Regarding the Optimality of Speedup Bounds of Mixed-Criticality - PowerPoint PPT Presentation

Regarding the Optimality of Speedup Bounds of Mixed-Criticality Schedulability Tests Zhishan Guo Department of Computer Science, Missouri S&T Presented at Dagstuhl Seminar 17131 Mar. 29, 2017

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: Mode switch Static Analysis; - All deadlines met under normal mode Pessimistic - HI deadlines met under HI mode c i H c i L t Measurement Based; Optimistic

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: Mode switch Static Analysis; - All deadlines met under normal mode Pessimistic - HI deadlines met under HI mode c i H Q: Why Mixed Criticality? A: The resources over-provisioned c i L to the critical functionalities t Measurement Based; can be used to execute the less- Optimistic critical functionalities instead. • E.g.1: x := a + b takes • E.g.2: - 20 cycles - 3 ~9~ 321 cycles

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: Static Analysis; - All deadlines met under normal mode Pessimistic - HI deadlines met under HI mode c i H Q: Why Mixed Criticality? A: The resources over-provisioned c i L to the critical functionalities t Measurement Based; can be used to execute the less- Optimistic critical functionalities instead. Mode switch – Important & Interesting: 300+ papers in 8 years [1] – Hard [2] NP-Hard in the strong sense [1] A Burns and R Davis. Mixed-criticality systems, a review. 9 th ed, 2017. [2] S Baruah. Mixed criticality scheduling is highly intractable, 2008.

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: - All deadlines met under normal mode Mode switch - HI deadlines met under HI mode – Important, Interesting, & Hard NP-Hard in the strong sense Speedup Bound Strategy Work Uniprocessor, 1.618, Best OCBP [Baruah, Li, Soutgie Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] Multi processor, 1.618 4/3 MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] A schedulability test has speedup factor s , s ≥1, if any task set that is schedulable by any algorithm on platform with processing speed of 1, it will be deemed schedulable by this test upon a processor that is s times as fast .

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: - All deadlines met under normal mode Mode switch - HI deadlines met under HI mode – Important, Interesting, & Hard NP-Hard in the strong sense Speedup Bound Strategy Work “Optimal” Uniprocessor, 1.618, Best OCBP [Baruah, Li, Soutgie Strategy Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] 1 4/3 Multi processor, 1.618 4/3 MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] A schedulability test has speedup factor s , s ≥1, if any task set that is schedulable by any algorithm on platform with processing speed of 1, it will be deemed schedulable by this test upon a processor that is s times as fast .

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: - All deadlines met under normal mode Mode switch - HI deadlines met under HI mode – Important, Interesting, & Hard NP-Hard in the strong sense Speedup Bound Strategy Work “Optimal” Uniprocessor, 1.618, Best OCBP [Baruah, Li, Stougie Strategy Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] 3/4 1 Multi processor, 1.618 4/3 MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] A schedulability test has speedup factor s , s ≥1, if any task set that is schedulable by any algorithm on platform with processing speed of 1, it will be deemed schedulable by this test upon a processor that is s times as fast .

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: - All deadlines met under normal mode - HI deadlines met under HI mode – Important, Interesting, & Hard Speedup Bound Strategy Work Uniprocessor, 1.618, Best OCBP [Baruah, Li, Soutgie Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] Multi processor, 1.618 4/3 Best MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] DOMINATE A schedulability test has speedup factor s , s ≥1, if any task set that is schedulable by any algorithm on platform with processing speed of 1, it will be deemed schedulable by this test upon a processor that is s times as fast .

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: Demand-Based MC - All deadlines met under normal mode [ Easwaran , RTSS’13 ] - HI deadlines met under HI mode [ Ekberg & Yi, RTS 50(1) ] – Important, Interesting, & Hard DOMINATE Speedup Bound Strategy Work Uniprocessor, 1.618, Best OCBP [Baruah, Li, Soutgie Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] Multi processor, 1.618 4/3 Best MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] A schedulability test has speedup factor s , s ≥1, if any task set that is schedulable by any algorithm on platform with processing speed of 1, it will be deemed schedulable by this test upon a processor that is s times as fast .

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. Lazy Priority Adjustment – MC Correctness: [ Gu et al., RTCSA’13 ] - All deadlines met under normal mode LE-EDF - HI deadlines met under HI mode [ Guo & Baruah, RTNS’15 ] – Important, Interesting, & Hard DOMINATE Speedup Bound Strategy Work Uniprocessor, 1.618, Best OCBP [Baruah, Li, Soutgie Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] Multi processor, 1.618 4/3 Best MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] • Best (Optimal) speedup factor ≠ Optimal scheduling strategy/analysis

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. – MC Correctness: - All deadlines met under normal mode Mode switch - HI deadlines met under HI mode – Important, Interesting, & Hard NP-Hard in the strong sense “Optimal” Speedup Bound Strategy Work clairvoyant Uniprocessor, 1.618, Best OCBP [Baruah, Li, Soutgie CONDITIONS Strategy SUFFICIENT Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] 1 4/3 Multi processor, 1.618 4/3 MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] NECESSARY A schedulability test has speedup factor s , s ≥1, if any task set that is CONDITIONS schedulable by any algorithm on platform with processing speed of 1, it will be deemed schedulable by this test upon a processor that is s times as fast .

MC & Vestal’s Interpretation • Mixed Criticality (MC) [Vestal, RTSS’07] – MC: functionalities of different degree of importance are implemented upon a shared platform. Lazy Priority Adjustment – MC Correctness: [ Gu et al., RTCSA’13 ] - All deadlines met under normal mode LE-EDF - HI deadlines met under HI mode [ Guo & Baruah, RTNS’15 ] – Important, Interesting, & Hard Speedup Bound Strategy Work Uniprocessor, 1.618, Best OCBP [Baruah, Li, Soutgie Vestal Job RTAS’10] Uniprocessor, 4/3, Best EDF-VD [Li & Baruah RTSS’10] Vestal Task [Baruah et al. ECRTS’12] Multi processor, 1.618 4/3 Best MC-Fluid [Lee et al. RTSS’14] Vestal Task 4/3, Best MCF [Our Work, RTSS’15] • Best (Optimal) speedup factor ≠ Optimal scheduling strategy/analysis • Speedup against clairvoyant ≠ Speedup over online optimal

Thank you! Zhishan Guo guozh@mst.edu Mar. 29, 2017

Acknowledgement • Prof. Sanjoy Baruah, UNC Chapel Hill (Ph.D. advisor) • Prof. Nathan Fisher, Wayne State U • Prof. Luca Santinelli, ONERA France • Prof. Mohammed Al Faruque, UC Irvine • Dr. Zhenkai Zhang, Vanderbilt U • Prof. Abusayeed Saifullah, Wayne State U • Prof. Sajal Das, MST • Prof. Haoyi Xiong, MST • Ms. Sai Sruti, MST • Mr. Ashik Bhuiyan, MST

Backup Slides