The backplane bandwidth is the maximum amount of data that can be passed between the switch interface processor or interface card and the data bus. The higher the bandwidth of a switch’s backplane, the stronger the ability to process data, but at the same time the design cost will increase.
However, how to check whether the backplane bandwidth of a switch is enough? Obviously, the method of estimation is useless. The author believes that it should be considered from two aspects:
1. The sum of the X number of port capacity should be 2 times less than the backplane bandwidth, which can achieve full duplex non-blocking switching, proving that the switch has the conditions to maximize data switching performance.
2. Full configuration throughput (Mbps) = Number of full configuration GE ports × 1.488Mpps The theoretical throughput of 1 gigabit port when the packet length is 64 bytes is 1.488Mpps. For example, a switch that can provide up to 64 gigabit ports, with a full configuration throughput of 64×1.488Mpps = 95.2Mpps, to ensure that non-blocking packet switching is provided when all ports are operating at average speed. If a switch can provide up to 176 gigabit ports and the claimed throughput is less than 261.8Mpps (176 x 1.488Mpps = 261.8), then the user has reason to think that the switch is using a blocking structural design.
Generally, switches that satisfy both are qualified switches.
Switches with relatively large backplanes and relatively small throughput, in addition to retaining the ability to upgrade and expand, there is a problem with software efficiency/special chip circuit design; the backplane is relatively small. Switches with relatively large throughput have relatively high overall performance. However, the backplane bandwidth can be trusted by the manufacturer, but the throughput cannot be trusted by the manufacturer, because the latter is a design value, testing is difficult and not very meaningful.