Abacn commented on code in PR #27702:
URL: https://github.com/apache/beam/pull/27702#discussion_r1276622056
##########
sdks/java/io/kafka/src/main/java/org/apache/beam/sdk/io/kafka/ReadFromKafkaDoFn.java:
##########
@@ -311,17 +324,26 @@ public OffsetRangeTracker restrictionTracker(
if (restriction.getTo() < Long.MAX_VALUE) {
return new OffsetRangeTracker(restriction);
}
- Map<String, Object> updatedConsumerConfig =
- overrideBootstrapServersConfig(consumerConfig, kafkaSourceDescriptor);
- KafkaLatestOffsetEstimator offsetPoller =
- new KafkaLatestOffsetEstimator(
- consumerFactoryFn.apply(
- KafkaIOUtils.getOffsetConsumerConfig(
- "tracker-" + kafkaSourceDescriptor.getTopicPartition(),
- offsetConsumerConfig,
- updatedConsumerConfig)),
- kafkaSourceDescriptor.getTopicPartition());
- return new GrowableOffsetRangeTracker(restriction.getFrom(), offsetPoller);
+ final Map<TopicPartition, KafkaLatestOffsetEstimator>
offsetEstimatorCacheInstance =
+ Preconditions.checkStateNotNull(this.offsetEstimatorCache);
+
+ TopicPartition topicPartition = kafkaSourceDescriptor.getTopicPartition();
+ KafkaLatestOffsetEstimator offsetEstimator =
offsetEstimatorCacheInstance.get(topicPartition);
+ if (offsetEstimator == null || offsetEstimator.isClosed()) {
Review Comment:
Consider add some comments about why caching approach is 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]
