amogh-jahagirdar commented on code in PR #15006:
URL: https://github.com/apache/iceberg/pull/15006#discussion_r2695333703
##########
core/src/main/java/org/apache/iceberg/MergingSnapshotProducer.java:
##########
@@ -1073,6 +1088,139 @@ private List<ManifestFile> newDeleteFilesAsManifests() {
return cachedNewDeleteManifests;
}
+ // Merge duplicates, internally takes care of updating newDeleteFilesBySpec
to remove
+ // duplicates and add the newly merged DV
+ private void mergeDVsAndWrite() {
+ Map<Integer, List<MergedDVContent>> mergedIndicesBySpec =
Maps.newConcurrentMap();
+
+ Tasks.foreach(dvsByReferencedFile.entrySet())
+ .executeWith(ThreadPools.getDeleteWorkerPool())
+ .stopOnFailure()
+ .throwFailureWhenFinished()
+ .run(
+ entry -> {
+ String referencedLocation = entry.getKey();
+ DeleteFileSet dvsToMerge = entry.getValue();
+ // Nothing to merge
+ if (dvsToMerge.size() < 2) {
+ return;
+ }
+
+ MergedDVContent merged = mergePositions(referencedLocation,
dvsToMerge);
+
+ mergedIndicesBySpec
+ .computeIfAbsent(
+ merged.specId, spec ->
Collections.synchronizedList(Lists.newArrayList()))
+ .add(merged);
+ });
+
+ // Update newDeleteFilesBySpec to remove all the duplicates
+ mergedIndicesBySpec.forEach(
+ (specId, mergedDVContent) -> {
+ mergedDVContent.stream()
+ .map(content -> content.mergedDVs)
+ .forEach(duplicateDVs ->
newDeleteFilesBySpec.get(specId).removeAll(duplicateDVs));
+ });
+
+ writeMergedDVs(mergedIndicesBySpec);
+ }
+
+ // Produces a Puffin per partition spec containing the merged DVs for that
spec
+ private void writeMergedDVs(Map<Integer, List<MergedDVContent>>
mergedDVContentBySpec) {
+ Map<Integer, DeleteFileSet> mergedDVsBySpec = Maps.newHashMap();
+
+ mergedDVContentBySpec.forEach(
+ (specId, mergedDVsForSpec) -> {
+ try (DVFileWriter dvFileWriter =
+ new BaseDVFileWriter(
+ OutputFileFactory.builderFor(ops(), spec(specId),
FileFormat.PUFFIN, 1, 1)
+ .build(),
+ path -> null)) {
+
+ for (MergedDVContent mergedDV : mergedDVsForSpec) {
+ LOG.warn(
+ "Merged {} duplicate deletion vectors for data file {} in
table {}. The merged DVs are orphaned, and writers should merge DVs per file
before committing",
Review Comment:
I can edit the language around this, yeah I can see how it's confusing
>Although this raises the question of why we aren't just deleting the
duplicates?
I was a bit wary about doing any more unnecessary I/Os on the commit path,
want to limit the chance of failures. Thuogh we could do a best effort w try
catch?
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
