Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,12 @@ import org.apache.spark.unsafe.types.CalendarInterval
object EventTimeWatermark {
/** The [[org.apache.spark.sql.types.Metadata]] key used to hold the eventTime watermark delay. */
val delayKey = "spark.watermarkDelayMs"

def getDelayMs(delay: CalendarInterval): Long = {
// We define month as `31 days` to simplify calculation.
val millisPerMonth = CalendarInterval.MICROS_PER_DAY / 1000 * 31
delay.milliseconds + delay.months * millisPerMonth
}
}

/**
Expand All @@ -37,9 +43,10 @@ case class EventTimeWatermark(
// Update the metadata on the eventTime column to include the desired delay.
override val output: Seq[Attribute] = child.output.map { a =>
if (a semanticEquals eventTime) {
val delayMs = EventTimeWatermark.getDelayMs(delay)
val updatedMetadata = new MetadataBuilder()
.withMetadata(a.metadata)
.putLong(EventTimeWatermark.delayKey, delay.milliseconds)
.putLong(EventTimeWatermark.delayKey, delayMs)
.build()
a.withMetadata(updatedMetadata)
} else if (a.metadata.contains(EventTimeWatermark.delayKey)) {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -84,10 +84,7 @@ case class EventTimeWatermarkExec(
child: SparkPlan) extends SparkPlan {

val eventTimeStats = new EventTimeStatsAccum()
val delayMs = {
val millisPerMonth = CalendarInterval.MICROS_PER_DAY / 1000 * 31
delay.milliseconds + delay.months * millisPerMonth
}
val delayMs = EventTimeWatermark.getDelayMs(delay)

sparkContext.register(eventTimeStats)

Expand All @@ -105,10 +102,16 @@ case class EventTimeWatermarkExec(
override val output: Seq[Attribute] = child.output.map { a =>
if (a semanticEquals eventTime) {
val updatedMetadata = new MetadataBuilder()
.withMetadata(a.metadata)
.putLong(EventTimeWatermark.delayKey, delayMs)
.build()

.withMetadata(a.metadata)
.putLong(EventTimeWatermark.delayKey, delayMs)
.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