[FEATURE] Skip some servers if having multi servers for one partition #2535
Description
Code of Conduct
- I agree to follow this project's Code of Conduct
Search before asking
- I have searched in the issues and found no similar issues.
Describe the feature
If the partition reassign is activated, the single partition's data will be stored in the multi servers, that will make the client read side to retrieve these data from multi servers.
When the spark AQE is enabled and this job stage is optimized by the AQE rules, the task will skip the partial data from the mapId. For the LOAD_BALANCE mode of partition split, some mapIds data doesn't exist in some servers, we could skip it to speed up reading.
Motivation
No response
Describe the solution
No response
Additional context
No response
Are you willing to submit PR?
- Yes I am willing to submit a PR!