ivakegg commented on a change in pull request #2293:
URL: https://github.com/apache/accumulo/pull/2293#discussion_r732742385
##########
File path:
server/gc/src/main/java/org/apache/accumulo/gc/GarbageCollectionAlgorithm.java
##########
@@ -217,11 +221,43 @@ private void confirmDeletes(GarbageCollectionEnvironment
gce,
throw new RuntimeException(
"Scanner over metadata table returned unexpected column : " +
entry.getKey());
}
+ Set<String> tableIdsAfter = gce.getTableIDs();
+ ensureAllTablesChecked(Collections.unmodifiableSet(tableIdsBefore),
+ Collections.unmodifiableSet(tableIdsSeen),
Collections.unmodifiableSet(tableIdsAfter));
confirmDeletesFromReplication(gce.getReplicationNeededIterator(),
candidateMap.entrySet().iterator());
}
+ @VisibleForTesting
+ /**
+ *
+ */
+ protected void ensureAllTablesChecked(Set<String> tableIdsBefore,
Set<String> tableIdsSeen,
+ Set<String> tableIdsAfter) {
+
+ // if a table was added or deleted during this run, it is acceptable to not
+ // have seen those tables ids when scanning the metadata table. So get the
intersection
+ Set<String> tableIdsMustHaveSeen = new HashSet<>(tableIdsBefore);
+ tableIdsMustHaveSeen.retainAll(tableIdsAfter);
+
+ if (tableIdsMustHaveSeen.isEmpty() && !tableIdsSeen.isEmpty()) {
+ // we saw no table ids in ZK but did in the metadata table. This is
unexpected.
Review comment:
if all tables are deleted since the scan, then could this not be a valid
situation?
##########
File path:
server/gc/src/main/java/org/apache/accumulo/gc/GarbageCollectionAlgorithm.java
##########
@@ -217,11 +221,43 @@ private void confirmDeletes(GarbageCollectionEnvironment
gce,
throw new RuntimeException(
"Scanner over metadata table returned unexpected column : " +
entry.getKey());
}
+ Set<String> tableIdsAfter = gce.getTableIDs();
+ ensureAllTablesChecked(Collections.unmodifiableSet(tableIdsBefore),
+ Collections.unmodifiableSet(tableIdsSeen),
Collections.unmodifiableSet(tableIdsAfter));
confirmDeletesFromReplication(gce.getReplicationNeededIterator(),
candidateMap.entrySet().iterator());
}
+ @VisibleForTesting
+ /**
+ *
+ */
+ protected void ensureAllTablesChecked(Set<String> tableIdsBefore,
Set<String> tableIdsSeen,
+ Set<String> tableIdsAfter) {
+
+ // if a table was added or deleted during this run, it is acceptable to not
+ // have seen those tables ids when scanning the metadata table. So get the
intersection
+ Set<String> tableIdsMustHaveSeen = new HashSet<>(tableIdsBefore);
+ tableIdsMustHaveSeen.retainAll(tableIdsAfter);
+
+ if (tableIdsMustHaveSeen.isEmpty() && !tableIdsSeen.isEmpty()) {
+ // we saw no table ids in ZK but did in the metadata table. This is
unexpected.
+ throw new RuntimeException(
+ "Saw no table ids in ZK but did see table ids in metadata table: " +
tableIdsSeen);
+ }
+
+ // From that intersection, remove all the table ids that were seen.
+ tableIdsMustHaveSeen.removeAll(tableIdsSeen);
+
+ // If anything is left then we missed a table and may not have removed
rfiles still in use
Review comment:
and may not have removed -> and might remove
##########
File path:
server/gc/src/main/java/org/apache/accumulo/gc/GarbageCollectionAlgorithm.java
##########
@@ -217,11 +221,43 @@ private void confirmDeletes(GarbageCollectionEnvironment
gce,
throw new RuntimeException(
"Scanner over metadata table returned unexpected column : " +
entry.getKey());
}
+ Set<String> tableIdsAfter = gce.getTableIDs();
+ ensureAllTablesChecked(Collections.unmodifiableSet(tableIdsBefore),
+ Collections.unmodifiableSet(tableIdsSeen),
Collections.unmodifiableSet(tableIdsAfter));
confirmDeletesFromReplication(gce.getReplicationNeededIterator(),
candidateMap.entrySet().iterator());
}
+ @VisibleForTesting
+ /**
+ *
+ */
+ protected void ensureAllTablesChecked(Set<String> tableIdsBefore,
Set<String> tableIdsSeen,
+ Set<String> tableIdsAfter) {
+
+ // if a table was added or deleted during this run, it is acceptable to not
+ // have seen those tables ids when scanning the metadata table. So get the
intersection
+ Set<String> tableIdsMustHaveSeen = new HashSet<>(tableIdsBefore);
+ tableIdsMustHaveSeen.retainAll(tableIdsAfter);
+
+ if (tableIdsMustHaveSeen.isEmpty() && !tableIdsSeen.isEmpty()) {
+ // we saw no table ids in ZK but did in the metadata table. This is
unexpected.
+ throw new RuntimeException(
+ "Saw no table ids in ZK but did see table ids in metadata table: " +
tableIdsSeen);
+ }
+
+ // From that intersection, remove all the table ids that were seen.
+ tableIdsMustHaveSeen.removeAll(tableIdsSeen);
Review comment:
What I think we want is that tableIdsMustHaveSeem is equivalent to
tableIdsSeen. This just tests if tableIdsSeen is a superset of
tableIdsMustHaveSeen.
--
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]
