HyukjinKwon commented on a change in pull request #34594:
URL: https://github.com/apache/spark/pull/34594#discussion_r750811632
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/BloomFilterBenchmark.scala
##########
@@ -81,8 +80,55 @@ object BloomFilterBenchmark extends SqlBasedBenchmark {
}
}
+ private def writeParquetBenchmark(): Unit = {
+ withTempPath { dir =>
+ val path = dir.getCanonicalPath
+
+ runBenchmark(s"Parquet Write") {
Review comment:
```suggestion
runBenchmark("Parquet Write") {
```
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/benchmark/BloomFilterBenchmark.scala
##########
@@ -81,8 +80,55 @@ object BloomFilterBenchmark extends SqlBasedBenchmark {
}
}
+ private def writeParquetBenchmark(): Unit = {
+ withTempPath { dir =>
+ val path = dir.getCanonicalPath
+
+ runBenchmark(s"Parquet Write") {
+ val benchmark = new Benchmark(s"Write ${scaleFactor}M rows", N, output
= output)
+ benchmark.addCase("Without bloom filter") { _ =>
+ df.write.mode("overwrite").parquet(path + "/withoutBF")
+ }
+ benchmark.addCase("With bloom filter") { _ =>
+ df.write.mode("overwrite")
+ .option(ParquetOutputFormat.BLOOM_FILTER_ENABLED + "#value", true)
+ .parquet(path + "/withBF")
+ }
+ benchmark.run()
+ }
+ }
+ }
+
+ private def readParquetBenchmark(): Unit = {
+ val blockSizes = Seq(2 * 1024 * 1024, 4 * 1024 * 1024, 6 * 1024 * 1024, 8
* 1024 * 1024,
+ 12 * 1024 * 1024, 16 * 1024 * 1024, 32 * 1024 * 1024)
+ for (blocksize <- blockSizes) {
+ withTempPath { dir =>
+ val path = dir.getCanonicalPath
+ df.write.option("parquet.block.size", blocksize).parquet(path +
"/withoutBF")
+ df.write.option(ParquetOutputFormat.BLOOM_FILTER_ENABLED + "#value",
true)
+ .option("parquet.block.size", blocksize)
+ .parquet(path + "/withBF")
+
+ runBenchmark(s"Parquet Read") {
Review comment:
```suggestion
runBenchmark("Parquet Read") {
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
