hi Flink community,
is there a document about NUMA scheduling for Flink? What are the NUMA related optimization or features shipped in Flink?
The best I can find is the following, which does not cover about what are the operators can benefit from NUMA scheduling (e.g. example of FlinkSQL queries or a query plan which can benefit from NUMA scheduling)
https://issues.apache.org/jira/browse/FLINK-3163