Github user gczsjdy commented on a diff in the pull request: https://github.com/apache/spark/pull/19763#discussion_r152002860 --- Diff: core/src/main/scala/org/apache/spark/internal/config/package.scala --- @@ -485,4 +485,13 @@ package object config { "array in the sorter.") .intConf .createWithDefault(Integer.MAX_VALUE) + + private[spark] val SHUFFLE_MAP_OUTPUT_STATISTICS_PARALLEL_AGGREGATION_THRESHOLD = + ConfigBuilder("spark.shuffle.mapOutputStatistics.parallelAggregationThreshold") + .internal() + .doc("Multi-thread is used when the number of mappers * shuffle partitions exceeds this " + + "threshold") + .intConf + .createWithDefault(100000000) --- End diff -- Now I also think it's a little bit large... In the case I mentioned, the 5s gap is created by 10^8 of this value. Maybe 10^7 is good?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org