Github user rdblue commented on the issue: https://github.com/apache/spark/pull/21558 Yes, I just checked and speculative attempts do get a different TID. Just turn on speculation, run a large stage, and sort tasks in a stage by TID. There aren't duplicates.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org