Fairness measure

From Wikipedia, the free encyclopedia

Fairness measures or metrics are used in network engineering to determine whether users or applications are receiving a fair share of system resources. There are several mathematical and conceptual definitions of fairness.

[edit] TCP fairness

Congestion control mechanisms for new network transmission protocols or peer to peer applications must interact well with TCP. TCP fairness requires that a new protocol receive no larger share of the network than a comparable TCP flow. This is important as TCP is the dominant transport protocol on the Internet, and if new protocols acquire unfair capacity they tend to cause problems such as congestion collapse. This was the case with the first versions of RealMedia's streaming protocol: it was based on UDP and was widely blocked at organizational firewalls until a TCP-based version was developed[citation needed].

[edit] Jain's fairness index

Jain's equation,

fairness =\frac{( \sum x_i )^2 }{(n \cdot \sum x_i^2 )} .

rates the fairness of a set of values. The result ranges from 1/n (worst case) to 1 (best case). This metric identifies underutilized channels and is not unduly sensitive to atypical network flow patterns.[1]

[edit] Max-min fairness

Main article: Max-min fairness

Max-min fairness states that small flows receive what they demand and larger flows share the remaining capacity equally. Bandwidth is allocated equally to all flows until one is satisfied, then bandwidth is equally increased among the remainder and so on until all flows are satisfied or bandwidth is exhausted.

[edit] Notes

  1. ^ Jain, R., Chiu, D.M., and Hawe, W. (1984) A Quantitative Measure of Fairness and Discrimination for Resource Allocation in Shared Systems. DEC Research Report TR-301

[edit] Further reading

  • Almeida, A.; Casetti, C.; Ouslati, S.; Avratchenkov, K. & Johansson, M. A Taxonomy of Congestion Control (in deliverable No: D.WP.JR.2.1.1) EuroNGI, 2004