On the Cost of Task Re-Scheduling in Fault-Tolerant Task Parallel Computations
نویسندگان
چکیده
Fault tolerance is still an “hot” topic in the context of Grid computing. There exist several solutions and techniques to face this issue, some of them inherited from the fault tolerance research, some other introduced in the context of Grid computing. Anyway, poor work has been done in providing such fault tolerance strategies in a lightweight, scalable and analyzable way. In this technical report we address the last aspect, by considering an abstract model of computation for a class of structured parallel programs (namely farm computations) to analyze the overhead incurred by parallel computations in the case of failures. We present the evolution of our study showing the model we exploit, and its properties, and the results we obtained. We also completely define some base cases, and we present experimental results to validate our approach.
منابع مشابه
Stability Assessment Metamorphic Approach (SAMA) for Effective Scheduling based on Fault Tolerance in Computational Grid
Grid Computing allows coordinated and controlled resource sharing and problem solving in multi-institutional, dynamic virtual organizations. Moreover, fault tolerance and task scheduling is an important issue for large scale computational grid because of its unreliable nature of grid resources. Commonly exploited techniques to realize fault tolerance is periodic Checkpointing that periodically ...
متن کاملImproving the palbimm scheduling algorithm for fault tolerance in cloud computing
Cloud computing is the latest technology that involves distributed computation over the Internet. It meets the needs of users through sharing resources and using virtual technology. The workflow user applications refer to a set of tasks to be processed within the cloud environment. Scheduling algorithms have a lot to do with the efficiency of cloud computing environments through selection of su...
متن کاملGreen Energy-aware task scheduling using the DVFS technique in Cloud Computing
Nowdays, energy consumption as a critical issue in distributed computing systems with high performance has become so green computing tries to energy consumption, carbon footprint and CO2 emissions in high performance computing systems (HPCs) such as clusters, Grid and Cloud that a large number of parallel. Reducing energy consumption for high end computing can bring various benefits such as red...
متن کاملSupervised Workpools for Reliable Massively Parallel Computing
The manycore revolution is steadily increasing the performance and size of massively parallel systems, to the point where system reliability becomes a pressing concern. Therefore, massively parallel compute jobs must be able to tolerate failures. For example, in the HPCGAP project we aim to coordinate symbolic computations in architectures with 10 cores. At that scale, failures are a real issue...
متن کاملA new Shuffled Genetic-based Task Scheduling Algorithm in Heterogeneous Distributed Systems
Distributed systems such as Grid- and Cloud Computing provision web services to their users in all of the world. One of the most important concerns which service providers encounter is to handle total cost of ownership (TCO). The large part of TCO is related to power consumption due to inefficient resource management. Task scheduling module as a key component can has drastic impact on both user...
متن کامل