LinMingQiang commented on code in PR #100:
URL:
https://github.com/apache/flink-connector-kafka/pull/100#discussion_r1600879571
##########
flink-connector-kafka/src/main/java/org/apache/flink/connector/kafka/source/reader/KafkaPartitionSplitReader.java:
##########
@@ -122,27 +122,21 @@ public RecordsWithSplitIds<ConsumerRecord<byte[],
byte[]>> fetch() throws IOExce
KafkaPartitionSplitRecords recordsBySplits =
new KafkaPartitionSplitRecords(consumerRecords,
kafkaSourceReaderMetrics);
List<TopicPartition> finishedPartitions = new ArrayList<>();
- for (TopicPartition tp : consumerRecords.partitions()) {
+ for (TopicPartition tp : consumer.assignment()) {
long stoppingOffset = getStoppingOffset(tp);
- final List<ConsumerRecord<byte[], byte[]>> recordsFromPartition =
- consumerRecords.records(tp);
-
- if (recordsFromPartition.size() > 0) {
- final ConsumerRecord<byte[], byte[]> lastRecord =
- recordsFromPartition.get(recordsFromPartition.size() -
1);
-
- // After processing a record with offset of "stoppingOffset -
1", the split reader
- // should not continue fetching because the record with
stoppingOffset may not
- // exist. Keep polling will just block forever.
- if (lastRecord.offset() >= stoppingOffset - 1) {
- recordsBySplits.setPartitionStoppingOffset(tp,
stoppingOffset);
- finishSplitAtRecord(
- tp,
- stoppingOffset,
- lastRecord.offset(),
- finishedPartitions,
- recordsBySplits);
- }
+ long consumerPosition = consumer.position(tp);
+ // Stop fetching when the consumer's position reaches the
stoppingOffset.
+ // Control messages may follow the last record; therefore, using
the last record's
+ // offset as a stopping condition could result in indefinite
blocking.
+ if (consumerPosition >= stoppingOffset) {
+ LOG.debug(
+ "Position of {}: {}, has reached stopping offset: {}",
+ tp,
+ consumerPosition,
+ stoppingOffset);
+ recordsBySplits.setPartitionStoppingOffset(tp, stoppingOffset);
+ finishSplitAtRecord(
+ tp, stoppingOffset, consumerPosition,
finishedPartitions, recordsBySplits);
}
// Track this partition's record lag if it never appears before
kafkaSourceReaderMetrics.maybeAddRecordsLagMetric(consumer, tp);
Review Comment:
we do not need to track tp when consumerRecords is empty.
--
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]
