Improving data-intensive EDA performance with annotation-driven laziness - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Science of Computer Programming Année : 2015

Improving data-intensive EDA performance with annotation-driven laziness

Résumé

Event-driven programming in large scale environments is becoming a common requirement of modern distributed applications. It introduces some beneficial effects such as real-time state updates and replications, which enable new kinds of applications and efficient architectural solutions. However, these benefits could be compromised if the adopted infrastructure were not designed to ensure efficient delivery of events and related data. This paper presents an architectural model, a middleware (WS-Link) and annotation-based mechanisms to ensure high performance in delivering events carrying large attachments. We transparently decouple event notification from related data to avoid useless data-transfers. This way, while event notifications are routed in a conventional manner through an event service, data are directly and transparently transferred from publishers to subscribers. The theoretical analysis shows that we can reduce the average event delivery time by half, compared to a conventional approach requiring the full mediation of the event service. The experimental analysis confirms that the proposed approach outperforms the conventional one (both for throughput and delivery time) even though the middleware overhead, introduced by the specific adopted model, slightly reduces the expected benefits.

Dates et versions

hal-01094590 , version 1 (12-12-2014)

Identifiants

Citer

Quirino Zagarese, Gerardo Canfora, Eugenio Zimeo, Iyad Alshabani, Laurent Pellegrino, et al.. Improving data-intensive EDA performance with annotation-driven laziness. Science of Computer Programming, 2015, 97 (Special Issue on Service-Oriented Architecture and Programming (SOAP)), pp.266-279. ⟨10.1016/j.scico.2014.03.007⟩. ⟨hal-01094590⟩
157 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More