In this paper, we introduce a network management system for autonomous service management that can be effectively utilized in emergency situations. In order to alleviate the problem of a shortage of human resources in disaster situations, approaches for autonomous service management are helpful. Such approaches require knowledge of maximum load capacity of managed server systems so that a benchmark test should be conducted to acquire knowledge. However, in a disaster recovery phase, a configuration of the server system changes frequently due to the occurrence of the secondary disaster or fluctuating user demand. Therefore, a benchmark technique should be established that can be applied even to running server systems. In our proposal, we describe a non-destructive benchmarking technique that can acquire knowledge of the maximum load capacity of the server system without imposing heavy load. A prototype system based on our proposal is designed and implemented for experiments. The results of the experiments confirm that the proposed system can stably operate a service by proactively controlling the amount of computing resource of the server system.