maropu commented on a change in pull request #27246:
URL: https://github.com/apache/spark/pull/27246#discussion_r444569786
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/ExternalAppendOnlyUnsafeRowArrayBenchmark.scala
##########
@@ -182,6 +182,47 @@ object ExternalAppendOnlyUnsafeRowArrayBenchmark extends
BenchmarkBase {
}
}
+ def testAgainstUnsafeSorterSpillReader(
+ numSpillThreshold: Int,
+ numRows: Int,
+ numIterators: Int,
+ iterations: Int): Unit = {
+ val rows = testRows(numRows)
+ val benchmark = new Benchmark(s"Spilling SpillReader with $numRows rows",
iterations * numRows,
+ output = output)
+
+ benchmark.addCase("UnsafeSorterSpillReader_bufferSize1024") { _: Int =>
+ val array = UnsafeExternalSorter.create(
+ TaskContext.get().taskMemoryManager(),
+ SparkEnv.get.blockManager,
+ SparkEnv.get.serializerManager,
+ TaskContext.get(),
+ null,
+ null,
+ 1024,
+ SparkEnv.get.memoryManager.pageSizeBytes,
+ numSpillThreshold,
+ false)
+
+ rows.foreach(x =>
+ array.insertRecord(
+ x.getBaseObject,
+ x.getBaseOffset,
+ x.getSizeInBytes,
+ 0,
+ false))
+
+ for (_ <- 0L until numIterators) {
Review comment:
What's a difference with the existing benchmark code? If its almost the
same, just re-running them for updating the benchmark numbers looks okay.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
