Switching Fabric

Switching Fabric

The switching fabric is at the very heart of a router. It is through the switching fabric that the packets are in fact switched (that is, forwarded) from an input port to an output port. Switching can be completed in a number of ways, as shown in Figure 1:

●  Switching via memory. The simplest, earliest routers were often traditional computers, with switching between input and output ports being done under direct control of the CPU (routing processor).

Three switching techniques

Input and output ports functioned as traditional I/O devices in a traditional operating system. An input port with an arriving packet first signaled the routing processor via an interrupt. The packet was then copied from the input port into processor memory. The routing processor then extracted the destination address from the header, looked up the appropriate output port in the forwarding table, and copied the packet to the output ports buffers. Note that if the memory bandwidth is such that B packets per second can be written into, or read from memory, then the overall forwarding throughput (the total rate at which packets are transferred from input ports to output ports) must be less than B/2.

Several mordern routers also switch via memory. A major difference from early routers, however, is that the lookup of the destination address and the storing of the packet into the appropriate memory location is performed by processors on the input line cards. In some ways, routers that switch via memory look very much like shared-memory multiprocessors, with the processors on a line card switching packets into the memory of the appropriate output port. Ciscos Catalyst 8500 series switches [Cisco 8500 2009] forward packets via a shared memory. An abstract model for studying the  properties of memory-based switching and a comparison with other forms of switching can be found in [Iyer 2002].

●  Switching via a bus. In this approach, the input ports transfer a packet directly to the output port over a shared bus, without  intervention by the routing processor (note that when switching via memory, the packet must also cross the system bus going  to/from memory). Although the routing processor is not involved in the bus transfer, because the bus is shared, only one packet at a time can be transferred over the bus. A packet arriving at an input port and finding the bus busy with the transfer of another packet is blocked from passing through the switching fabric and is queued at the input port. Because every packet must cross the single bus, the switching bandwidth of the router is limited to the bus speed.

Given that bus bandwidths of over 1 Gbps are possible in today's technology, switching via a bus is often adequate for routers that operate in access and enterprise networks (for instance, local area and corporate networks). Bus-based switching has been adopted in a number of current router products, including the Cisco 5600 [Cisco Switches 2009], which switches packets over a 32 Gbps backplane bus.

●  Switching via an interconnection network. One way to overcome the bandwidth limitation of a single, shared bus is to use a more sophisticated interconnection network, such as those that have been used in the past to interconnect processors in a multiprocessor computer architecture. A crossbar switch is an interconnection network consisting of 2n buses that connect n input ports to n output ports, as illustrated in Figure 1. A packet arriving at an input port travels along the horizontal bus attached to the input port until it intersects with the vertical bus leading to the desired output port. If the vertical bus leading to the output port is free, the packet is transferred to the output port. If the vertical bus is being used to transfer a packet from another input port to this same output port. the arriving packet is blocked and must be queued at the input port.

Delta and Omega switching fabrics have also been proposed as an interconnetion network between input and output ports. See [Tobagi 1990] for a survey of switch architectures. Cisco 12000 family switches [Cisco 12000 2009] use an interconnection network, providing up to 60 Gbps through the switching fabric. One trend in interconnection network design [Keshav 1998] is to fragment a variable-length IP packet into fixed-length cells, then tag and switch the fixed-Iength cells through the interconnection network. The celIs are then reassembled into the original packet at the output port. The fixed-length cell and internal tag can significantly simplify and speed up the switching of the packet through the interconnection network.

Output port processing

Tags

switching fabric, router, interconnection network, switch architecture

Copy Right

The contents available on this website are copyrighted by TechPlus unless otherwise indicated. All rights are reserved by TechPlus, and content may not be reproduced, published, or transferred in any form or by any means, except with the prior written permission of TechPlus.