curcur commented on pull request #15823: URL: https://github.com/apache/flink/pull/15823#issuecomment-834137001
Let's sync up offline? 1. what causes the job to have more than 200 connections, with parallelism = 4? 2. If we have too many connections for the preparing state(uncommitted), can we slow down the source pace? 3. Should we set up an upper limit for connection pool size? 4. Why "Prevent sources from waiting on cancellation" would help to reduce the connection in this case? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
