That depends on scheduling, but probably that would be true. Until the tuple
is sent across the wire its memory will be shared, as soon as it goes to a
different worker, the memory is duplicated.
- Bobby
On Saturday, April 11, 2015 8:39 PM, clay teahouse
<[email protected]> wrote:
Hi all,I have a simple question which probably has been asked before, but I
cannot find a concrete answer. I'd appreciate your feedback.
Assume I have a spout that emit tuples which are consumed by 4 different bolts .
Spout A ---> Bolt B ---> Bolt C ---> Bolt D
---> Bolt E
I have 4 works, each with one executor thread. I understand that there are
send and receive queues for sending and receiving tuples. Does this mean in
this scenario, the memory usage would be 4 times as if I had one spout and one
bolt (ignoring all other overheads)?
thanks,Clay
