Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19763#discussion_r152016336
--- Diff:
core/src/main/scala/org/apache/spark/internal/config/package.scala ---
@@ -485,4 +485,20 @@ 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(10000000)
+
+ private[spark] val SHUFFLE_MAP_OUTPUT_STATISTICS_CORES =
+ ConfigBuilder("spark.shuffle.mapOutputStatistics.cores")
--- End diff --
nit: `cores` -> `parallelism`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
