amogh-jahagirdar commented on code in PR #4578:
URL: https://github.com/apache/iceberg/pull/4578#discussion_r885148555
##########
core/src/main/java/org/apache/iceberg/RemoveSnapshots.java:
##########
@@ -161,21 +174,89 @@ public List<Snapshot> apply() {
private TableMetadata internalApply() {
this.base = ops.refresh();
+ if (base.snapshots().isEmpty()) {
+ return base;
+ }
Set<Long> idsToRetain = Sets.newHashSet();
- List<Long> ancestorIds = SnapshotUtil.ancestorIds(base.currentSnapshot(),
base::snapshot);
- if (minNumSnapshots >= ancestorIds.size()) {
- idsToRetain.addAll(ancestorIds);
- } else {
- idsToRetain.addAll(ancestorIds.subList(0, minNumSnapshots));
+ // Identify refs that should be removed
+ Map<String, SnapshotRef> retainedRefs = computeRetainedRefs(base.refs());
+ Map<Long, List<String>> retainedIdToRefs = Maps.newHashMap();
+ for (Map.Entry<String, SnapshotRef> retainedRefEntry :
retainedRefs.entrySet()) {
+ long snapshotId = retainedRefEntry.getValue().snapshotId();
+ retainedIdToRefs.putIfAbsent(snapshotId, Lists.newArrayList());
+ retainedIdToRefs.get(snapshotId).add(retainedRefEntry.getKey());
+ }
+
+ for (long idToRemove : idsToRemove) {
+ List<String> refsForId = retainedIdToRefs.get(idToRemove);
+ Preconditions.checkArgument(refsForId == null,
+ "Cannot expire %s. Still referenced by refs: %s", idToRemove,
refsForId);
}
- TableMetadata updateMeta = base.removeSnapshotsIf(snapshot ->
- idsToRemove.contains(snapshot.snapshotId()) ||
- (snapshot.timestampMillis() < expireOlderThan &&
!idsToRetain.contains(snapshot.snapshotId())));
- List<Snapshot> updateSnapshots = updateMeta.snapshots();
- List<Snapshot> baseSnapshots = base.snapshots();
- return updateSnapshots.size() != baseSnapshots.size() ? updateMeta : base;
+ idsToRetain.addAll(retainedIdToRefs.keySet());
+ Set<Long> branchSnapshotsToRetain =
computeAllBranchSnapshotsToRetain(retainedRefs);
+ idsToRetain.addAll(branchSnapshotsToRetain);
+ TableMetadata.Builder updatedMetaBuilder = TableMetadata.buildFrom(base);
+ idsToRemove.addAll(base.snapshots().stream().map(Snapshot::snapshotId)
+ .filter(snapshot ->
!idsToRetain.contains(snapshot)).collect(Collectors.toSet()));
+ base.refs().keySet().stream().filter(ref ->
!retainedRefs.containsKey(ref)).forEach(updatedMetaBuilder::removeRef);
+ updatedMetaBuilder.removeSnapshots(idsToRemove);
+ return updatedMetaBuilder.build();
+ }
+
+ private Map<String, SnapshotRef> computeRetainedRefs(Map<String,
SnapshotRef> refs) {
+ Map<String, SnapshotRef> retainedRefs = Maps.newHashMap();
+ retainedRefs.put(SnapshotRef.MAIN_BRANCH,
refs.get(SnapshotRef.MAIN_BRANCH));
+ for (Map.Entry<String, SnapshotRef> refEntry : refs.entrySet()) {
+ String name = refEntry.getKey();
+ SnapshotRef ref = refEntry.getValue();
+ Snapshot snapshot = base.snapshot(ref.snapshotId());
+ long maxRefAgeMs = ref.maxRefAgeMs() != null ? ref.maxRefAgeMs() :
defaultMaxRefAgeMs;
+ if (snapshot != null) {
+ long refAgeMs = now - snapshot.timestampMillis();
+ if (refAgeMs <= maxRefAgeMs) {
+ retainedRefs.put(name, ref);
+ }
+ } else {
+ LOG.warn("Removing invalid ref {}: snapshot {} does not exist", name,
ref.snapshotId());
+ }
+ }
+
+ return retainedRefs;
+ }
+
+ private Set<Long> computeAllBranchSnapshotsToRetain(Map<String, SnapshotRef>
refs) {
+ Set<Long> branchSnapshotsToRetain = Sets.newHashSet();
+ for (Map.Entry<String, SnapshotRef> refEntry : refs.entrySet()) {
+ SnapshotRef ref = refEntry.getValue();
Review Comment:
Yeah I think we can actually just let this method take in the list of refs
directly instead of the entire map, and then just iterate over that.
--
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]
