jerrypeng commented on code in PR #52729:
URL: https://github.com/apache/spark/pull/52729#discussion_r2482862960
##########
connector/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaMicroBatchStream.scala:
##########
@@ -235,7 +345,25 @@ private[kafka010] class KafkaMicroBatchStream(
override def toString(): String = s"KafkaV2[$kafkaOffsetReader]"
override def metrics(latestConsumedOffset: Optional[Offset]): ju.Map[String,
String] = {
- KafkaMicroBatchStream.metrics(latestConsumedOffset, latestPartitionOffsets)
+ val reCalculatedLatestPartitionOffsets =
+ if (inRealTimeMode) {
+ if (!latestConsumedOffset.isPresent) {
+ // this means a batch has no end offsets, which should not happen
+ None
+ } else {
+ Some {
+ kafkaOffsetReader.fetchLatestOffsets(
+
Some(latestConsumedOffset.get.asInstanceOf[KafkaSourceOffset].partitionToOffsets))
+ }
+ }
+ } else {
+ // If we are in micro-batch mode, we need to get the latest partition
offsets at the
+ // start of the batch and recalculate the latest offsets at the end
for backlog
+ // estimation.
Review Comment:
Will revert this code based on this thread:
https://github.com/apache/spark/pull/52729/files#r2482113567
So this is not needed
--
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]
