I found this interesting behavior while running some adhoc analysis query. I have a Spark SQL query where I am joining 2 tables and then performing a count operation. In the Spark Web UI, I see there are 4 Stages getting launched.
The interesting behavior I see here is that I see the result before all stages are executed. The Stage 2 which performs the Sort merge join is running but I see the result in the Spark Shell before the completion of Stage 2. However, the application still continues to run? Any thoughts on this behavior? -- Sent from: http://apache-spark-developers-list.1001551.n3.nabble.com/ --------------------------------------------------------------------- To unsubscribe e-mail: dev-unsubscr...@spark.apache.org