Volunteer Cloud Computing: MapReduce over the Internet

Costa, Fernando Albuquerque; Silva, Luis; Dahlin, Mike

doi:10.1109/ipdps.2011.345

Cited by 38 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MapReduce is a programming model and an associated implementation for processing and generating large datasets that is amenable to a broad variety of real world tasks [3]. Users specify their computation in terms of a map and a reduce function.…”

Section: Mapreduce Modelmentioning

confidence: 99%

A Security Protection Framework for Cloud Computing

2016

J Inf Process Syst

View full text Add to dashboard Cite

Cloud computing is a new style of computing in which dynamically scalable and reconfigurable resources are provided as a service over the internet. The MapReduce framework is currently the most dominant programming model in cloud computing. It is necessary to protect the integrity of MapReduce data processing services. Malicious workers, who can be divided into collusive workers and non-collusive workers, try to generate bad results in order to attack the cloud computing. So, figuring out how to efficiently detect the malicious workers has been very important, as existing solutions are not effective enough in defeating malicious behavior. In this paper, we propose a security protection framework to detect the malicious workers and ensure computation integrity in the map phase of MapReduce. Our simulation results show that our proposed security protection framework can efficiently detect both collusive and non-collusive workers and guarantee high computation accuracy.

show abstract

Section: Mapreduce Modelmentioning

confidence: 99%

A Security Protection Framework for Cloud Computing

2016

J Inf Process Syst

View full text Add to dashboard Cite

show abstract

“…In our work, we do not focus on solving reliability issues; instead we are concerned with performance issues of allocating compute resources to MapReduce jobs and relocating source data. Costa et al [12] propose MapReduce in a global wide-area volunteer setting. However, this system is implemented in the BOINC framework with all input data held by the central scheduler.…”

Section: Related Workmentioning

confidence: 99%

Cross-Phase Optimization in MapReduce

Heintz¹,

Chandra²,

Weissman³

2014

Cloud Computing for Data-Intensive Applications

View full text Add to dashboard Cite

Abstract-MapReduce has been designed to accommodate large-scale data-intensive workloads running on large singlesite homogeneous clusters. Researchers have begun to explore the extent to which the original MapReduce assumptions can be relaxed including skewed workloads, iterative applications, and heterogeneous computing environments. Our work continues this exploration by applying MapReduce across widely distributed data over distributed computation resources. This problem arises when datasets are generated at multiple sites as is common in many scientific domains and increasingly ecommerce applications. It also occurs when multi-site resources such as geographically separated data centers are applied to the same MapReduce job. Using Hadoop, we show that the absence of network and node homogeneity and locality of data lead to poor performance. The problem is that interaction of MapReduce phases becomes pronounced in the presence of heterogeneous network behavior. In this paper, we propose new cross-phase optimization techniques that enable independent MapReduce phases to influence one another.We propose techniques that optimize the push and map phases to enable push-map overlap and to allow map behavior to feed back into push dynamics. Similarly, we propose techniques that optimize the map and reduce phases to enable shuffle cost to feed back and affect map scheduling decisions. We evaluate the benefits of our techniques in both Amazon EC2 and PlanetLab. The experimental results show the potential of these techniques as performance is improved from 7%-18% depending on the execution environment and application.

show abstract

“…Clouds and grids are also considered as execution platforms for large distributed scientific and business applications [23] [24]. BOINC-MR [25] combines MapReduce with BOINC. It aims at to increase the computing power of volunteer distributed systems, allowing more complex applications and paradigms as MapReduce to be executed at dispersed resources on the Internet.…”

Section: Related Workmentioning

confidence: 99%

Support for bioinformatics applications through volunteer and scalable computing frameworks

Gutiérrez

Azevedo

Barreto

et al. 2014

2014 IEEE International Conference on Cluster Computing (CLUSTER)

View full text Add to dashboard Cite

Many e-science applications can benefit from the elasticity of resources provided by volunteer and distributed platforms. While the former is based on resources assigned voluntarily by its owners, the second is based on resources specially configured for this purpose. In this paper, we present the integration of BOINC and Hadoop, two of the most popular middlewares available today, at the infrastructure level of mc 2 , a platform designed to support scientific applications. We discuss some case studies related to DNA sequencing running in CloudBurst, model selection running in the MEGA Computational Core and similarity searches running in BLAST. Our results show scientific users can run their experiments in our platform with a high level of abstraction and, in some cases, with very good performance.

show abstract

Volunteer Cloud Computing: MapReduce over the Internet

Cited by 38 publications

References 9 publications

A Security Protection Framework for Cloud Computing

A Security Protection Framework for Cloud Computing

Cross-Phase Optimization in MapReduce

Support for bioinformatics applications through volunteer and scalable computing frameworks

Contact Info

Product

Resources

About