maropu commented on a change in pull request #26109: [SPARK-29461][SQL] Measure
the number of records being updated for JDBC writer
URL: https://github.com/apache/spark/pull/26109#discussion_r337851846
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/jdbc/JDBCWriteSuite.scala
##########
@@ -543,4 +545,58 @@ class JDBCWriteSuite extends SharedSparkSession with
BeforeAndAfter {
}.getMessage
assert(errMsg.contains("Statement was canceled or the session timed out"))
}
+
+ test("metrics") {
+ val df = spark.createDataFrame(sparkContext.parallelize(arr2x2), schema2)
+ val df2 = spark.createDataFrame(sparkContext.parallelize(arr1x2), schema2)
+
+ runAndVerifyRecordsWritten(2) {
+ df.write.mode(SaveMode.Append).jdbc(url, "TEST.BASICCREATETEST", new
Properties())
+ }
+
+ runAndVerifyRecordsWritten(1) {
+ df2.write.mode(SaveMode.Overwrite).jdbc(url, "TEST.BASICCREATETEST", new
Properties())
+ }
+
+ runAndVerifyRecordsWritten(1) {
+ df2.write.mode(SaveMode.Overwrite).option("truncate", true)
+ .jdbc(url, "TEST.BASICCREATETEST", new Properties())
+ }
+
+ runAndVerifyRecordsWritten(0) {
+ intercept[AnalysisException] {
+ df2.write.mode(SaveMode.ErrorIfExists).jdbc(url,
"TEST.BASICCREATETEST", new Properties())
+ }
+ }
+
+ runAndVerifyRecordsWritten(0) {
+ df.write.mode(SaveMode.Ignore).jdbc(url, "TEST.BASICCREATETEST", new
Properties())
+ }
+ }
+
+ private def runAndVerifyRecordsWritten(expected: Long)(job: => Unit): Unit =
{
+ assert(expected === runAndReturnMetrics(job,
_.taskMetrics.outputMetrics.recordsWritten))
+ }
+
+ private def runAndReturnMetrics(job: => Unit, collector:
(SparkListenerTaskEnd) => Long): Long = {
+ val taskMetrics = new ArrayBuffer[Long]()
+
+ // Avoid receiving earlier taskEnd events
+ sparkContext.listenerBus.waitUntilEmpty()
+
+ val listener = new SparkListener() {
+ override def onTaskEnd(taskEnd: SparkListenerTaskEnd): Unit = {
+ taskMetrics += collector(taskEnd)
+ }
+ }
+ sparkContext.addSparkListener(listener)
+
+ job
+
+ sparkContext.listenerBus.waitUntilEmpty()
+
+ sparkContext.removeSparkListener(listener)
+ taskMetrics.sum
+ }
+
Review comment:
nit: remove this blank.
----------------------------------------------------------------
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]
