Independence Thresholds: Balancing Tractability and Practicality in Soft Real-Time Stochastic Analysis

The issue of stochastic response-time analysis is considered in the context of soft real-time multiprocessor schedulers. For such analysis to yield tractable, closed-form results, it is inevitably necessary to assume that execution times are probabilistically independent. However, stochastic dependencies among tasks are often common in actual systems. To enable closed-form analysis results to be applied to such systems, the concept of an independence threshold is introduced. Such a threshold is a "tunable" per-task parameter that can be adjusted to control the extent of dependency in task execution times as assumed in analysis, such thresholds can even be applied in settings where explicit dependencies exist among tasks through resource sharing. A method is presented for setting independence thresholds in which measured task execution times are subjected to known statistical independence tests. This method is applied in a case study involving MPEG decoding. In this case study, the usage of independence thresholds enabled up to a 3.5-fold reduction in provisioned task execution times compared to a worst-case provisioning without compromising analysis assumptions.

[1]  D. Brillinger,et al.  Handbook of methods of applied statistics , 1967 .

[2]  R. Bartels.  The Rank Version of von Neumann's Ratio Test for Randomness , 1982 .

[3]  Liliana Cucu-Grosjean,et al.  Measurement-Based Probabilistic Timing Analysis for Multi-path Programs , 2012, 2012 24th Euromicro Conference on Real-Time Systems.

[4]  James H. Anderson,et al.  Optimality Results for Multiprocessor Real-Time Locking , 2010, 2010 31st IEEE Real-Time Systems Symposium.

[5]  James H. Anderson,et al.  A Stochastic Framework for Multiprocessor Soft Real-Time Scheduling , 2010, 2010 16th IEEE Real-Time and Embedded Technology and Applications Symposium.

[6]  J. Shaffer.  Multiple Hypothesis Testing , 1995 .

[7]  J. V. Bradley.  Distribution-Free Statistical Tests , 1968 .

[8]  Alan Burns,et al.  Probabilistic timing analysis: An approach using copulas , 2005, J. Embed. Comput..

[9]  Francisco J. Cazorla,et al.  Kernel Partitioning of Streaming Applications: A Statistical Approach to an NP-complete Problem , 2012, 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture.

[10]  Alan Burns,et al.  Statistical analysis of WCET for scheduling , 2001, Proceedings 22nd IEEE Real-Time Systems Symposium (RTSS 2001) (Cat. No.01PR1420).

[11]  Liliana Cucu-Grosjean,et al.  Response Time Analysis for Fixed-Priority Tasks with Multiple Probabilistic Parameters , 2013, 2013 IEEE 34th Real-Time Systems Symposium.

[12]  James H. Anderson,et al.  Scheduling and locking in multiprocessor real-time operating systems , 2011 .

[13]  James H. Anderson,et al.  Fair lateness scheduling: reducing maximum lateness in G-EDF-like scheduling , 2013, Real-Time Systems.

[14]  Hennadiy Leontyev,et al.  Generalized tardiness bounds for global multiprocessor scheduling , 2007, Real Time Syst..

[15]  Alan Burns,et al.  A Probabilistic Framework for Schedulability Analysis , 2003, EMSOFT.

[16]  James H. Anderson,et al.  Soft Real-Time on Multiprocessors: Are Analysis-Based Schedulers Really Worth It? , 2011, 2011 IEEE 32nd Real-Time Systems Symposium.

[17]  Luigi Palopoli,et al.  An Analytical Bound for Probabilistic Deadlines , 2012, 2012 24th Euromicro Conference on Real-Time Systems.

[18]  Gabriel A. Moreno,et al.  Statistical-Based WCET Estimation and Validation , 2009, WCET.

[19]  James H. Anderson,et al.  A Multiprocessor Server-Based Scheduler for Soft Real-Time Tasks with Stochastic Execution Demand , 2011, 2011 IEEE 17th International Conference on Embedded and Real-Time Computing Systems and Applications.

[20]  James H. Anderson,et al.  Tardiness bounds under global EDF scheduling on a multiprocessor , 2005, 26th IEEE International Real-Time Systems Symposium (RTSS'05).