Selection of a checkpoint interval in a critical-task environment

Geist, Robert; Reynolds, R. C.; Westall, James

doi:10.1109/24.9847

Cited by 43 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic power management through voltage/frequency scaling [15] utilizes the slack in a given computation to reduce energy consumption while checkpointing.The authors of [7,11] utilize that slack to improve the reliability of the computation. Hence, it is natural to explore the interplay of power management and fault tolerance [12], when both techniques result in delaying the completion time of tasks, thus resulting in a tradeoff between power consumption, reliability and performance.…”

Section: Related Workmentioning

confidence: 99%

Energy-aware checkpointing of divisible tasks with soft or hard deadlines

Aupy

Benoît

Melhem

et al. 2013

2013 International Green Computing Conference Proceedings

View full text Add to dashboard Cite

Abstract:In this paper, we aim at minimizing the energy consumption when executing a divisible workload under a bound on the total execution time, while resilience is provided through checkpointing. We discuss several variants of this multi-criteria problem. Given the workload, we need to decide how many chunks to use, what are the sizes of these chunks, and at which speed each chunk is executed. Furthermore, since a failure may occur during the execution of a chunk, we also need to decide at which speed a chunk should be re-executed in the event of a failure. The goal is to minimize the expectation of the total energy consumption, while enforcing a deadline on the execution time, that should be met either in expectation (soft deadline), or in the worst case (hard deadline). For each problem instance, we propose either an exact solution, or a function that can be optimized numerically. The different models are then compared through an extensive set of experiments. Protocoles de checkpointà faible consommatioń energétique pour des tâches divisibles, sous contrainte faible ou forte du temps d'exécution Résumé :Ce travail viseà minimiser la consommation d'énergie lors de l'exécution d'une quantité de travail divisible, sous contrainte de temps d'exécution, sur une plateforme soumiseà des fautes passagères. La résilience est fournie grâceà un protocole de sauvegarde de points de reprise (checkpoints). Nousétudions différentes variantes de ce problème multi-critère. Etant donnée une quantité de travail, nous devons décider du découpage optimal de celle-ci en morceaux qui seront sauvegardés ; plus précisément, nous devons déterminer le nombre, la taille et la vitesse d'exécution de chacun de ces morceaux. De plus, sachant qu'une faute peut arriver pendant l'exécution de l'un d'entre eux, nous devons décider de la vitesse de ré-exécution de ces morceaux en cas de faute. Le but de ce travail est de minimiser l'espérance de la consommation d'énergie, sous une contrainte temporelle, qui peutêtre atteinte en moyenne (contrainte faible), ou dans le pire cas (contrainte forte). Pour chaque instance du problème, nous fournissons soit une solution exacte, soit une fonction qui peutêtre optimisée numériquement. Les différents modèles sont ensuite comparés via un ensemblé etendu d'expériences.

show abstract

Section: Related Workmentioning

confidence: 99%

Energy-aware checkpointing of divisible tasks with soft or hard deadlines

Aupy

Benoît

Melhem

et al. 2013

2013 International Green Computing Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…Authors [3,4,14,16,22,23] have applied equidistant checkpointing, adaptive checkpointing and other fault tolerance techniques to single as well as multiprocessor systems. But have restricted themselves to assumption that relative deadline is always less than or equal to the period.…”

Section: Introductionmentioning

confidence: 99%

Checkpointing Based Fault Tolerance Patterns for Systems with Arbitrary Deadlines

Tuithung

Ghosh²,

Mukhopadhyay³

2007

15th International Conference on Advanced Computing and Communications (ADCOM 2007)

View full text Add to dashboard Cite

This paper aims to provide a fault tolerant scheduling algorithm that have fault tolerance patterns for periodic task sets with arbitrary deadlines. The fault tolerance is achieved by checkpointing where number of checkpoint is decided on the bases of the lemmas proposed. These patterns provide minimum tolerance to all the releases and an improved tolerance to some releases pertaining to the availability of the slack time. They may be binary (i.e., either provide maximum or minimum tolerance to a release) or greedy (i.e., provide an improved tolerance whenever it is possible) in nature. Theorems have been proposed to ensure that the task set is schedulable with at least minimum fault tolerance. The effectiveness of the proposed patterns have been measured through extensive examples and simulations.

show abstract

“…Authors [3,4,14,16,21,22] have applied equidistant checkpointing, adaptive checkpointing and other fault tolerance techniques to single as well as multiprocessor systems. But have restricted themselves to assumption that relative deadline is always less than or equal to the period.…”

Section: Introductionmentioning

confidence: 99%

Multiple Fault Tolerance Patterns for Systems with Arbitrary Deadline

Agrawal

Yadav

Das

2007

10th International Conference on Information Technology (ICIT 2007)

View full text Add to dashboard Cite

This paper aims to provide a fault tolerant scheduling algorithm that have fault tolerance patterns for periodic task with arbitrary deadlines. The fault tolerance is achieved by checkpointing where number of checkpoint is decided on the bases of the lemmas proposed. These patterns provide minimum tolerance to all the releases and an improved tolerance to some releases pertaining to the availability of the slack time. They may be binary (i.e., either provide maximum or minimum tolerance to a release) or greedy (i.e., provide an improved tolerance whenever it is possible) in nature. Theorems have been proposed to ensure that the task set is schedulable with at least minimum fault tolerance. The effectiveness of the proposed patterns have been measured through extensive examples and simulations. 10th International Conference on Information Technology 0-7695-3068-0/07 $25.00 © 2007 IEEE DOI 167 10th International Conference on Information Technology 0-7695-3068-0/07 $25.00

show abstract

Selection of a checkpoint interval in a critical-task environment

Cited by 43 publications

References 6 publications

Energy-aware checkpointing of divisible tasks with soft or hard deadlines

Energy-aware checkpointing of divisible tasks with soft or hard deadlines

Checkpointing Based Fault Tolerance Patterns for Systems with Arbitrary Deadlines

Multiple Fault Tolerance Patterns for Systems with Arbitrary Deadline

Contact Info

Product

Resources

About