This paper has analyzed the existent measures of uncertainty based on covering rough sets. It is revealed that they all bear some irrationality under specified situations. Here a concept of relative knowledge granularities based on covering rough sets is defined. And we propose an uncertainty measure of covering rough sets based on knowledge granularities and prove its relevant properties. Analysis has proven that the uncertainty measuring approach overcomes the irrationality of former approaches, so it provides a new method for measuring the uncertainty of covering rough sets.