An Empirical Evaluation of How The Network Impacts The Performance and Energy Efficiency in RAMCloud

Abstract : In-memory storage systems emerged as a de-facto building block for today's large scale Web architectures and Big Data processing frameworks. Many research and engineering efforts have been dedicated to improve their performance and memory efficiency. More recently, such systems can leverage high-performance networks, e.g., Infiniband. To be able to leverage these systems it is essential to understand the trade-offs induced by the use of high-performance networks. This paper reports on work in progress aiming to contribute to a better understanding of the main factors impacting performance of in-memory storage systems. Through a study carried on RAMCloud, we focus on two settings: 1) clients are collocated within the same network as the storage servers (with Infiniband interconnects); 2) clients access the servers from a remote network, through TCP/IP. We compare and discuss aspects related to scalability and power consumption for these two scenarios which correspond to different deployment models for applications making use of in-memory cloud storage systems.
Type de document :
Article dans une revue
Workshop on the Integration of Extreme Scale Computing and Big Data Management and Analytics in conjunction with IEEE/ACM CCGrid 2017 , IEEE, 2017
Liste complète des métadonnées

https://hal.inria.fr/hal-01376923
Contributeur : Yacine Taleb <>
Soumis le : mercredi 15 février 2017 - 14:40:58
Dernière modification le : samedi 25 février 2017 - 01:09:46

Fichier

CCGRIDW.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01376923, version 2

Citation

Yacine Taleb, Shadi Ibrahim, Gabriel Antoniu, Toni Cortes. An Empirical Evaluation of How The Network Impacts The Performance and Energy Efficiency in RAMCloud. Workshop on the Integration of Extreme Scale Computing and Big Data Management and Analytics in conjunction with IEEE/ACM CCGrid 2017 , IEEE, 2017. <hal-01376923v2>

Partager

Métriques

Consultations de
la notice

286

Téléchargements du document

75