|
|
Hi all
Our intention is to create a savepoint from the current prod pipeline (running on Flink 1.7.1) and bring up another one behind the scenes using this savepoint to avoid reprocessing of all data and create the local state again. It looks like it's technically possible but we're unsure about the isolation between the two instances once this idle one is up. More precisely our concern is that there are lot of hardcoded paths, configuration parameters in the savepoint files and we'd like to ensure that none them (e.g kafka topics, dbs, state location) will be used in the newly loaded app.
Is this a real concern? If yes how to overcome it?
Thanks Peter
|
Locked
