Details
-
Improvement
-
Status: Resolved
-
Major
-
Resolution: Invalid
-
2.0.0
-
None
-
None
-
We have more than two hundred high-performance machine to handle more than 2T data by one query
Description
If a job have more then one hundred thousand tasks and spark.speculation is true, when speculable tasks start, choosing a speculable will waste lots of time and block other tasks. We do a ad-hoc query for data analyse, we can't tolerate one job wasting time even it is a large job