Re: packet error rate

Walter Roberson wrote:
In article <1139380314.818253.132610@xxxxxxxxxxxxxxxxxxxxxxxxxxxx>,
fangyong.F@xxxxxxxxx <fangyong.F@xxxxxxxxx> wrote:

For analysing the quality of firewall, I want to collect network
statistic data and calculate packet error rate(PER). But I don't know
the threshold of PER which means the network becoming bad.

Ethernet is, if I recall correctly, designed for an error rate
of around 1 in 1E10 bits (10,000,000,000 bits) -- which is around
11 seconds of transmissions at gigabit rates and less than 2 minutes
at 100 megabits. (Remember that the rate applies to -all- bits
transmitted, not just payload, and not just those involved
in any one TCP connection.)

Ethernet is a uncontrolled, contention network -- the writing of packets takes place without looking to see if the link is already busy. This generates "collision" which must be retried. When the link is running at ~70% utilization, these collisions will start to occur more frequently, and thus generate more retries. This is *not* considered an *error* case and will not show up as PERs.

Jeff B (remove the No-Spam to reply)