Data center network acquisition symptom algorithm based on Hamiltonian Cycle

In the network, fault diagnosis includes two major phases: first the test result (symptom) is obtained through the test model; and second, the faulty node is determined by applying a diagnosis algorithm to the symptoms. In this paper, we mainly study the first stage, and an efficient algorithm based on Hamiltonian cycle---ASHC (acquiring symptom based on Hamiltonian cycle) is proposed, which mainly sends test data packets via Hamilton cycle to test each server and record the test results, then we use simple comparison models for test results to obtain test symptoms. The advantage of this algorithm is that the central server does not need to communicate with each server directly, so as to save system resources.