Workflow management for soft real-time interactive applications in virtualized environments

Gogouvitis, Spyridon V.; Konstanteli, Kleopatra; Waldschmidt, Stefan; Kousiouris, George; Katsaros, Georgios; Menychtas, Andreas; Kyriazis, Dimosthenis; Varvarigou, Theodora

doi:10.1016/j.future.2011.05.017

Cited by 30 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding applications, the execution of scientific workflows [24,25,26,27] has obtained significant success, whereas many early studies [4,5,6,28,29] have assessed that public clouds have not been designed for running tightly coupled MPI applications, primarily due to their poor network performance, processor sharing and the use of commodity interconnection technologies. In order to overcome this performance bottleneck, Amazon EC2 introduced their Cluster Compute (CC) instances.…”

Section: Hpc In the Cloudmentioning

confidence: 99%

Performance analysis of HPC applications in the cloud

Expósito

Taboada

Ramos

et al. 2013

Future Generation Computer Systems

View full text Add to dashboard Cite

The scalability of High Performance Computing (HPC) applications depends heavily on the efficient support of network communications in virtualized environments. However, Infrastructure as a Service (IaaS) providers are more focused on deploying systems with higher computational power interconnected via high-speed networks rather than improving the scalability of the communication middleware. This paper analyzes the main performance bottlenecks in HPC applications scalability on Amazon EC2 Cluster Compute platform: (1) evaluating the communication performance on shared memory and a virtualized 10 Gigabit Ethernet network; (2) assessing the scalability of representative HPC codes, the NAS Parallel Benchmarks, using an important number of cores, up to 512; (3) analyzing the new cluster instances (CC2), both in terms of single instance performance, scalability and costefficiency of its use; (4) suggesting techniques for reducing the impact of the virtualization overhead in the scalability of communication-intensive HPC codes, such as the direct access of the Virtual Machine to the network and reducing the number of processes per instance; and (5) proposing the combination of message-passing with multithreading as the most scalable and cost-effective option for running HPC applications on Amazon EC2 Cluster Compute platform.

show abstract

Section: Hpc In the Cloudmentioning

confidence: 99%

Performance analysis of HPC applications in the cloud

Expósito

Taboada

Ramos

et al. 2013

Future Generation Computer Systems

View full text Add to dashboard Cite

show abstract

“…Other works deal with offering users soft real-time guarantees on shared resources [27], [28]. However, in contrast to our problem statement, all computation tasks must eventually complete.…”

Section: A Soft Real-time Systemsmentioning

confidence: 97%

Resource Management Architecture for Fair Scheduling of Optional Computations

Camillo

Caron

Guivarch

et al. 2013

2013 Eighth International Conference on P2P, Parallel, Grid, Cloud and Internet Computing

View full text Add to dashboard Cite

Abstract-Most High-Performance Computing platforms require users to submit a pre-determined number of computation requests (also called jobs). Unfortunately, this is cumbersome when some of the computations are optional, i.e., they are not critical, but their completion would improve results. For example, given a deadline, the number of requests to submit for a Monte Carlo experiment is difficult to choose. The more requests are completed, the better the results are, however, submitting too many might overload the platform. Conversely, submitting too few requests may leave resources unused and misses an opportunity to improve the results. This paper introduces and solves the problem of scheduling optional computations. It proposes a generic client-server architecture and an implementation in a production GridRPC middleware, which auto-tunes the number of requests. Real-life experiments show that several metrics are improved, such as user satisfaction, fairness and the number of completed requests. Moreover, the solution is shown to be scalable.

show abstract

“…It has also (1) to fit the cloud elasticity to keep up when an application or infrastructure scales up or down dynamically [18] and (2) to provide a "simple" interface so that the cloud complexity is as transparent as possible for end users. This requires being able to "generate and deploy on the fly" contextual monitoring means.…”

Section: Adapting Qos Management and Governance To Multi-cloud Systemsmentioning

confidence: 99%

Multi-dimensional Model Driven Policy Generation

Ouedraogo

Biennier

2014

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. As Cloud Computing provides agile and scalable IT infrastructure, QoS-assured services and customizable computing environment, it increases the call for agile and dynamic deployment and governance environments over multi-cloud infrastructure. By now, governance and Non Functional Properties (such as security, QoS…) are managed in a static way, limiting the global benefits of deploying service-based information system over multi-cloud environments. To overcome this limit, we propose a contextualised policy generation process to allow both an agile management NFP in a multi-cloud context and a secured deployment of the service-based information system. The last step of this Model Driven Policy Engineering approach uses policies as Model@runtime to select, compose, deploy and orchestrate NFP management functions depending on the exact execution context. Moreover, a dynamic governance loop including autonomic KPI management is used to control continuously the governance results.

show abstract

Workflow management for soft real-time interactive applications in virtualized environments

Cited by 30 publications

References 24 publications

Performance analysis of HPC applications in the cloud

Performance analysis of HPC applications in the cloud

Resource Management Architecture for Fair Scheduling of Optional Computations

Multi-dimensional Model Driven Policy Generation

Contact Info

Product

Resources

About