This paper investigates the practical issues in applying network tomography to monitor failures. We outline an approach for selecting paths to monitor, detecting and confirming the existence of a failure, correlating multiple independent observations into a single failure event, and applying existing binary networking tomography algorithms to identify failures. We evaluate the ability of network tomography algorithms to correctly detect and identify failures in a controlled environment on the VINI testbed. Categories and Subject Descriptors: C.2.3 [Network Operations]: Network monitoring C.2.3 [Network Operations]: Network management C.2.5 [Local and Wide-Area Network]: Internet General Terms: Experimentation, Management, Measurement, Reliability