Merkat: Market-based Autonomous Application and Resource Management in the Cloud

Abstract : Organizations owning HPC infrastructures are facing difficulties in managing their infrastructures. These difficulties come from the need to provide concurrent resource access to applications with different resource requirements while considering that users might have different performance objectives, or Service Level Objectives (SLOs) for executing them. To address these challenges this paper proposes a market-based SLO-driven cloud platform. This platform relies on a market-based model to allocate resources to applications while taking advantage of cloud flexibility to maximize resource utilization. The combination of currency distribution and dynamic resource pricing ensures fair resource distribution. In the same time, autonomous controllers apply adaptation policies to scale the application resource demand according to user SLOs. The adaptation policies can: (i) dynamically tune the amount of CPU and memory provisioned for the virtual machines in contention periods; (ii) dynamically change the number of virtual machines. We evaluated this proposed platform on the Grid'5000 testbed. Results show that: (i) the platform provides flexible support for different application types and different SLOs; (ii) the platform is capable to provide good user satisfaction achieving acceptable performance degradation compared to existing centralized solutions.
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/hal-00850862
Contributor : Stefania Victoria Costache <>
Submitted on : Friday, August 9, 2013 - 11:40:35 AM
Last modification on : Friday, November 16, 2018 - 1:39:37 AM
Long-term archiving on : Wednesday, April 5, 2017 - 8:29:06 PM

File

RR-8343.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00850862, version 1

Citation

Stefania Victoria Costache, Nikos Parlavantzas, Christine Morin, Samuel Kortas. Merkat: Market-based Autonomous Application and Resource Management in the Cloud. [Research Report] RR-8343, INRIA. 2013. ⟨hal-00850862⟩

Share

Metrics

Record views

797

Files downloads

473