Ethernet Packet Size 2.5 2000/08/02 2006/05/18 04:54:13.342 GMT-5 Don Johnson dhj@rice.edu Don Johnson dhj@rice.edu Indra Neel Datta kashent@alumni.rice.edu capacity ethernet packet size (Blank Abstract) A subtle consideration in Ethernet is the minimum packet size P min . The time required to transmit such packets equals P min C , where C is the Ethernet's capacity in bps. Ethernet now comes in two different types, each with individual specifications, the most distinguishing of which is capacity: 10 Mbps and 100 Mbps. If the minimum transmission time is such that the beginning of the packet has not propagated the full length of the Ethernet before the end-of-transmission, it is possible that two computers will begin transmission at the same time and, by the time their transmissions cease, the other's packet will not have propagated to the other. In this case, computers in-between the two will sense a collision, which renders both computer's transmissions senseless to them, without the two transmitting computers knowing a collision has occurred at all! For Ethernet to succeed, we must have the minimum packet transmission time exceed twice the voltage propagation time. P min C 2 L c or P min 2 L C c Thus, for the 10 Mbps Ethernet having a 1 km maximum length specification, the minimum packet size is about 70 bits. The 100 Mbps Ethernet was designed more recently than the 10 Mbps alternative. To maintain the same minimum packet size as the earlier, slower version, what should its length specification be? Why should the minimum packet size remain the same? The cable must be a factor of ten shorter: It cannot exceed 100 m. Different minimum packet sizes means different packet formats, making connecting old and new systems together more complex than need be.