Techniques are disclosed for monitoring the performance of transient virtual volumes created for a virtual machine. Each transient virtual volume is created in response to a first trigger event, used by the virtualization environment solely to perform a single function supporting execution of the virtual machine, and deleted in response to a second trigger event. When creation of a current transient virtual volume is detected, and while the virtualization environment uses the current transient virtual volume to perform a single function supporting execution of the virtual machine, performance data is collected for the current transient virtual volume, and combined with performance data collected for at least one other, previously deleted transient virtual volume that was used solely to perform the same single function supporting execution of the same virtual machine. The combined performance data is represented as performance data for a single monitored virtual volume associated with the virtual machine.