Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/21909#discussion_r206400571
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVBenchmarks.scala
---
@@ -119,8 +119,47 @@ object CSVBenchmarks {
}
}
+ def countBenchmark(rowsNum: Int): Unit = {
+ val colsNum = 10
+ val benchmark = new Benchmark(s"Count a dataset with $colsNum
columns", rowsNum)
+
+ withTempPath { path =>
+ val fields = Seq.tabulate(colsNum)(i => StructField(s"col$i",
IntegerType))
+ val schema = StructType(fields)
+
+ spark.range(rowsNum)
+ .select(Seq.tabulate(colsNum)(i => lit(i).as(s"col$i")): _*)
+ .write
+ .csv(path.getAbsolutePath)
+
+ val ds = spark.read.schema(schema).csv(path.getAbsolutePath)
+
+ benchmark.addCase(s"Select $colsNum columns + count()", 3) { _ =>
+ ds.select("*").filter((_: Row) => true).count()
+ }
+ benchmark.addCase(s"Select 1 column + count()", 3) { _ =>
+ ds.select($"col1").filter((_: Row) => true).count()
--- End diff --
does this benchmark result vary if we select `col2` or `col10`?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
