Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/21603#discussion_r202286983 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala --- @@ -386,6 +386,17 @@ object SQLConf { .booleanConf .createWithDefault(true) + val PARQUET_FILTER_PUSHDOWN_INFILTERTHRESHOLD = + buildConf("spark.sql.parquet.pushdown.inFilterThreshold") + .doc("The maximum number of values to filter push-down optimization for IN predicate. " + + "Large threshold won't necessarily provide much better performance. " + + "The experiment argued that 300 is the limit threshold. " + + "This configuration only has an effect when 'spark.sql.parquet.filterPushdown' is enabled.") + .internal() + .intConf + .checkValue(threshold => threshold > 0, "The threshold must be greater than 0.") --- End diff -- Yup.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org