Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/16391#discussion_r93812042 --- Diff: sql/core/src/test/scala/org/apache/spark/sql/DatasetBenchmark.scala --- @@ -133,24 +134,29 @@ object DatasetBenchmark { def aggregate(spark: SparkSession, numRows: Long): Benchmark = { import spark.implicits._ - val df = spark.range(1, numRows).select($"id".as("l"), $"id".cast(StringType).as("s")) + val rdd = spark.sparkContext.range(0, numRows) + val ds = spark.range(0, numRows) + val df = ds.toDF("l") + val benchmark = new Benchmark("aggregate", numRows) - val rdd = spark.sparkContext.range(1, numRows).map(l => Data(l, l.toString)) benchmark.addCase("RDD sum") { iter => - rdd.aggregate(0L)(_ + _.l, _ + _) + rdd.map(l => (l % 10, l)).reduceByKey(_ + _).foreach(_ => Unit) --- End diff -- aggregate without grouping is not a common use case
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org