ueshin commented on a change in pull request #31367:
URL: https://github.com/apache/spark/pull/31367#discussion_r567030338
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/CoGroupedArrowPythonRunner.scala
##########
@@ -71,6 +83,9 @@ class CoGroupedArrowPythonRunner(
}
PythonUDFRunner.writeUDFs(dataOut, funcs, argOffsets)
+ val deltaTime = System.nanoTime()-startTime
+ pythonCodeSerializeTime += deltaTime
+ pythonCodeSent += dataOut.size()
Review comment:
ditto as https://github.com/apache/spark/pull/31367#discussion_r566439263
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonUDFRunner.scala
##########
@@ -46,12 +54,23 @@ class PythonUDFRunner(
new WriterThread(env, worker, inputIterator, partitionIndex, context) {
protected override def writeCommand(dataOut: DataOutputStream): Unit = {
+ val startTime = System.nanoTime()
PythonUDFRunner.writeUDFs(dataOut, funcs, argOffsets)
+ val deltaTime = System.nanoTime()-startTime
+ pythonCodeSerializeTime += deltaTime
+ pythonCodeSent += dataOut.size()
Review comment:
ditto.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/CoGroupedArrowPythonRunner.scala
##########
@@ -83,6 +98,7 @@ class CoGroupedArrowPythonRunner(
writeGroup(nextRight, rightSchema, dataOut, "right")
}
dataOut.writeInt(0)
+ pythonDataSent += dataOut.size()
Review comment:
ditto.
----------------------------------------------------------------
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]
