The backplane bandwidth of the switch is the maximum data throughput between the switch interface processor or interface card and the data bus. The backplane bandwidth indicates the total data exchange capacity of the switch. The unit is Gbps, which is also called switching bandwidth. The backplane bandwidth of general switches varies from several Gbps to hundreds of Gbps. The higher the backplane bandwidth of a switch, the stronger the ability to process data, but at the same time, the higher the design cost.
Generally speaking, the calculation method is as follows:
1) Backplane Bandwidth at Line Speed
Examine the total bandwidth that all ports on the switch can provide. The formula is port number * corresponding port rate * 2 (full duplex mode). If the total bandwidth is less than the nominal backplane bandwidth, the backplane bandwidth is linear.
2) Layer 2 Packet Forwarding Speed
Layer 2 packet forwarding rate = the number of Gigabit ports * 1.488 Mpps + 100 Mpps * 0.1488 Mpps + the number of other types of ports * corresponding calculation method. If this rate can be less than the nominal Layer 2 packet forwarding rate, the switch can achieve line speed when doing Layer 2 switch.
3) Layer 3 Packet Forwarding Speed
Layer 3 packet forwarding rate = number of Gigabit ports * 1.488 Mpps + number of 100 Mpps * 0.1488 Mpps + number of other types of ports * corresponding calculation method. If this rate can be less than the nominal three-layer packet forwarding rate, then the switch can achieve line speed when doing Layer 3 switching.
So how did 1.488 Mpps get it?
Packet forwarding speed is measured by the number of 64 byte packets per unit time. For Gigabit Ethernet, the calculation method is as follows: 1,000,000,000 bps/8 bit/(64+8+12) byte=1,488,095 pps. It is shown that when the frame size of Ethernet is 64 byte, the fixed overhead of 8 byte frame head and 12 byte frame gap should be considered. Therefore, the packet forwarding rate of a Gigabit Ethernet port with line speed is 1.488 Mpps when forwarding 64 byte packets. Fast Ethernet's line-speed port packet forwarding rate is exactly one tenth of Gigabit Ethernet's, 148.8 kpps.
* For 10 Gigabit ethernet, the packet forwarding rate of a line-speed port is 14.88 Mpps.
* For Gigabit Ethernet, the packet forwarding rate of a wire-speed port is 1.488 Mpps.
* For fast ethernet, the packet forwarding rate of a line-speed port is 0.1488 Mpps.
* For the POS port of OC-12, the packet forwarding rate of a line-speed port is 1.17Mpps.
* For the POS port of OC-48, the packet forwarding rate of a line-speed port is 468 MppS.
So, if we can satisfy the above three conditions, then we can say that this switch really achieves linear non-blocking.
The utilization of backplane bandwidth resources is closely related to the internal structure of switches. At present, there are several main internal structures of switches: one is the shared memory structure, which relies on the central switching engine to provide high-performance full-port connections, and the core engine checks each input packet to determine the routing. This method requires a lot of memory bandwidth and high management costs, especially with the increase of switch ports, the price of central memory will be very high, so the switch core becomes the bottleneck of performance implementation; secondly, cross-bus structure, which can establish direct point-to-point connection between ports, which is for single-point transmission performance. Good, but not suitable for multi-point transmission; third, hybrid cross-bus structure, which is a hybrid cross-bus implementation, its design idea is to divide the integrated cross-bus matrix into small cross-matrix, and connect through a high-performance bus. Its advantage is to reduce the number of cross buses, reduce the cost and reduce bus contention, but the bus connecting the cross matrix becomes a new performance bottleneck.