SaketaChalamchala commented on code in PR #10750:
URL: https://github.com/apache/ozone/pull/10750#discussion_r3754162682
##########
hadoop-ozone/ozone-manager/src/main/java/org/apache/hadoop/ozone/om/snapshot/SnapshotDiffManager.java:
##########
@@ -1354,6 +1356,104 @@ private String resolveBucketRelativePath(boolean
isFSOBucket,
.substring(1);
}
+ /**
+ * Returns whether any ancestor of the given parent is a deleted directory.
+ * The walk stops at renamed directories because their descendant deletes are
+ * not subsumed by a deleted ancestor above them.
+ *
+ * @param objectIdToParentId from-snapshot directory parent graph keyed by
stable
+ * objectId; must not be the to-snapshot graph
+ * @param renamedDirectoryIds objectIds of directories renamed in the diff
(from
+ * snapshot objectIds, not destination paths)
+ */
+ @VisibleForTesting
+ boolean hasDeletedAncestor(long parentObjectId, Set<Long>
deletedDirectoryIds,
+ Set<Long> renamedDirectoryIds, Map<Long, Long> objectIdToParentId,
+ long bucketObjectId, Map<Long, Boolean> ancestorMemo) {
+ Objects.requireNonNull(objectIdToParentId, "objectIdToParentId must not be
null");
+ Objects.requireNonNull(renamedDirectoryIds, "renamedDirectoryIds must not
be null");
+
+ if (parentObjectId == bucketObjectId) {
+ return false;
+ }
+ Boolean cached = ancestorMemo.get(parentObjectId);
+ if (cached != null) {
+ return cached;
+ }
+
+ List<Long> path = new ArrayList<>();
+ long current = parentObjectId;
+ boolean result;
+ while (true) {
+ if (current == bucketObjectId) {
+ result = false;
+ break;
+ }
+ cached = ancestorMemo.get(current);
+ if (cached != null) {
+ result = cached;
+ break;
+ }
+ if (renamedDirectoryIds.contains(current)) {
+ result = false;
+ ancestorMemo.put(current, false);
+ break;
+ }
+ if (deletedDirectoryIds.contains(current)) {
+ result = true;
+ ancestorMemo.put(current, true);
+ break;
+ }
+ Long nextParent = objectIdToParentId.get(current);
+ if (nextParent == null) {
+ result = false;
+ ancestorMemo.put(current, false);
+ break;
+ }
+ path.add(current);
+ current = nextParent;
+ }
+ for (Long node : path) {
+ ancestorMemo.put(node, result);
+ }
+ return result;
+ }
+
+ /**
+ * Filters mixed directory and file delete entries, retaining only those
without
+ * a deleted directory ancestor. FSO buckets only.
+ *
+ * @param objectIdToParentId from-snapshot directory parent graph keyed by
stable
+ * objectId, built from a full fromSnapshot directoryTable scan
+ * @param renamedDirectoryIds objectIds of directories renamed in the diff
(from
+ * snapshot objectIds); pass an empty set when there are no renames
+ */
+ @VisibleForTesting
+ <T extends WithParentObjectId> List<T> filterTopLevelDeletedEntries(
Review Comment:
The intention is to persist the diff report entries to RocksDB for large
diffs (>1M) in [HDDS-15391](https://issues.apache.org/jira/browse/HDDS-15391).
Will add flexibility to read from RocksDB then.
--
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]
