arXiv subjects

Jian-Jia Chen

Publications and source records attributed to Jian-Jia Chen.

60 records · Page 4Linked to original sources

arXiv2016

A Note on the Exact Schedulability Analysis for Segmented Self-Suspending Systems

This report considers a sporadic real-time task system with $n$ sporadic tasks on a uniprocessor platform, in which the lowest-priority task is a segmented self-suspension task and the other higher-priority tasks are ordinary sporadic real-time tasks. This report proves that the schedulability analysis for fixed-priority preemptive scheduling even with only one segmented self-suspending task as the lowest-priority task is $co{\cal NP}$-hard in the strong sense. Under fixed-priority preemptive scheduling, Nelissen et al. in ECRTS 2015 provided a mixed-integer linear programming (MILP) formulation to calculate an upper bound on the worst-case response time of the lowest-priority self-suspending task. This report provides a comprehensive support to explain several hidden properties that were not provided in their paper. We also provide an input task set to explain why the resulting solution of their MILP formulation can be quite far from the exact worst-case response time.

cs.DS↗

arXiv2016

Automatic Parameter Derivations in k2U Framework

We have recently developed a general schedulability test framework, called k2U, which can be applied to deal with a large variety of task models that have been widely studied in real-time embedded systems. The k2U framework provides several means for the users to convert arbitrary schedulability tests (regardless of platforms and task models) into polynomial-time tests with closed mathematical expressions. However, the applicability (as well as the performance) of the k2U framework relies on the users to index the tasks properly and define certain constant parameters. This report describes how to automatically index the tasks properly and derive those parameters. We will cover several typical schedulability tests in real-time systems to explain how to systematically and automatically derive those parameters required by the k2U framework. This automation significantly empowers the k2U framework to handle a wide range of classes of real-time execution platforms and task models, including uniprocessor scheduling, multiprocessor scheduling, self-suspending task systems, real-time tasks with arrival jitter, services and virtualizations with bounded delays, etc.

cs.DS↗

arXiv2016

A Note on Modeling Self-Suspending Time as Blocking Time in Real-Time Systems

This report presents a proof to support the correctness of the schedulability test for self-suspending real-time task systems proposed by Jane W. S. Liu in her book titled "Real-Time Systems" (Pages 164-165). The same concept was also implicitly used by Rajkumar, Sha, and Lehoczky in RTSS 1988 (Page 267) for analyzing self-suspending behaviour due to synchronization protocols in multiprocessor systems.

cs.DS↗

arXiv2015

k2U: A General Framework from k-Point Effective Schedulability Analysis to Utilization-Based Tests

To deal with a large variety of workloads in different application domains in real-time embedded systems, a number of expressive task models have been developed. For each individual task model, researchers tend to develop different types of techniques for deriving schedulability tests with different computation complexity and performance. In this paper, we present a general schedulability analysis framework, namely the k2U framework, that can be potentially applied to analyze a large set of real-time task models under any fixed-priority scheduling algorithm, on both uniprocessor and multiprocessor scheduling. The key to k2U is a k-point effective schedulability test, which can be viewed as a "blackbox" interface. For any task model, if a corresponding k-point effective schedulability test can be constructed, then a sufficient utilization-based test can be automatically derived. We show the generality of k2U by applying it to different task models, which results in new and improved tests compared to the state-of-the-art. Analogously, a similar concept by testing only k points with a different formulation has been studied by us in another framework, called k2Q, which provides quadratic bounds or utilization bounds based on a different formulation of schedulability test. With the quadratic and hyperbolic forms, k2Q and k2U frameworks can be used to provide many quantitive features to be measured, like the total utilization bounds, speed-up factors, etc., not only for uniprocessor scheduling but also for multiprocessor scheduling. These frameworks can be viewed as a "blackbox" interface for schedulability tests and response-time analysis.

cs.OS↗

arXiv2013

Competitive Design and Analysis for Machine-Minimizing Job Scheduling Problem

We explore the machine-minimizing job scheduling problem, which has a rich history in the line of research, under an online setting. We consider systems with arbitrary job arrival times, arbitrary job deadlines, and unit job execution time. For this problem, we present a lower bound 2.09 on the competitive factor of \emph{any} online algorithms, followed by designing a 5.2-competitive online algorithm. We also point out a false claim made in an existing paper of Shi and Ye regarding a further restricted case of the considered problem. To the best of our knowledge, what we present is the first concrete result concerning online machine-minimizing job scheduling with arbitrary job arrival times and deadlines.

cs.DS↗

arXiv2013

Online Power-Managing Strategy with Hard Real-Time Guarantees

We consider the problem of online dynamic power management that provides hard real-time guarantees. In this problem, each of the given jobs is associated with an arrival time, a deadline, and an execution time, and the objective is to decide a schedule of the jobs as well as a sequence of state transitions on the processors so as to minimize the total energy consumption. In this paper, we examine the problem complexity and provide online strategies to achieve energy-efficiency. First, we show that the competitive factor of any online algorithm for this problem is at least 2.06. Then we present an online algorithm which gives a 4-competitive schedule. When the execution times of the jobs are unit, we show that the competitive factor improves to 3.59. At the end, the algorithm is generalized to allow a trade-off between the number of processors we use and the energy-efficiency of the resulting schedule.

cs.DS↗