A probabilistic approach for fault tolerant multiprocessor real-time scheduling

Berten,; Goossens,; Jeannot,

doi:10.1109/ipdps.2006.1639409

Cited by 6 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each task τ i is assumed to have t i replicas and a probability p i which is the probability that a replica fails. The work in Berten et al (2006) has several interesting results. First, sufficient number of processors that are required to meet all the deadlines of all the replicas of all tasks is computed based on a sufficient schedulability condition for global EDF scheduling.…”

Section: Related Workmentioning

confidence: 99%

“…There are several works on fault-tolerant scheduling based on partitioned and global approaches for multiprocessors (Oh and Son 1994;Bertossi et al 1999;Hashimoto et al 2000;Chen et al 2007;Kim et al 2010;Berten et al 2006;Girault et al 2003;Liberato et al 1999;Pathan and Jonsson 2011a;Huang et al 2011). In partitioned fault-tolerant scheduling, a task-allocation algorithm assigns the primary and backups of each task to distinct processors 1 at design time.…”

Section: Fault-tolerant Real-time Schedulingmentioning

confidence: 99%

“…The Pr S for lifetime of 1 year for the B fault model in Table 5 is 0.99838547. We also computed the Pr S where all backups are passive (∀i, h i = 0) as is assumed in many previous works (Chen et al 2007;Hashimoto et al 2000;Kim et al 2010;Bertossi et al 1999;Oh and Son 1994;Berten et al 2006;Liberato et al 1999;Pathan and Jonsson 2011a;Huang et al 2011). This value of Pr S is also 0.99838547 for lifetime of 1 year for the B fault model.…”

Section: Impact Of the Heuristic To Determine Number Of Active Backupsmentioning

confidence: 99%

“…There are few works that addressed fault-tolerant global scheduling (Berten et al 2006;Liberato et al 1999;Pathan and Jonsson 2011a;Huang et al 2011). Berten et al (2006) proposed fault-tolerant EDF scheduling based on probabilistic analysis assuming strictly periodic tasks, deadline equals period, re-execution of the primary as only means of backup and does not consider processor failures.…”

Section: Related Workmentioning

confidence: 99%

“…Berten et al (2006) proposed fault-tolerant EDF scheduling based on probabilistic analysis assuming strictly periodic tasks, deadline equals period, re-execution of the primary as only means of backup and does not consider processor failures. Each task τ i is assumed to have t i replicas and a probability p i which is the probability that a replica fails.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Real-time scheduling algorithm for safety-critical systems on faulty multicore environments

Pathan

2016

Real-Time Syst

View full text Add to dashboard Cite

An algorithm (called FTM) for scheduling of real-time sporadic tasks on a multicore platform is proposed. Each task has a deadline by which it must complete its non-erroneous execution. The FTM algorithm executes backups in order to recover from errors caused by non-permanent and permanent hardware faults. The worst-case schedulability analysis of FTM algorithm is presented considering an applicationlevel error model, which is independent of the stochastic behavior of the underlying hardware-level fault model. Then, the stochastic behavior of hardware-level fault model is plugged in to the analysis to derive the probability of meeting all the deadlines. Such probabilistic guarantee is the level of assurance (i.e., reliability) regarding the correct functional and timing behaviors of the system. One of the salient features of FTM algorithm is that it executes some backups in active redundancy to exploit the parallel multicore architecture while other backups passively to avoid unnecessary execution of too many active backups. This paper also proposes a scheme to determine for each task the number of backups that should run in active redundancy in order to increase the probability of meeting all the deadlines. The effectiveness of the proposed approach is demonstrated using an example application.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Fault-tolerant Real-time Schedulingmentioning

confidence: 99%

Section: Impact Of the Heuristic To Determine Number Of Active Backupsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Real-time scheduling algorithm for safety-critical systems on faulty multicore environments

Pathan

2016

Real-Time Syst

View full text Add to dashboard Cite

show abstract

Satisfaction-based query replication

Quiané-Ruiz

Lamarre

Valduriez

2011

Distrib Parallel Databases

View full text Add to dashboard Cite

In large-scale Internet-based distributed systems, participants (consumers and providers) are typically autonomous, i.e. they may have special interests towards queries and other participants. In this context, a way to avoid a participant to voluntarily leave the system is satisfying its interests when allocating queries. However, participants satisfaction may also be negatively affected by the failures of other participants. Query replication is a solution to deal with providers failures, but, it is challenging because of autonomy: it cannot only quickly overload the system, but also it can dissatisfy participants with uninteresting queries. Thus, a natural question arises: should queries be replicated? If so, which ones? and how many times? In this paper, we answer these questions by revisiting query replication from a satisfaction and probabilistic point of view. We propose a new algorithm, called S b QR, that decides on-the-fly whether a query should be replicated and at which rate. As replicating a large number of queries might overload the system, we propose a variant of our algorithm, called S b QR+. The idea is to voluntarily fail to allocate as many replicas as required by consumers for low critical queries so as to keep resources for high critical queries during query-intensive periods. Our experimental results demonstrate that our algorithms significantly outperform the baseline algorithms from both the Communicated by M. Tamer Özsu. 2 Distrib Parallel Databases (2012) 30:1-26performance and satisfaction points of view. We also show that our algorithms automatically adapt to the criticality of queries and different rates of participant failures.

show abstract