pvary commented on code in PR #10526:
URL: https://github.com/apache/iceberg/pull/10526#discussion_r1718186250
##########
flink/v1.19/flink/src/main/java/org/apache/iceberg/flink/sink/IcebergFilesCommitter.java:
##########
@@ -426,30 +425,45 @@ private void commitOperation(
}
@Override
- public void processElement(StreamRecord<WriteResult> element) {
- this.writeResultsOfCurrentCkpt.add(element.getValue());
+ public void processElement(StreamRecord<FlinkWriteResult> element) {
+ FlinkWriteResult flinkWriteResult = element.getValue();
+ List<WriteResult> writeResults =
+ writeResultsSinceLastSnapshot.computeIfAbsent(
+ flinkWriteResult.checkpointId(), k -> Lists.newArrayList());
+ writeResults.add(flinkWriteResult.writeResult());
}
@Override
public void endInput() throws IOException {
// Flush the buffered data files into 'dataFilesPerCheckpoint' firstly.
- long currentCheckpointId = Long.MAX_VALUE;
- dataFilesPerCheckpoint.put(currentCheckpointId,
writeToManifest(currentCheckpointId));
- writeResultsOfCurrentCkpt.clear();
-
+ long currentCheckpointId = IcebergStreamWriter.END_INPUT_CHECKPOINT_ID;
+ writeToManifestUptoLatestCheckpoint(currentCheckpointId);
commitUpToCheckpoint(dataFilesPerCheckpoint, flinkJobId, operatorUniqueId,
currentCheckpointId);
}
+ private void writeToManifestUptoLatestCheckpoint(long checkpointId) throws
IOException {
+ if (!writeResultsSinceLastSnapshot.containsKey(checkpointId)) {
+ dataFilesPerCheckpoint.put(checkpointId, EMPTY_MANIFEST_DATA);
+ }
+
+ for (Map.Entry<Long, List<WriteResult>> writeResultsOfCheckpoint :
+ writeResultsSinceLastSnapshot.entrySet()) {
+ dataFilesPerCheckpoint.put(
+ writeResultsOfCheckpoint.getKey(),
+ writeToManifest(writeResultsOfCheckpoint.getKey(),
writeResultsOfCheckpoint.getValue()));
Review Comment:
Maybe we should create a test case for it, as this is a non-trivial issue?
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
