in part by AFOSR FA9550-07-1-0216 and NSF CNS-0720703.
-
[show abstract]
[hide abstract]
ABSTRACT: Compositional schedulability analysis of hierarchical real-time systems is a well-studied problem. Various techniques have been developed to abstract resource requirements of com-ponents in such systems, and schedulability has been ad-dressed using these abstract representations (also called com-ponent interfaces). These approaches for compositional anal-ysis incur resource overheads when they abstract components into interfaces. In this talk, we define notions of resource schedulability and optimality for component interfaces, and compare various approaches. This research was support in part by AFOSR FA9550-07-1-0216 and NSF CNS-0720703.
-
[show abstract]
[hide abstract]
ABSTRACT: Cyber-physical systems (CPSs) are becoming all-pervasive, and due to increasing complexity they are designed using component-based approaches. Temporal constraints of such complex CPSs are then modeled using hierarchical scheduling frameworks. Therefore, there is a need to develop compositional schedulability analysis techniques for such CPSs. In this essay, we describe one such CPS present in air-crafts. We also discuss the hierarchical frameworks that are found in these systems, and highlight shortcomings of existing techniques in analyzing them.
ACM SIGBED Review 5(1):6.
-
[show abstract]
[hide abstract]
ABSTRACT: Runtime verification involves monitoring the system at runtime to check for conformance of the execution trace to user defined safety properties. Typically, run-time verifiers do not assume a system model and hence cannot predict violations until they occur. This limits the practical applicability of runtime verification. Steering is the process of predicting the occurrence of violations and preventing them by controlling system execution. Steerers can achieve this using a limited knowledge of the system model even in situations where it is infeasible to store the entire model. In this paper, we explore a control-theoretic view of steering for discrete event systems. We introduce an architecture for steering and also describe different steering paradigms.
Electronic Notes in Theoretical Computer Science.
