A voxel in MRI often contains tissue as well as cerebrospinal fluid (CSF). During functional stimulation, volume fractions of these different water compartments may change. To directly image the CSF volume fraction and measure its functional change, we utilized a rotating-frame longitudinal relaxation time (T(1rho))-weighted MRI technique. At 9.4T with a spin-locking frequency of approximately 500Hz, T(1rho) of tissue water and CSF are about 48 and 450ms, respectively. Therefore, the parenchyma signal becomes negligible when a long spin-locking time (e.g., 200ms) is applied, leaving only the CSF signal. Baseline CSF volume fraction (V(csf)) and its change induced by visual stimulation were mapped in isoflurane-anesthetized cats (n=6). In both T(1rho)-weighted fMRI with spin locking times of 200 and 300ms, negative changes with similar magnitudes were observed, indicating that a decrease in V(csf) is a dominant contributor. In the region with voxels containing the visual cortex and CSF compartments, an average baseline V(csf) was 24.6+/-2%, an average CSF volume fraction change (DeltaV(csf)/V(csf)) was -2.45+/-0.6%, and an absolute change in CSF volume fraction (DeltaV(csf)) was -0.6+/-0.15%. A negative correlation was observed between pixel-wise baseline V(csf) and DeltaV(csf)/V(csf), which can be explained by similar DeltaV(csf) among voxels. Our results suggest that the functional reduction of CSF volume fraction could contribute to fMRI signals, especially when the tissue signal is significantly reduced as compared to the CSF with certain experimental techniques or parameters.