Skip to content

[SPARK-19859][SS]The new watermark should override the old one #17199

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zsxwing wants to merge 1 commit into from
Closed

[SPARK-19859][SS]The new watermark should override the old one #17199

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions ...alyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/EventTimeWatermark.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,13 @@ case class EventTimeWatermark(
.putLong(EventTimeWatermark.delayKey, delay.milliseconds)
.build()
a.withMetadata(updatedMetadata)
} else if (a.metadata.contains(EventTimeWatermark.delayKey)) {
// Remove existing watermark
val updatedMetadata = new MetadataBuilder()
.withMetadata(a.metadata)
.remove(EventTimeWatermark.delayKey)
.build()
a.withMetadata(updatedMetadata)
} else {
a
}
Expand Down
14 changes: 14 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/streaming/EventTimeWatermarkSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ import org.scalatest.BeforeAndAfter

import org.apache.spark.internal.Logging
import org.apache.spark.sql.AnalysisException
import org.apache.spark.sql.catalyst.plans.logical.EventTimeWatermark
import org.apache.spark.sql.execution.streaming._
import org.apache.spark.sql.functions.{count, window}
import org.apache.spark.sql.streaming.OutputMode._
Expand Down Expand Up @@ -305,6 +306,19 @@ class EventTimeWatermarkSuite extends StreamTest with BeforeAndAfter with Loggin
)
}

test("the new watermark should override the old one") {
val df = MemoryStream[(Long, Long)].toDF()
.withColumn("first", $"_1".cast("timestamp"))
.withColumn("second", $"_2".cast("timestamp"))
.withWatermark("first", "1 minute")
.withWatermark("second", "2 minutes")

val eventTimeColumns = df.logicalPlan.output
.filter(_.metadata.contains(EventTimeWatermark.delayKey))
assert(eventTimeColumns.size === 1)
assert(eventTimeColumns(0).name === "second")
}

private def assertNumStateRows(numTotalRows: Long): AssertOnQuery = AssertOnQuery { q =>
val progressWithData = q.recentProgress.filter(_.numInputRows > 0).lastOption.get
assert(progressWithData.stateOperators(0).numRowsTotal === numTotalRows)
Expand Down