Hi experts, I am running flink 1.10, the flink job is stateless. I am trying to understand how local buffer pool works:
1. lets say taskA and taskB both run in the same TM JVM, each task will have its own local buffer pool, and taskA will write to pool-A, and taskB will read from pool-A and write to pool-b, if taskB consume slower from pool-A than taskA writes to it, it will cause backpressure. 2. If the above assumption is correct, then this works when taskA and taskB is not chained together, if chained, there is no buffer in between, the StreamRecord will be directly passed from taskA to taskB? 3. what is the configuration parameter for this local buffer pool? and what is the relationship between local buffer pool with network buffer pool? 4. is the configuration for the total local buffer per TM? and is it evenly spread between tasks? Thanks a lot! Eleanore
