Amazon.com, Inc.
Node placement for replication groups

Abstract:

Data replication groups may be used to store data in a distributed computing environment. A data replication group may include a set of nodes executing a consensus protocol to maintain data durably. In order to increase efficiency and performance of the data replication group a placement system may be used to determine the placement of node of the data replication groups. The nodes may be executed by a set of host computer systems within a distributed computing environment. The placement system may determine the placement of the nodes within the set of host computer systems based at least in part on one or more constraints. A selection algorithm may be used to determine a set of node for a data replication group satisfying the one or more constraints.