Abstract: A method for execution by a dispersed storage and task (DST) execution unit identifying a failing memory device based on memory device diagnostic data. A cloning task is executed by designating memory of a replacement memory device to store encoded slices stored in the failing memory device, where the cloning task is executed over a cloning duration time period. A write request is received via a network at a receiving time during the cloning duration time period that includes a new encoded slice, and the new encoded slice is assigned to a temporary memory device for storage based on an identifier of the new encoded. The new encoded slice is transferred from the temporary memory device to the replacement memory device in response to an elapsing of the cloning duration time period corresponding to completion of the execution of the cloning task.

Abstract: Based on a detected data transfer instruction, a computing device within a dispersed storage network (DSN) determines a data transfer synchronization protocol that substantially maintains synchronization of at least the write threshold number of first associated slices (e.g., a first row of encoded data slices) to be transferred from the first set of storage units (SUs) to a second set of SUs based on a substantially same first transfer rate and substantially maintains synchronization of at least the write threshold number of second associated slices (e.g., a second row of encoded data slices) to be transferred from the first set of SUs to the second set of SUs based on a substantially same second transfer rate. The computing device then executes the data transfer synchronization protocol to perform substantially synchronized transfer of respective sets of the plurality of sets of encoded data slices from the first set of SUs to the second set of SUs.