deniskuzZ commented on code in PR #6039:
URL: https://github.com/apache/hive/pull/6039#discussion_r2297451068
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/compaction/IcebergTableOptimizer.java:
##########
@@ -85,52 +85,53 @@ public IcebergTableOptimizer(HiveConf conf, TxnStore
txnHandler, MetadataCache m
*/
@Override
public Set<CompactionInfo> findPotentialCompactions(long lastChecked,
ShowCompactResponse currentCompactions,
- Set<String> skipDBs, Set<String> skipTables) {
+ Set<String> skipDBs,
Set<String> skipTables) {
Set<CompactionInfo> compactionTargets = Sets.newHashSet();
- getTableNames().stream()
- .filter(table -> !skipDBs.contains(table.getDb()))
- .filter(table -> !skipTables.contains(table.getNotEmptyDbTable()))
- .map(table -> {
- org.apache.hadoop.hive.ql.metadata.Table hiveTable =
getHiveTable(table.getDb(), table.getTable());
- org.apache.iceberg.Table icebergTable =
IcebergTableUtil.getTable(conf, hiveTable.getTTable());
- return Pair.of(hiveTable, icebergTable);
- })
- .filter(t -> hasNewCommits(t.getRight(),
- snapshotTimeMilCache.get(t.getLeft().getFullyQualifiedName())))
- .forEach(t -> {
- String qualifiedTableName = t.getLeft().getFullyQualifiedName();
- org.apache.hadoop.hive.ql.metadata.Table hiveTable = t.getLeft();
- org.apache.iceberg.Table icebergTable = t.getRight();
-
- if (icebergTable.spec().isPartitioned()) {
- List<org.apache.hadoop.hive.ql.metadata.Partition> partitions =
findModifiedPartitions(hiveTable,
- icebergTable, snapshotTimeMilCache.get(qualifiedTableName),
true);
-
- partitions.forEach(partition ->
addCompactionTargetIfEligible(hiveTable.getTTable(), icebergTable,
- partition.getName(), compactionTargets, currentCompactions,
skipDBs, skipTables));
-
- if (IcebergTableUtil.hasUndergonePartitionEvolution(icebergTable)
&& !findModifiedPartitions(hiveTable,
- icebergTable, snapshotTimeMilCache.get(qualifiedTableName),
false).isEmpty()) {
- addCompactionTargetIfEligible(hiveTable.getTTable(),
icebergTable,
- null, compactionTargets, currentCompactions, skipDBs,
skipTables);
- }
- } else {
- addCompactionTargetIfEligible(hiveTable.getTTable(), icebergTable,
null, compactionTargets,
- currentCompactions, skipDBs, skipTables);
- }
-
- snapshotTimeMilCache.put(qualifiedTableName,
icebergTable.currentSnapshot().timestampMillis());
- });
+ Iterable<Table> tables = getTables();
Review Comment:
> How is Catalogs.loadTable invoking HiveTableOperations.doRefresh as when I
see in HiveTableOperations.doRefresh, it shows no usages ? Am I missing
something here ?
try to run the test under debug
> Even if we consider adding it to code, let's say I added this to
HiveTableOperations' constructor but adding this to TableFetcher is not
possible as TableFetcher does not have access to conf. One thing that can be
done is adding this to IcebergHouseKeeperService.java but I don't know if it
will add any value
I don't follow why can't you propagate Configuration object to TableFetcher.
This would introduce client-side caching, eliminating the need for multiple
consecutive calls to hms.getTable(database, tableName).
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/compaction/IcebergTableOptimizer.java:
##########
@@ -85,52 +85,53 @@ public IcebergTableOptimizer(HiveConf conf, TxnStore
txnHandler, MetadataCache m
*/
@Override
public Set<CompactionInfo> findPotentialCompactions(long lastChecked,
ShowCompactResponse currentCompactions,
- Set<String> skipDBs, Set<String> skipTables) {
+ Set<String> skipDBs,
Set<String> skipTables) {
Set<CompactionInfo> compactionTargets = Sets.newHashSet();
- getTableNames().stream()
- .filter(table -> !skipDBs.contains(table.getDb()))
- .filter(table -> !skipTables.contains(table.getNotEmptyDbTable()))
- .map(table -> {
- org.apache.hadoop.hive.ql.metadata.Table hiveTable =
getHiveTable(table.getDb(), table.getTable());
- org.apache.iceberg.Table icebergTable =
IcebergTableUtil.getTable(conf, hiveTable.getTTable());
- return Pair.of(hiveTable, icebergTable);
- })
- .filter(t -> hasNewCommits(t.getRight(),
- snapshotTimeMilCache.get(t.getLeft().getFullyQualifiedName())))
- .forEach(t -> {
- String qualifiedTableName = t.getLeft().getFullyQualifiedName();
- org.apache.hadoop.hive.ql.metadata.Table hiveTable = t.getLeft();
- org.apache.iceberg.Table icebergTable = t.getRight();
-
- if (icebergTable.spec().isPartitioned()) {
- List<org.apache.hadoop.hive.ql.metadata.Partition> partitions =
findModifiedPartitions(hiveTable,
- icebergTable, snapshotTimeMilCache.get(qualifiedTableName),
true);
-
- partitions.forEach(partition ->
addCompactionTargetIfEligible(hiveTable.getTTable(), icebergTable,
- partition.getName(), compactionTargets, currentCompactions,
skipDBs, skipTables));
-
- if (IcebergTableUtil.hasUndergonePartitionEvolution(icebergTable)
&& !findModifiedPartitions(hiveTable,
- icebergTable, snapshotTimeMilCache.get(qualifiedTableName),
false).isEmpty()) {
- addCompactionTargetIfEligible(hiveTable.getTTable(),
icebergTable,
- null, compactionTargets, currentCompactions, skipDBs,
skipTables);
- }
- } else {
- addCompactionTargetIfEligible(hiveTable.getTTable(), icebergTable,
null, compactionTargets,
- currentCompactions, skipDBs, skipTables);
- }
-
- snapshotTimeMilCache.put(qualifiedTableName,
icebergTable.currentSnapshot().timestampMillis());
- });
+ Iterable<Table> tables = getTables();
Review Comment:
> How is Catalogs.loadTable invoking HiveTableOperations.doRefresh as when I
see in HiveTableOperations.doRefresh, it shows no usages ? Am I missing
something here ?
try to run the test under debug
> Even if we consider adding it to code, let's say I added this to
HiveTableOperations' constructor but adding this to TableFetcher is not
possible as TableFetcher does not have access to conf. One thing that can be
done is adding this to IcebergHouseKeeperService.java but I don't know if it
will add any value
I don't follow why can't you propagate Configuration object to TableFetcher.
This would introduce client-side caching, eliminating the need for multiple
consecutive calls to hms.getTable(database, tableName).
--
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]
