Minimizing Cost of Virtual Machines for Deadline-Constrained MapReduce Applications in the Cloud

Hwang, Eunji; Kim, Kyong Hoon

doi:10.1109/grid.2012.19

Cited by 56 publications

(27 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, majority of prior works [4], [10], [6], [5], [7], [11] did not consider the time it takes to upload data to Cloud when modelling the scheduling and provisioning problems. Conversely, we consider the time it takes to transfer the input data to the mappers and intermediate data to the reducers.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…The LFFCost algorithm [5] is a heuristic that is expected to have lower execution time. However, it can not handle budget and deadline constraints.…”

Section: Algorithmsmentioning

confidence: 99%

“…• LFFCost -an implementation of the List and First Fit (LFF) algorithm proposed by Hwang and Kim [5]. Virtual machines (VMs) in LFFCost are sorted by cost.…”

Section: Algorithms For Provisioning and Schedulingmentioning

confidence: 99%

“…As shown in Figure 7, BBCostPerf algorithm runs faster than BTCost and BBCost because it stops traversing the tree in early stages when PerfTree finds a solution with less cost earlier than CostTree. Most existing MapReduce schedulers and frameworks do not consider budget as a constraint [4], [10], [6], [5], [7], [11], although they help in efficiently running a MapReduce job in Cloud environments. In addition, the majority of the implementations are Hadoop-based and use Hadoop default scheduling algorithms to schedule jobs on Clouds [4], [10], [6], [11].…”

Section: Performance Evaluationmentioning

confidence: 99%

“…There are many SLA-based Big Data computing and MapReduce scheduling studies [4], [5], [6], [7] in the Cloud context, however they do not provision Cloud resources dynamically. Instead, they have the resources already pre-provisioned (static) on a private Cloud, which form a virtual cluster.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

SLA-Aware Provisioning and Scheduling of Cloud Resources for Big Data Analytics

Alrokayan

Dastjerdi

Buyya

2014

2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)

View full text Add to dashboard Cite

Abstract-The stunning growth in data has immensely impacted organizations. Their infrastructure and traditional data management system could not keep up to scale of Big Data. They have to either invest heavily on their infrastructure or move their Big Data analytics to Cloud where they can benefit from both on-demand scalability and contemporary data management techniques. However, to make Cloud hosted Big Data analytics available to wider range of enterprises, we have to carefully capture their preferences in terms of budget and service level objectives. Therefore, this study aims at proposing a SLA and cost-aware resource provisioning and task scheduling approach tailored for Big Data applications in the Cloud. Current approaches assume that data is pre-stored in cluster nodes prior to deployment of Big Data applications. In addition, their focus is purely on task scheduling, and not virtual machine provisioning. We argue that in the Cloud computing context this is not applicable, because the nodes are provisioned dynamically (data cannot be pre-stored) and leaving provisioning to user may lead to under or over provisioning that can both lead to SLA or budget constraint violations. Therefore, in this study we first model the user request, which consist of Big Data analytics jobs with budget and deadline. Then, we model infrastructures as a list of data centers, virtual machines (offered in a pay-as-yougo model), data sources, and network throughputs. After that, to address the aforementioned issues, we propose and compare costaware and SLA-based algorithms which provision cloud resources and schedule analytics tasks.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

“…The LFFCost algorithm [5] is a heuristic that is expected to have lower execution time. However, it can not handle budget and deadline constraints.…”

Section: Algorithmsmentioning

confidence: 99%

“…• LFFCost -an implementation of the List and First Fit (LFF) algorithm proposed by Hwang and Kim [5]. Virtual machines (VMs) in LFFCost are sorted by cost.…”

Section: Algorithms For Provisioning and Schedulingmentioning

confidence: 99%