rdblue commented on code in PR #4578:
URL: https://github.com/apache/iceberg/pull/4578#discussion_r873031857
##########
core/src/main/java/org/apache/iceberg/RemoveSnapshots.java:
##########
@@ -155,27 +168,93 @@ public List<Snapshot> apply() {
TableMetadata updated = internalApply();
List<Snapshot> removed = Lists.newArrayList(base.snapshots());
removed.removeAll(updated.snapshots());
-
return removed;
}
private TableMetadata internalApply() {
this.base = ops.refresh();
+ if (base.refs().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());
+ Set<Long> retainedRefIds = retainedRefs.entrySet().stream()
+ .map(refEntry -> refEntry.getValue().snapshotId())
+ .collect(Collectors.toSet());
+
+ for (long idToRemove : idsToRemove) {
+ Preconditions.checkArgument(!retainedRefIds.contains(idToRemove),
+ "Cannot expire %s. There is a reference to it", idToRemove);
+ }
+
+ idsToRetain.addAll(retainedRefIds);
+ 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 Set<Long> computeAllBranchSnapshotsToRetain(Map<String, SnapshotRef>
refs) {
+ Set<Long> branchSnapshotsToRetain = Sets.newHashSet();
+ for (Map.Entry<String, SnapshotRef> refEntry : refs.entrySet()) {
+ SnapshotRef ref = refEntry.getValue();
+ if (ref.isBranch()) {
+ long expireSnapshotsOlderThan;
+ int minSnapshotsToKeep;
+ if (ref.maxSnapshotAgeMs() == null) {
+ expireSnapshotsOlderThan = expireOlderThan;
+ } else {
+ expireSnapshotsOlderThan = now - ref.maxSnapshotAgeMs();
+ }
+
+ if (ref.minSnapshotsToKeep() == null) {
+ minSnapshotsToKeep = defaultMinNumSnapshots;
+ } else {
+ minSnapshotsToKeep = ref.minSnapshotsToKeep();
+ }
+
+ branchSnapshotsToRetain.addAll(
+ computeBranchSnapshotsToRetain(ref.snapshotId(),
expireSnapshotsOlderThan, minSnapshotsToKeep));
+ }
+ }
+
+ return branchSnapshotsToRetain;
+ }
+
+ 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();
+ long maxRefAgeMs = ref.maxRefAgeMs() != null ? ref.maxRefAgeMs() :
defaultMaxRefAgeMs;
+ Snapshot snapshot = base.snapshot(ref.snapshotId());
+ if (snapshot != null && now - snapshot.timestampMillis() <= maxRefAgeMs)
{
Review Comment:
Nit: this relies on precedence. I prefer to use parens to make precedence
clear: `(now - snapshot.timestampMillis()) <= maxRefAgeMs`.
Another good option is to separately handle snapshots that don't exist
(there shouldn't be any -- warn and expire them) and then use a variable,
`refAge`:
```java
Snapshot snapshot = base.snapshot(ref.snapshotId());
if (snapshot != null) {
long refAgeMs = now - snapshot.timestampMillis();
if (refAgeMs <= maxRefAgeMs()) {
retainedRefs.put(name, ref);
}
} else {
LOG.warn("Removing invalid ref %s: missing snapshot %s", name,
ref.snapshotId());
}
```
--
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]
