Currently, the chunk cloning sequence is to first run _storeCurrentLocs to gather the recordIds of all documents in the chunk to be moved, so they can be sorted in the order on disk and then telling the recipient shard to start the initial clone.

The recipient shard's preparation for initial clone consists of several steps, including cleaning up the range for the chunk.

We should overlap these two stages.

This only applies to 3.4 and later.