A Fault Injection Framework for Real-time Multicore Embedded Systems
Resumo
In this paper, we present a non-intrusive framework to inject faults in real-time multicore embedded systems without impairing the temporal characteristics of the critical tasks being executed, thus enabling a fine-grain simulation of the behavior of such systems under faulty conditions. The proposed technique consists of injecting specific traces to designated OS variables, hardware counters, and sensor values. The traces to be injected can either be defined at compile-time or generated at runtime. The fault injection framework builds upon a previously developed non-intrusive, real-time monitoring system. The fault injection mechanism actuates whenever a monitored variable is sampled by the monitoring system. The fault injection process is agnostic to hardware platform. The performance of the framework was assessed in terms of execution time overhead and of the impact on the execution of critical tasks. The results show a maximum execution time overhead on the system of 0.1001% and an average task activation jitter not higher than 5.0096µs. These results corroborate the suitability of the proposed framework to simulate the behavior of critical systems in the face of failures. After presenting the proposed architecture, the conducted experiments, and the achieved results, we discuss the application of the proposed technique in the scope of Digital Twins.
Referências
L. P. Horstmann J. L. C. Hoffmann and A. A. Frohlich "A Framework to Design and Implement Real-time Multicore Schedulers using Machine Learning" 24th IEEE Conference on Emerging Technologies and Factory Automation (ETFA) Sep. 2019.
J. Arlat M. Aguera L. Amat Y. Crouzet J.-C. Fabre J.-C. Laprie et al. "Fault injection for dependability validation: a methodology and some applications" IEEE Transactions on Software Engineering vol. 16 no. 2 pp. 166-182 1990.
G. Kanawati N. Kanawati and J. Abraham "FERRARI: a tool for the validation of system dependability properties" [1992] Digest of Papers. FTCS-22: The Twenty-Second International Symposium on Fault-Tolerant Computing. IEEE 1992 [online] Available: https://doi.org/10.1109/ftcs.1992.243567.
W.-I. Kao R. Iyer and D. Tang "FINE: A fault injection and monitoring environment for tracing the UNIX system behavior under faults" IEEE Transactions on Software Engineering vol. 19 no. 11 pp. 1105-1118 1993.
J. Carreira H. Madeira and J. Silva "Xception: a technique for the experimental evaluation of dependability in modern computers" IEEE Transactions on Software Engineering vol. 24 no. 2 pp. 125-136 1998.
C. Yang C. Yang T. Peng X. Yang and W. Gui "A fault-injection strategy for traction drive control systems" IEEE Transactions on Industrial Electronics vol. 64 no. 7 pp. 5719-5727 Jul. 2017.
"ARM ARM Cortex-A53 MPCore Processor" ARM 2016 [online] Available: .
"UFSC/LISHA" EPOS: Embedded Parallel Operating System. 2019 [online] Available: https://epos.lisha.ufsc.br/.
"Raspberry pi 3 model b" Raspberry PI Foundation. 2019 [online] Available: https://www.raspberrypi.org/products/raspberry-pi-3-model=b/.
S. K. Venkata I. Ahn D. Jeon A. Gupta C. Louie S. Garcia et al. "SD- VBS: The San Diego vision benchmark suite" 2009 IEEE International Symposium on Workload Characterization (IISWC) pp. 55-64 october 2009.
X. Wu and V. Taylor "Utilizing Hardware Performance Counters to Model and Optimize the Energy and Performance of Large Scale Scientific Applications on Power-Aware Supercomputers" 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) pp. 1180-1189 2016.
J. K. Rai A. Negi R. Wankar and K. Nayak "Performance prediction on multi-core processors" 2010 International Conference on Computational Intelligence and Communication Networks. IEEE Nov. 2010.
K. Ott and R. Mahapatra "Hardware performance counters for embedded software anomaly detection" 2018 IEEE 16th Intl Conf on Dependable Autonomic and Secure Computing 16th Intl Conf on Pervasive Intelligence and Computing 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech) Aug.2018.
"Heechul Yun" Miscmicro-benchmarks & tools. 2019.
