International Business Machines Corporation
Scalable and balanced distribution of asynchronous operations in data replication systems

Abstract:

A computer-implemented method, according to one embodiment, includes: receiving data replication operations from one or more compute nodes at a primary location, storing the received data replication operations in a queue, and dividing the queued data replication operations into a number of independent sub-groups. The number of independent sub-groups is equal to or less than a number of worker gateway nodes. Each of the independent sub-groups are further added to a respective one of the worker gateway nodes. One or more instructions are also sent to each of the worker gateway nodes to send the data replication operations included in the respective independent sub-group to a remote storage location. Other systems, methods, and computer program products are described in additional embodiments.