maropu commented on a change in pull request #22324: [SPARK-25237][SQL] Remove
updateBytesReadWithFileSize in FileScanRDD
URL: https://github.com/apache/spark/pull/22324#discussion_r361395422
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/FileBasedDataSourceSuite.scala
##########
@@ -473,6 +476,27 @@ class FileBasedDataSourceSuite extends QueryTest with
SharedSQLContext with Befo
}
}
}
+
+ test("SPARK-25237 compute correct input metrics in FileScanRDD") {
+ withTempPath { p =>
+ val path = p.getAbsolutePath
+ spark.range(1000).repartition(1).write.csv(path)
+ val bytesReads = new mutable.ArrayBuffer[Long]()
+ val bytesReadListener = new SparkListener() {
+ override def onTaskEnd(taskEnd: SparkListenerTaskEnd) {
+ bytesReads += taskEnd.taskMetrics.inputMetrics.bytesRead
+ }
+ }
+ sparkContext.addSparkListener(bytesReadListener)
+ try {
+ spark.read.csv(path).limit(1).collect()
+ sparkContext.listenerBus.waitUntilEmpty(1000L)
+ assert(bytesReads.sum === 7860)
Review comment:
Ah, I see. Can you make a pr to fix that?
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
