vkorukanti commented on a change in pull request #33091:
URL: https://github.com/apache/spark/pull/33091#discussion_r661073820
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateSuite.scala
##########
@@ -1122,6 +1106,43 @@ class FlatMapGroupsWithStateSuite extends
StateStoreMetricsTest {
spark.createDataset(Seq(("a", 2), ("b", 1))).toDF)
}
+ test("SPARK-35896: metrics in StateOperatorProgress are output correctly") {
+ val inputData = MemoryStream[(String, Int)]
+ val result =
+ inputData.toDS
+ .select($"_1".as("key"), timestamp_seconds($"_2").as("eventTime"))
+ .withWatermark("eventTime", "10 seconds")
+ .as[(String, Long)]
+ .groupByKey(_._1)
+ .flatMapGroupsWithState(Update, EventTimeTimeout)(sampleTestFunction)
+
+ testStream(result, Update)(
+ StartStream(additionalConfs = Map(SQLConf.SHUFFLE_PARTITIONS.key ->
"3")),
+
+ AddData(inputData, ("a", 11), ("a", 13), ("a", 15)),
+ // Max event time = 15. Timeout timestamp for "a" = 15 + 5 = 20.
Watermark = 15 - 10 = 5.
+ CheckNewAnswer(("a", 15)), // Output = max event time of a
+ assertNumStateRows(
+ total = Seq(1), updated = Seq(1), droppedByWatermark = Seq(0), removed
= Some(Seq(0))),
+
+ AddData(inputData, ("a", 4)), // Add data older than watermark for
"a"
+ CheckNewAnswer(), // No output as data should get
filtered by watermark
+ assertStateOperatorProgressMetric(
Review comment:
Got it. Renamed it to `numStateStoreInstances`.
--
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]
