Skip to content

[HUDI-596] Close KafkaConsumer every time after we use it #1303

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vinothchandar merged 1 commit into from
Feb 4, 2020
Merged

[HUDI-596] Close KafkaConsumer every time after we use it #1303

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
50 changes: 26 additions & 24 deletions hudi-utilities/src/main/java/org/apache/hudi/utilities/sources/helpers/KafkaOffsetGen.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -172,33 +172,35 @@ public KafkaOffsetGen(TypedProperties props) {
public OffsetRange[] getNextOffsetRanges(Option<String> lastCheckpointStr, long sourceLimit) {

// Obtain current metadata for the topic
KafkaConsumer consumer = new KafkaConsumer(kafkaParams);
List<PartitionInfo> partitionInfoList;
partitionInfoList = consumer.partitionsFor(topicName);
Set<TopicPartition> topicPartitions = partitionInfoList.stream()
.map(x -> new TopicPartition(x.topic(), x.partition())).collect(Collectors.toSet());

// Determine the offset ranges to read from
Map<TopicPartition, Long> fromOffsets;
if (lastCheckpointStr.isPresent()) {
fromOffsets = checkupValidOffsets(consumer, lastCheckpointStr, topicPartitions);
} else {
KafkaResetOffsetStrategies autoResetValue = KafkaResetOffsetStrategies
.valueOf(props.getString("auto.offset.reset", Config.DEFAULT_AUTO_RESET_OFFSET.toString()).toUpperCase());
switch (autoResetValue) {
case EARLIEST:
fromOffsets = consumer.beginningOffsets(topicPartitions);
break;
case LATEST:
fromOffsets = consumer.endOffsets(topicPartitions);
break;
default:
throw new HoodieNotSupportedException("Auto reset value must be one of 'smallest' or 'largest' ");
Map<TopicPartition, Long> toOffsets;
try (KafkaConsumer consumer = new KafkaConsumer(kafkaParams)) {
List<PartitionInfo> partitionInfoList;
partitionInfoList = consumer.partitionsFor(topicName);
Set<TopicPartition> topicPartitions = partitionInfoList.stream()
.map(x -> new TopicPartition(x.topic(), x.partition())).collect(Collectors.toSet());

// Determine the offset ranges to read from
if (lastCheckpointStr.isPresent()) {
fromOffsets = checkupValidOffsets(consumer, lastCheckpointStr, topicPartitions);
} else {
KafkaResetOffsetStrategies autoResetValue = KafkaResetOffsetStrategies
.valueOf(props.getString("auto.offset.reset", Config.DEFAULT_AUTO_RESET_OFFSET.toString()).toUpperCase());
switch (autoResetValue) {
case EARLIEST:
fromOffsets = consumer.beginningOffsets(topicPartitions);
break;
case LATEST:
fromOffsets = consumer.endOffsets(topicPartitions);
break;
default:
throw new HoodieNotSupportedException("Auto reset value must be one of 'smallest' or 'largest' ");
}
}
}

// Obtain the latest offsets.
Map<TopicPartition, Long> toOffsets = consumer.endOffsets(topicPartitions);
// Obtain the latest offsets.
toOffsets = consumer.endOffsets(topicPartitions);
}

// Come up with final set of OffsetRanges to read (account for new partitions, limit number of events)
long maxEventsToReadFromKafka = props.getLong(Config.MAX_EVENTS_FROM_KAFKA_SOURCE_PROP,
Expand Down