2026-08-20T19:38:26Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:20307 2024-07-04T05:10:00Z ddc:004 open_access

Tighter Worst-Case Response Time Bounds for Jitter-Based Self-Suspension Analysis Günzel, Mario von der Brüggen, Georg Chen, Jian-Jia Worst-Case Response Time WCRT Jitter Self-Suspension Analysis Tasks are called self-suspending if they can yield their ready state (specifically, releasing the processor while having highest priority) despite being incomplete, for instance, to offload computation to an external device or when waiting on access rights for shared resources or data. This self-suspending behavior requires special treatment when applying analytical results to compute worst-case response time bounds. One typical treatment is modeling self-suspension as release jitter in a so-called jitter-based analysis. The state of the art, when considering task-level fixed-priority scheduling, individually quantifies the jitter term of each higher-priority task by its worst-case response time minus its worst-case execution time. This work tightens the jitter term by taking the execution behavior of the other higher-priority tasks into account. Our improved jitter-based analysis analytically dominates the previous jitter-based analysis. Moreover, an evaluation for synthetically generated sporadic tasks demonstrates that this jitter term results in tighter worst-case response time bounds for self-suspending tasks. We observe an improvement for up to 55.89 % of the tasksets compared to the previous jitter-based analysis. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Mario Günzel and Georg von der Brüggen and Jian-Jia Chen 2024 Is Part Of LIPIcs, Volume 298, 36th Euromicro Conference on Real-Time Systems (ECRTS 2024) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ECRTS.2024.4 urn:nbn:de:0030-drops-203074 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2024.4 eng https://creativecommons.org/licenses/by/4.0/legalcode