Characterizing Performance and Energy-Efficiency of The RAMCloud Storage System

Abstract : Most large popular web applications, like Facebook and Twitter, have been relying on large amounts of in-memory storage to cache data and offer a low response time. As the main memory capacity of clusters and clouds increases, it becomes possible to keep most of the data in the main memory. This motivates the introduction of in-memory storage systems. While prior work has focused on how to exploit the low-latency of in-memory access at scale, there is very little visibility into the energy-efficiency of in-memory storage systems. Even though it is known that main memory is a fundamental energy bottleneck in computing systems (i.e., DRAM consumes up to 40% of a server's power). In this paper, by the means of experimental evaluation, we have studied the performance and energy-efficiency of RAM-Cloud — a well-known in-memory storage system. We reveal that although RAMCloud is scalable for read-only applications, it exhibits non-proportional power consumption. We also find that the current replication scheme implemented in RAMCloud limits the performance and results in high energy consumption. Surprisingly, we show that replication can also play a negative role in crash-recovery.
Type de document :
Communication dans un congrès
The 37th IEEE International Conference on Distributed Computing Systems (ICDCS 2017) , Jun 2017, Atlanta, United States. 2017
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01496959
Contributeur : Yacine Taleb <>
Soumis le : mardi 28 mars 2017 - 11:16:23
Dernière modification le : jeudi 19 avril 2018 - 11:46:06
Document(s) archivé(s) le : jeudi 29 juin 2017 - 16:30:53

Fichier

ICDCS-CR.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01496959, version 1

Citation

Yacine Taleb, Shadi Ibrahim, Gabriel Antoniu, Toni Cortes. Characterizing Performance and Energy-Efficiency of The RAMCloud Storage System. The 37th IEEE International Conference on Distributed Computing Systems (ICDCS 2017) , Jun 2017, Atlanta, United States. 2017. 〈hal-01496959〉

Partager

Métriques

Consultations de la notice

1008

Téléchargements de fichiers

267