A framework for multi-core schedulability analysis accounting for resource stress and sensitivity

Abstract

Timing verification of multi-core systems is complicated by contention for shared hardware resources between co-running tasks on different cores. This paper introduces the Multi-core Resource Stress and Sensitivity (MRSS) task model that characterizes how much stress each task places on resources and how much it is sensitive to such resource stress. This model facilitates a separation of concerns, thus retaining the advantages of the traditional two-step approach to timing verification (i.e. timing analysis followed by schedulability analysis). Response time analysis is derived for the MRSS task model, providing efficient context-dependent and context independent schedulability tests for both fixed priority preemptive and fixed priority non-preemptive scheduling. Dominance relations are derived between the tests, along with complexity results, and proofs of optimal priority assignment policies. The MRSS task model is underpinned by a proof-of-concept industrial case study. The problem of task allocation is considered in the context of the MRSS task model, with Simulated Annealing shown to provide an effective solution.

Mixed Criticality on Multi-cores Accounting for Resource Stress and Resource Sensitivity

“…Further aspects of the model are based on the concept of resource sensitive contenders and resource stressing contenders [30,31].…”

“…Finally, MCS is the mixed criticality scheme employed, which is either NMC, SMC, AMC, or AMCR, as described in Section 4. This naming convention builds on that introduced in [30,31] for schedulability tests compatible with the MRSS task model.…”

“…Work on micro-benchmarks [36,44,56,60,61] has sort to characterize the maximum amount of interference that a task can be subject to, assuming a given multi-core hardware configuration. Further research on the Multi-core Resource Stress and Sensitivity (MRSS) task model [30,31] takes this idea a step further, aiming to bound the total amount of interference that can occur from two different perspectives by employing additional task parameters:…”

“…The resource sensitivity and resource stress parameters of a task characterize, in a simple but useful way, the impact on that task's execution time of contention over the resource and the behavior of the arbitration policy in controlling access to it. See [30,31] for a discussion of how the resource sensitivity and resource stress parameters can be obtained. By combining measures of resource stress and resource sensitivity, analysis of the MRSS task model can more accurately bound the amount of interference that can actually occur.…”

“…By combining measures of resource stress and resource sensitivity, analysis of the MRSS task model can more accurately bound the amount of interference that can actually occur. The MRSS task model retains the advantages of the two-step approach that is traditionally employed on single-core systems, providing a separation of concerns between timing analysis and schedulability analysis, and has been validated via a proof-of-concept case study on multi-core hardware [30,31].…”