Github user zsxwing commented on a diff in the pull request:
https://github.com/apache/spark/pull/16258#discussion_r92087215
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/EventTimeWatermarkExec.scala
---
@@ -61,15 +83,14 @@ case class EventTimeWatermarkExec(
delay: CalendarInterval,
child: SparkPlan) extends SparkPlan {
- // TODO: Use Spark SQL Metrics?
- val maxEventTime = new MaxLong
- sparkContext.register(maxEventTime)
+ val eventTimeStats = new EventTimeStatsAccum()
+ sparkContext.register(eventTimeStats)
override protected def doExecute(): RDD[InternalRow] = {
child.execute().mapPartitions { iter =>
val getEventTime = UnsafeProjection.create(eventTime :: Nil,
child.output)
iter.map { row =>
- maxEventTime.add(getEventTime(row).getLong(0))
+ eventTimeStats.add((getEventTime(row).getLong(0).toDouble /
1000).toLong)
--- End diff --
nit: could be `getEventTime(row).getLong(0) / 1000`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
