Virtual machine localization in a distributed fault-tolerant system. Network traffic is minimized between nodes, while maintaining fault-tolerant behavior. Communication is measured between VM's, which are moved to minimize real network use. An availability group defines which resources cannot safely be disposed on a single device. When two VM's are in the same availability group, they are disposed as near as practical, but not on the same device. VM's and other resources they use are also disposed to minimize real network use. Minimizing real network use includes minimizing both channels occupied and communication distance. Availability groups can include both “hard” availability groups, for which data could be irretrievably lost, or “soft” availability groups, for which data could be lost, but could still be recovered with difficulty. Resource localization responds to both distance between VM's and their resources, and risk associated with losing data.