Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/19816#discussion_r153000843 --- Diff: R/pkg/tests/fulltests/test_sparkSQL.R --- @@ -3021,41 +3021,54 @@ test_that("dapplyCollect() on DataFrame with a binary column", { }) test_that("repartition by columns on DataFrame", { - df <- createDataFrame( --- End diff -- Actual diff is: ```R # The tasks here launch R workers with shuffles. So, we decrease the number of shuffle # partitions to reduce the number of the tasks to speed up the test. This is particularly # slow on Windows because the R workers are unable to be forked. See also SPARK-21693. conf <- callJMethod(sparkSession, "conf") value <- callJMethod(conf, "get", "spark.sql.shuffle.partitions") callJMethod(conf, "set", "spark.sql.shuffle.partitions", "5") tryCatch({ ... }, finally = { # Resetting the conf back to default value callJMethod(conf, "set", "spark.sql.shuffle.partitions", value) }) ```
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org