Address auto-configuration is a key problem in data center networks, where servers and switches encode topology information into their addresses for routing. A recent work DAC has been introduced to address this problem. Without malfunctions, DAC can auto-configure all the devices quickly. But in case of malfunctions, DAC requires significant human efforts to correct malfunctions and it can cause substantial operation delay of the whole data center. In this paper, the authors further optimize address auto-configuration process even in the presence of malfunctions. Instead of waiting for all the malfunctions to be corrected, they could first configure the devices that are not involved in malfunctions and let them work first.