Performance evaluation of dynamic reconfiguration in high-speed local area networks

Abstract

High-speed local area networks (LANs) consist of a set of switches connected by point-to-point links, and hostslinked to switches through a network interface card. Highspeed LANs may change their topology due to switches and hosts being turned on/off, link remapping, and component failures. In these cases, a distributed reconfiguration algorithm analyzes the topology, computes the new routing tables, and downloads them to the corresponding switches. Unfortunately, in most cases, user traffic is stopped during the reconfiguration process to avoid deadlock. Although network reconfigurations are not frequent, static reconfiguration such as this may take hundreds of milliseconds to execute, thus degrading system availability significantly.Several distributed real-time applications have strict communication requirements [9,11]. Distributed multimedia applications have similar, although less strict, quality of service (QoS) requirements. Both stopping packet transmission and discarding packets due to the reconfiguration process prevent the system from satisfying the above requirements. Therefore, in order to support hard real-time and distributed multimedia applications over a high-speed LAN, we need to avoid stopping user traffic and discarding packets when the topology changes.In this paper, we propose a new deadlock-free distributed reconfiguration algorithm that is able to asynchronously update routing tables without stopping user traffic. This algorithm is valid for any topology, including regular as well as irregular topologies. Simulation results show that the behavior of our algorithm is significantly better than for other algorithms based on a spanning-tree formation.

Dynamic virtual network restoration with optimal standby virtual router selection

“…Recent works mainly concentrated on optimizing the routing algorithms to provide better support for dynamic reconfiguration. These algorithms were studied by either using mathematical models, simulations [24,46,48], or by testing them on networks using local lab machines [100]. In order to implement such approaches on a wide-area core network, hardware and software would need to be modified on every router.…”

A new approach to provide real-time services on high-speed local area networks

“…Every port has the same number of virtual channels: RTC virtual channels for real-time traffic 3 , MIN adaptive virtual channels (minimal routing) and UD virtual channels (Up*/Down* routing) for best-effort traffic (see Subsection 3.2), and C/RTC virtual channels for reconfiguration control traffic and channel establishment traffic. The CONTROL UNIT manages all control messages due to reconfiguration, and all messages used to establish and to tear down real-time channels 4 .…”

“…Moreover, realtime constraints can not be met because of traffic disruption. Duato et al [1,3] have proposed a dynamic reconfiguration algorithm, called Partial Progressive Reconfiguration, to minimize the negative effects of static reconfiguration on network performance. The protocol guarantees that the global routing algorithm remains deadlock-free at any time.…”

“…When either a fault or a hot topology change breaks down a primary channel, realtime messages are redirected through its secondary channel and the dynamic reconfiguration algorithm, described in [1,3], is triggered. The procedure to be followed for interrupted secondary channels is the same apart from real-time traffic is unaffected.…”

“…On the other hand, dynamic reconfiguration, recently proposed by Duato et al [1,3], updates the routing tables without stopping user traffic. Note that dynamic reconfiguration by itself does not provide neither quality of service nor real-time services, but it provides support for an additional mechanism designed to meet real-time requirements.…”