A protocol for deadlock-free dynamic reconfiguration in high-speed local area networks

Citation
R. Casado et al., A protocol for deadlock-free dynamic reconfiguration in high-speed local area networks, IEEE PARALL, 12(2), 2001, pp. 115-132
Citations number
23
Categorie Soggetti
Computer Science & Engineering
Journal title
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
ISSN journal
10459219 → ACNP
Volume
12
Issue
2
Year of publication
2001
Pages
115 - 132
Database
ISI
SICI code
1045-9219(200102)12:2<115:APFDDR>2.0.ZU;2-3
Abstract
High-speed local area networks (LANs) consist of a set of switches intercon nected by point-to-point links, and hosts linked to those switches through a network interface card. High-speed LANs may change their topology due to switches being turned on/off, hot expansion, link remapping, and component failures. In these cases, a distributed reconfiguration protocol analyzes t he topology, computes the new routing tables, and downloads them to the cor responding switches. Unfortunately, in most cases, user, traffic is stopped during the reconfiguration process to avoid deadlock. These strategies are called static reconfiguration techniques. Although network reconfiguration s are not frequent, static reconfiguration such as this may take hundreds o f milliseconds to execute, thus degrading system availability significantly . Several distributed real-time applications have strict communication requ irements, Distributed multimedia applications have similar, although less s trict, quality of service (QoS) requirements [3], [4]. Both stopping packet transmission and discarding packets due to the reconfiguration process pre vent the system from satisfying the above requirements. Therefore, in order to support hard real-time and distributed multimedia applications over a h igh-speed LAN, we need to avoid stopping user traffic and discarding packet s when the topology changes. In this paper, we propose a new deadlock-free distributed reconfiguration protocol that is able to asynchronously update routing tables without stopping user traffic. This protocol is valid for an y topology, including regular as well as irregular topologies. It is also v alid for packet switching as well as for cut-through switching techniques a nd does not rely on the existence of virtual channels to work. Simulation r esults show that the behavior of our protocol is significantly better than for other protocols based on stopping user traffic.