Mixed-Criticality Scheduling on Multiprocessors with Service Guarantees

Ramanathan, Saravanan; Easwaran, Arvind

doi:10.1109/isorc.2018.00011

Cited by 10 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also as future work, we plan to revisit some mixedcriticality scheduling algorithms such as the ones in [13], [14], [15], [16] that have previously been proposed for addressing the non-survivability of traditional mixed-criticality scheduling algorithms. We will seek to characterize the robustness and resilience properties of these algorithms on the basis of the metrics that we have proposed in this paper.…”

Section: Discussionmentioning

confidence: 99%

“…Much of the criticism that has been directed at mixed-criticality scheduling theory that is based on the Vestal model can be traced to these poor survivability properties of the proposed algorithms. Some efforts have recently been made at designing mixed-criticality scheduling algorithms that exhibit some forms of survivability (see, for example [13], [14], [15], [16]); however, these are all ad hoc approaches towards incorporating some properties that are desirable from the perspective of survivability and do not attempt to formally define and quantify survivability -to our knowledge, Burns et al [17] represents a first effort at doing so. The focus in [17] is on defining task models that allow for the representation of robustness properties (in particular, HI-criticality tasks are defined as being robust to the dropping of individual jobs in the sense that the functionality of the task is not compromised upon such dropping, and algorithms are derived in [17] for scheduling systems comprising such tasks that judiciously select jobs to be dropped in order to not need to discard any LO-criticality tasks).…”

Section: Verification Versus Survivabilitymentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Robustness and Resilience into Mixed-Criticality Scheduling Theory

Baruah

Burns

2019

2019 IEEE 22nd International Symposium on Real-Time Distributed Computing (ISORC)

View full text Add to dashboard Cite

Mixed-criticality scheduling theory (MCSh) was developed to allow for more resource-efficient implementation of systems comprising different components that need to have their correctness validated at different levels of assurance. As originally defined, MCSh deals exclusively with pre-runtime verification of such systems; hence many mixed-criticality scheduling algorithms that have been developed tend to exhibit rather poor survivability characteristics during run-time. (E.g., MCSh allows for less-important ("LO-criticality") workloads to be completely discarded in the event that run-time behavior is not compliant with the assumptions under which the correctness of the LOcriticality workload should be verified.) Here we seek to extend MCSh to incorporate survivability considerations, by proposing quantitative metrics for the robustness and resilience of mixedcriticality scheduling algorithms. Such metrics allow us to make quantitative assertions regarding the survivability characteristics of mixed-criticality scheduling algorithms, and to compare different algorithms from the perspective of their survivability. We propose that MCSh seek to develop scheduling algorithms that possess superior survivability characteristics, thereby obtaining algorithms with better survivability properties than current ones (which, since they have been developed within a survivabilityagnostic framework, tend to focus exclusively on pre-runtime verification and ignore survivability issues entirely).

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Verification Versus Survivabilitymentioning

confidence: 99%

Incorporating Robustness and Resilience into Mixed-Criticality Scheduling Theory

Baruah

Burns

2019

2019 IEEE 22nd International Symposium on Real-Time Distributed Computing (ISORC)

View full text Add to dashboard Cite

show abstract

“…Although authors in [7] have proposed an approach to enhance the QoS by determining a constant drop rate parameter for LC tasks and guaranteeing their schedulability in the H I mode based on the defined parameter, their presented scheme has been analyzed in the worst-case scenario of tasks' execution, while there may exist significant amount of idle time in the processor at run-time, which could be used for improving the QoS of LC tasks. Some articles in the field of MC systems such as [14][15][16] have presented the scheduling algorithms for multi-core processors, which can also improve the LC tasks' QoS (row 2). However, these methods have been presented to guarantee the tasks' deadlines in the worst-case scenario at design-time.…”

Section: Related Workmentioning

confidence: 99%

“…In lines 7-11, the number of dropped LC tasks are counted to be used in the learning process. If the system switches back to the LO mode, a parameter (CountDrop) for each task, which counts the number of released LC tasks in the H I mode, is set to zero (lines [13][14]. Besides, there is a function (line 17) that checks whether the output of each task is ready.…”

Section: Liquid Approachmentioning

confidence: 99%

Learning-Oriented QoS- and Drop-Aware Task Scheduling for Mixed-Criticality Systems

et al. 2022

View full text Add to dashboard Cite

In Mixed-Criticality (MC) systems, multiple functions with different levels of criticality are integrated into a common platform in order to meet the intended space, cost, and timing requirements in all criticality levels. To guarantee the correct, and on-time execution of higher criticality tasks in emergency modes, various design-time scheduling policies have been recently presented. These techniques are mostly pessimistic, as the occurrence of worst-case scenario at run-time is a rare event. Nevertheless, they lead to an under-utilized system due to frequent drops of Low-Criticality (LC) tasks, and creation of unused slack times due to the quick execution of high-criticality tasks. Accordingly, this paper proposes a novel optimistic scheme, that introduces a learning-based drop-aware task scheduling mechanism, which carefully monitors the alterations in the behaviour of the MC system at run-time, to exploit the generated dynamic slacks for reducing the LC tasks penalty and preventing frequent drops of LC tasks in the future. Based on an extensive set of experiments, our observations have shown that the proposed approach exploits accumulated dynamic slack generated at run-time, by 9.84% more on average compared to existing works, and is able to reduce the deadline miss rate by up to 51.78%, and 33.27% on average, compared to state-of-the-art works.

show abstract

“…However, if this core also switches mode then these tasks will be suspended. This model has been previously published in [96].…”

Section: Schedulingmentioning

confidence: 99%

Multi-core mixed-criticality real-time scheduling

Ramanathan¹

Self Cite

View full text Add to dashboard Cite

The contributions of the co-authors are as follows:. I co-designed the problem with A/Prof Arvind Easwaran.. A/Prof Hyeonjoong Cho provided the initial project direction and helped in formulating the model.. I wrote the drafts of the manuscript. The manuscript was revised by A/Prof Arvind Easwaran.. All simulation experiments, including synthetic task set generation, was conducted by me in the Hardware and Embedded Systems Laboratory. I also analyzed the data.. A/Prof Arvind Easwaran assisted in designing experiments and provide guidance in the interpretation of simulation data.

show abstract

Mixed-Criticality Scheduling on Multiprocessors with Service Guarantees

Cited by 10 publications

References 16 publications

Incorporating Robustness and Resilience into Mixed-Criticality Scheduling Theory

Incorporating Robustness and Resilience into Mixed-Criticality Scheduling Theory

Learning-Oriented QoS- and Drop-Aware Task Scheduling for Mixed-Criticality Systems

Multi-core mixed-criticality real-time scheduling

Contact Info

Product

Resources

About