Flexible spin-lock model for resource sharing in multiprocessor real-time systems

Multiprocessor Real-Time Locking Protocols: A Systematic Review

“…Afshar et al [5] observed that this flexibility allows for a generalized view on both spin locks and suspension-based protocols. In particular, Afshar et al noted that jobs that spin at maximum priority are effectively non-preemptive, whereas jobs that spin at minimum priority are-from an analytical point of view-essentially suspended, in the sense that they neither prevent other jobs from executing nor issue further lock requests.…”

“…Afshar et al combined this observation with (unconditional) priority boosting and FIFO-ordered spin locks into a flexible spin-lock model (FSLM) [1,5] that can be tuned [11] to resemble either the MSRP [90],…”

“…Figure 15: Example P-FP schedule of five tasks on two processors illustrating preemptable spinning without request cancelation and priority boosting [5].…”

“…Based Definition 2, the suspension-oblivious schedulability analysis approach can be summarized as follows. 5 • Suppose we are given a self-suspending task set τ = {τ 1 , . .…”

“…Brandenburg [35] discusses how to factor non-preemptive spin-lock overheads into blocking and schedulability analyses. Balasubramanian et al [24] provide an overhead-aware blocking and schedulability analysis for Afshar et al's FSLM [5]. Balasubramanian et al's analysis [24] is based on executiontime inflation, similar to the original analysis of the MSRP [90], and hence is subject to structural pessimism [209].…”