Yeah this is a good one to discuss.
Current send will block in two conditions:
1. You are beginning a new data batch and have run out of buffer memory and
block.on.buffer.full=true
2. Regardless of block.on.buffer.full the first request for each topic will
block on fetching metadata that contains
I think we have discussed this issue before but I just want to bring it up
again to get confirmed.
Currently when the send() call is triggered, first of all the cluster
information will be fetched for the specified topic, and if such
information is not available yet the send call will block on ref
