Chasing errors through the network stack: a testbed for investigating errors in real traffic on optical networks

Abstract

Abstract-A testbed is described which allows both physical layer errors to be observed and analysed, as well as monitoring network performance via frame loss. Real network traffic loads can be used for testing, so that all measurements taken are representative of what would be seen in a deployed system. We illustrate our testbed with an examination of the behaviour of a well-known networking standard, Gigabit Ethernet, in conditions of reduced receiver power on optical fibre. Our testbed results show that the line codes used to represent the data in the network affect the bit error rate for that data. Along with the previously reported result that bit error rate and packet error rate have only a weakly deterministic relationship, this highlights the need for testing of all network layers within a complete system carrying real world traffic.

Performance Trade-Offs for Wavelength Striping Optical Switching Using a Novel Star Architecture

“…The 64B/66B scrambling, which is one-toone mapping of the data stream, provides data whitening. Such data whitening is intended to spread out erroneous data in the transmission [19]. The wavelengths were uniformly distributed from 1 = 1550.71 nm to 10 = 1554.33 nm and were spaced 0.4 nm (50 GHz) apart.…”

Alternatives for In-Service BER Estimation in All-Optical Networks: Towards Minimum Intrusion

“…• Solution: Equation 4 illustrates how the coding scheme affects the way in which bit errors on the physical layer propagate up the network stack. That is, both the errors occurring on an optical channel and the protection scheme applied have an impact on the PER for the packets transmitted over that channel, as shown in [17]. In a low power regime, [18] shows that 8B/10B block-coding causes a nondeterministic relationship between PER and BER in optical GigE packets.…”