Cache memory is a critical resource for performance, and as is well known, faults in it can significantly impact processor efficiency. In our everyday life, in non-critical real-time applications, it is desirable for quality of service that performance remains high, and that the worst-case execution time is as close to the average as possible. In this paper, we demonstrate that neither disabling only the faulty cache sub-blocks [1] nor disabling entire blocks that contain at least one faulty sub-block [23] yields optimal results in terms of average performance and performance variance in faulty CPU caches. Instead, we show that selectively disabling blocks with more than N faulty sub-blocks, while disabling only the faulty sub-blocks in all other blocks, leads to better average performance and lower performance variance. The optimal value of N depends on both the fault percentage and the granularity of the sub-block.