Performance analysis of checkpoint based efficient failure-aware scheduling algorithm

Microprocessors and Microsystems

2021

More than 21 000 objects fly in outer space and are exposed to the harsh space environment. The size of space objects considerably varies. Our research focuses on small satellites, such as CubeSats, which have to respect time, spatial and energy constraints. To tackle this issue, this paper presents and evaluates two fault tolerant online scheduling algorithms: the algorithm scheduling all tasks as aperiodic (called OneOff) and the algorithm placing arriving tasks as aperiodic or periodic tasks (called OneOff&Cyclic). Based on several scenarios, the results show that the performance of ordering policies are influenced by the system load and the proportions of simple and double tasks to all tasks to be executed. The "Earliest Deadline" and "Earliest Arrival Time" ordering policies for OneOff or the "Minimum Slack" ordering policy for OneOff&Cyclic reject the least tasks in all tested scenarios. The paper also deals with the analysis of scheduling time to evaluate real-time performance of ordering policies and shows that OneOff requires less time to find a new schedule than OneOff&Cyclic. Finally, it was found that the studied algorithms perform well also in a harsh environment and provide the same reliability level as systems based on triple modular redundancy with very much less system power consumption.Regarding this trade-off between physical aspects (weight, size and energy) and fault tolerance, CubeSats are in the centre of our interest. Taking into account all constraints, such as time, reliability or energy, the mapping and scheduling of tasks or applications to be executed on such devices represent a challenging problem.Last but not least, technology has been progressively under development and, as the author of [20] suggests, it might be better to make use of one state-ofthe-art integrated commercial off-the-shelf (COTS) chip, especially for missions with limited budget. In fact, it can take advantage of redundancy thanks to its several processors and function better than one outdated single processor chip even if it was designed for space missions. CubeSatsThe idea of CubeSats dates back to 1999 and its aim was to provide affordable access to space by defining standard dimensions to reduce costs and time [22]. At present, CubeSats become more and more popular, their number of launches increases and they are built not only at universities but also by companies and space agencies [12].CubeSats are small satellites consisting of several units (e.g. 1U, 2U, 3U or 6U) where each unit (1U) is a 10 cm cube, which can weigh up to 1.3 kg [22]. CubeSats are composed of several systems, such as on-board computer, electrical power system, attitude determination and control system, communication system, and payload. Their missions are aimed at scientific investigations, like studying urban heat islands [1] or polar auroras and airglow [7].CubeSats operate in the harsh space environment, where they are exposed to charged particles and radiations. These phenomena cause both transient effects, such as single event upset...

show abstract

Section: Fault Tolerance In Cubesatsmentioning

confidence: 99%

Improving the CubeSat reliability thanks to a multiprocessor system using fault tolerant online scheduling

Microprocessors and Microsystems

2021

show abstract

“…Although in other fields, software fault tolerant solutions are commonly used to improve the system reliability, such as checkpointing [16], task replication [17], task rescheduling [18] or task swapping [19], they are relatively rare on board of CubeSats. In our research, we were inspired by task replication, in particular by the primary-backup approach [20], [21] considering primary and backup copies to deal with faults.…”

Section: Fault Tolerance In Cubesatsmentioning

confidence: 99%

Fault-Tolerant Online Scheduling Algorithms for CubeSats

Proceedings of the 11th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures / 9th W

2020

CubeSats are small satellites operating in harsh space environment. In order to ensure correct functionality on board despite faults, fault tolerant techniques taking into account spatial, time and energy constraints should be considered. This paper presents a software-level solution taking advantage of several processors available on board. Two online scheduling algorithms are introduced and evaluated. The results show their performances and the trade-off between the rejection rate and energy consumption. Last but not least, it is stated that ordering policies achieving low rejection rate when using the algorithm scheduling all tasks as aperiodic are the "Earliest Deadline" and "Earliest Arrival Time". As for the algorithm treating arriving tasks as aperiodic or periodic tasks, the "Minimum Slack" ordering policy provides reasonable results.

show abstract

Special Session: Operating Systems under test: an overview of the significance of the operating system in the resiliency of the computing continuum

2021 IEEE 39th VLSI Test Symposium (VTS)

et al. 2021