In data communications, cut-through switching is a method of switching data frame or data packets, where the switching device (bridge or switch) forwards the frames or packets as soon as the destination address is available without waiting for the rest of the data to arrive.
Cut-through switching is used in packet switching systems. In packet-switching, the message is divided into a number of units called packets that are individually routed from the source to the destination. There is no need to establish a dedicated circuit for communication, since it is a connectionless network switching technique.
In cut − through switching, when the data frame or a packet starts arriving at a bridge or a switch, data transmission can start as soon as destination address field has arrived. The switch performs a look – up at the address table stored in it to check whether the destination address is valid. If the address is valid and the outgoing link is available, the switching device immediately starts to transmit the frame to the destination port, even before rest of the frame has arrived.
Here, the switching device acts as mere forwarder of frames. As the total frame is not yet available, it cannot perform error checks when it starts forwarding. It depends upon the on the destination devices for error handling.
The advantages of cut-through switching are −
Cut-through switching is mainly used for communications via fiber channel. It is also used for SCSI traffic for the low latency transmission.