Fairness is one of the most significant indicators to evaluate resource allocation algorithms in cloud computing, which reveals whether each user is allocated as much as that of all other users having the same identification number. In this paper the proposed system proposes Dynamic Evaluation Framework for Fairness (DEFF). DEFF is a framework to evaluate the fairness of an resource allocation algorithm. In this framework, two sub-models, Dynamic Demand Model (DDM) and Dynamic Node Model (DNM). These two models are proposed to describe the dynamic characteristics of resource demand and the computing node number under cloud computing environment. Combining Fairness on Dominant Shares and both Dynamic Demand Model (DDM) and Dynamic Node Model (DNM) , the system finally obtain Dynamic Evaluation Framework for Fairness. In this project to prove the effectiveness on fairness evaluation by using the DEFF framework the system adopt several typical resource allocation algorithms. The previous depicts resource demand of the nodes in each task phase, whereas the later gives a description to the variation of node number. With combination of DDM and DNM, the system obtain our evaluation model DEFF, which can better adapt the cloud environment.