An RDMA Middleware for Asynchronous Multi-stage Shuffling in Analytical Processing - Distributed Applications and Interoperable Systems (DAIS 2016) Access content directly
Conference Papers Year : 2016

An RDMA Middleware for Asynchronous Multi-stage Shuffling in Analytical Processing

Abstract

A key component in large scale distributed analytical processing is shuffling, the distribution of data to multiple nodes such that the computation can be done in parallel. In this paper we describe the design and implementation of a communication middleware to support data shuffling for executing multi-stage analytical processing operations in parallel. The middleware relies on RDMA (Remote Direct Memory Access) to provide basic operations to asynchronously exchange data among multiple machines. Experimental results show that the RDMA-based middleware developed can provide a 75 % reduction of the costs of communication operations on parallel analytical processing tasks, when compared with a sockets middleware.
Fichier principal
Vignette du fichier
416479_1_En_5_Chapter.pdf (390.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01434800 , version 1 (13-01-2017)

Licence

Attribution

Identifiers

Cite

Rui C. Gonçalves, José Pereira, Ricardo Jiménez-Peris. An RDMA Middleware for Asynchronous Multi-stage Shuffling in Analytical Processing. 16th IFIP WG 6.1 International Conference on Distributed Applications and Interoperable Systems (DAIS), Jun 2016, Heraklion, Crete, Greece. pp.61-74, ⟨10.1007/978-3-319-39577-7_5⟩. ⟨hal-01434800⟩
57 View
63 Download

Altmetric

Share

Gmail Facebook X LinkedIn More