之前一直有个疑问,如果consumer.setStartFromLatest()以及kafkaProperties.put("auto.offset.reset", "earliest")同时存在,究竟哪一个会起作用,答案肯定是consumer.setStartFromLatest(),为什么呢?我们一起来看一下
@Override
public void open(Configuration configuration) throws Exception {
// determine the offset commit mode,区分ON_CHECKPOINTS、DISABLED or KAFKA_PERIODIC,本文主要针对ON_CHECKPOINTS
this.offsetCommitMode = OffsetCommitModes.fromConfiguration(
getIsAutoCommitEnabled(),
enableCommitOnCheckpoints,
((StreamingRuntimeContext) getRuntimeContext()).isCheckpointingEnabled());
// create the kafka partition discoverer
this.partitionDiscoverer = createPartitionDiscoverer(
topicsDescriptor,
getRuntimeContext().getIndexOfThisSubtask(),
getRuntimeContext().getNumberOfParallelSubtasks());
this.partitionDiscoverer.open();
subscribedPartitionsToStartOffsets = new HashMap<>();
//获取fixed topic's or topic pattern 's partitions of this subtask
final List<KafkaTopicPartition> allPartitions = partitionDiscoverer.discoverPartitions();
//从checkpoint中恢复
if (restoredState != null) {
for (KafkaTopicPartition partition : allPartitions) {
//新的分区(未曾在checkpoint中的分区将从earliest offset 开始消费),old partition已经从checkpoint中恢复了,并且已经保存在subscribedPartitionsToStartOffsets
if (!restoredState.containsKey(partition)) {
restoredState.put(partition, KafkaTopicPartitionStateSentinel.EARLIEST_OFFSET);
}
}
for (Map.Entry<KafkaTopicPartition, Long> restoredStateEntry : restoredState.entrySet()) {
if (!restoredFromOldState) {
// seed the partition discoverer with the union state while filtering out
// restored partitions that should not be subscribed by this subtask
if (KafkaTopicPartitionAssigner.assign(
restoredStateEntry.getKey(), getRuntimeContext().getNumberOfParallelSubtasks())
== getRuntimeContext().getIndexOfThisSubtask()){
subscribedPartitionsToStartOffsets.put(restoredStateEntry.getKey(), restoredStateEntry.getValue());
}
} else {
// when restoring from older 1.1 / 1.2 state, the restored state would not be the union state;
// in this case, just use the restored state as the subscribed partitions
subscribedPartitionsToStartOffsets.put(restoredStateEntry.getKey(), restoredStateEntry.getValue());
}
}
if (filterRestoredPartitionsWithCurrentTopicsDescriptor) {
subscribedPartitionsToStartOffsets.entrySet().removeIf(entry -> {
if (!topicsDescriptor.isMatchingTopic(entry.getKey().getTopic())) {
LOG.warn(
"{} is removed from subscribed partitions since it is no longer associated with topics descriptor of current execution.",
entry.getKey());
return true;
}
return false;
});
}
LOG.info("Consumer subtask {} will start reading {} partitions with offsets in restored state: {}",
getRuntimeContext().getIndexOfThisSubtask(), subscribedPartitionsToStartOffsets.size(), subscribedPartitionsToStartOffsets);
} else {
// use the partition discoverer to fetch the initial seed partitions,
// and set their initial offsets depending on the startup mode.
// for SPECIFIC_OFFSETS and TIMESTAMP modes, we set the specific offsets now;
// for other modes (EARLIEST, LATEST, and GROUP_OFFSETS), the offset is lazily determined
// when the partition is actually read.
switch (startupMode) {
case SPECIFIC_OFFSETS:
if (specificStartupOffsets == null) {
throw new IllegalStateException(
"Startup mode for the consumer set to " + StartupMode.SPECIFIC_OFFSETS +
", but no specific offsets were specified.");
}
for (KafkaTopicPartition seedPartition : allPartitions) {
//指定partition的offset,从指定的offset卡开始,未指定的从group_offset开始
Long specificOffset = specificStartupOffsets.get(seedPartition);
if (specificOffset != null) {
// since the specified offsets represent the next record to read, we subtract
// it by one so that the initial state of the consumer will be correct
subscribedPartitionsToStartOffsets.put(seedPartition, specificOffset - 1);
} else {
// default to group offset behaviour if the user-provided specific offsets
// do not contain a value for this partition
//对应的startupMode也存储到 subscribedPartitionsToStartOffsets中
subscribedPartitionsToStartOffsets.put(seedPartition