Budget Constrained Resource Allocation for Non-Deterministic Workflows on a IaaS Cloud
نویسندگان
چکیده
Many scienti c applications are described through work ow structures. Due to the increasing level of parallelism o ered by modern computing infrastructures, work ow applications now have to be composed not only of sequential programs, but also of parallel ones. Cloud platforms bring on-demand resource provisioning and pay-as-you-go payment charging. Then the execution of a work ow corresponds to a certain budget. The current work addresses the problem of resource allocation for non-deterministic work ows under budget constraints. We present a way of transforming the initial problem into sub-problems that have been studied before. We propose two new allocation algorithms that are capable of determining resource allocations under budget constraints and we present ways of using them to address the problem at hand. Key-words: resource allocation, scheduling, PTG, work ow ∗ [email protected] † [email protected] ‡ [email protected] § [email protected] ha l-0 06 97 03 2, v er si on 2 20 M ay 2 01 2 Allocation sous contraintes de budget de work ows non-déterministes pour Cloud IaaS Résumé : De nombreuses applications scienti ques sont décrites sous la forme de work ows. Du fait de l'accroissement du niveau de parallélisme o ert par les infrastructures de calcul modernes, de telles applications doivent désormais être composées non seulement de programmes séquentiels mais aussi de programmes parallèles. Les Clouds o rent le provisionnement de ressources à la demande ainsi qu'une facturation à l'utilisation. L'exécution d'un work ow correspond alors à un certain budget. Dans cet article, nous considérons le problème de l'allocation de ressources à un work ow non déterministe en présence de contraintes de budget. Nous présentons une façon de transformer le problème initial en une série de sous-problèmes qui ont été largement étudiés. Nous proposons deux algorithmes originaux qui peuvent déterminer des allocations de ressources sous contrainte de budget. Nous détaillons également comment les utiliser pour résoudre le problème initial. Mots-clés : Allocation de ressources, ordonnancement, PTG, work ow ha l-0 06 97 03 2, v er si on 2 20 M ay 2 01 2 Allocating Non-Deterministic Work ows on a IaaS Cloud 3
منابع مشابه
Budget Constrained Resource Allocation for Non-deterministic Workflows on an IaaS Cloud
Many scienti c applications are described through work ow structures. Due to the increasing level of parallelism o ered by modern computing infrastructures, work ow applications now have to be composed not only of sequential programs, but also of parallel ones. Cloud platforms bring on-demand resource provisioning and pay-as-you-go payment charging. Then the execution of a work ow corresponds t...
متن کاملAlgorithms for cost- and deadline-constrained provisioning for scientific workflow ensembles in IaaS clouds
Large-scale applications expressed as scientific workflows are often grouped into ensembles of inter-related workflows. In this paper, we address a new and important problem concerning the efficient management of such ensembles under budget and deadline constraints on Infrastructure as a Service (IaaS) clouds. IaaS clouds are characterized by ondemand resource provisioning capabilities and a pa...
متن کاملScheduling Multilevel Deadline-Constrained Scientific Workflows on Clouds Based on Cost Optimization
This paper presents a cost optimizationmodel for scheduling scientificworkflows on IaaS clouds such asAmazonEC2orRackSpace. We assume multiple IaaS clouds with heterogeneous virtual machine instances, with limited number of instances per cloud and hourly billing. Input and output data are stored on a cloud object store such as Amazon S3. Applications are scientific workflows modeled as DAGs as ...
متن کاملResource provisioning and scheduling algorithms for scientific workflows in cloud computing environments
Scientific workflows describe a series of computations that enable the analysis of data in a structured and distributed manner. Their importance is exacerbated in todays big data era as they become a compelling mean to process and extract knowledge from the ever-growing data produced by increasingly powerful tools such as telescopes, particle accelerators, and gravitational wave detectors. Due ...
متن کاملEconomy Based Resource Allocation in IaaS Cloud
Infrastructure as a Service (IaaS) offers hardware resources (computing power, storage and network) as a service to its customers. The customers order these resources in the form of a lease. Aim of any service provider is to make a leasing plan to maximize the number of accepted leases. Opennebula is popular open source toolkit for building IaaS cloud. Opennebula has its own lease manager and i...
متن کامل