Toggle Main Menu Toggle Search

Open Access padlockePrints

Checkpointing models for tasks with widely different processing times

Lookup NU author(s): Dr Paul EzhilchelvanORCiD, Emeritus Professor Isi Mitrani

Downloads


Licence

This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by Springer, 2023.

For re-use rights please refer to the publisher's terms and conditions.


Abstract

A server subject to random breakdowns and repairs offers services to incomingjobs whose lengths are highly variable. A checkpointing policy aiming to protectagainst possibly lengthy recovery periods is in operation. The problem of howto choose a checkpointing interval in order to optimize performance is addressedby analysing a general queueing model which includes breakdowns, repairs, back-upsand recoveries. Exact solutions are obtained under both Markovian andnon-Markovian assumptions. Numerical experiments illustrate the conditionswhere checkpoints are useful and where they are not, and in the former case,quantify the achievable benefits.


Publication metadata

Author(s): Ezhilchelvan P, Mitrani I

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: EPEW 2022: Computer Performance Engineering

Year of Conference: 2023

Pages: 100-114

Online publication date: 25/01/2023

Acceptance date: 02/04/2018

Date deposited: 11/10/2022

ISSN: 0302-9743

Publisher: Springer

URL: https://doi.org/10.1007/978-3-031-25049-1_7

DOI: 10.1007/978-3-031-25049-1_7

Library holdings: Search Newcastle University Library for this item

Series Title: Part of the Lecture Notes in Computer Science book series

ISBN: 9783031250491


Share