Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Core: Fix loading a table in CachingCatalog with metadata table name #11738

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+45 −5
Open

Core: Fix loading a table in CachingCatalog with metadata table name #11738

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions core/src/main/java/org/apache/iceberg/CachingCatalog.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,14 +144,16 @@ public Table loadTable(TableIdentifier ident) {
return cached;
}

if (MetadataTableUtils.hasMetadataTableName(canonicalized)) {
Table table = tableCache.get(canonicalized, catalog::loadTable);

if (table instanceof BaseMetadataTable) {
// Cache underlying table
TableIdentifier originTableIdentifier =
TableIdentifier.of(canonicalized.namespace().levels());
Table originTable = tableCache.get(originTableIdentifier, catalog::loadTable);

// share TableOperations instance of origin table for all metadata tables, so that metadata
// table instances are
// also refreshed as well when origin table instance is refreshed.
// Share TableOperations instance of origin table for all metadata tables, so that metadata
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we still need code below when we already cache the metadata table above?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's needed to share the underlying TableOperations between the originTable and the metadata table. We basically create another Table object for the table metadata with a different TableOperations and then update the cache with that object.

// table instances are also refreshed as well when origin table instance is refreshed.
if (originTable instanceof HasTableOperations) {
TableOperations ops = ((HasTableOperations) originTable).operations();
MetadataTableType type = MetadataTableType.from(canonicalized.name());
Expand All @@ -164,7 +166,7 @@ public Table loadTable(TableIdentifier ident) {
}
}

return tableCache.get(canonicalized, catalog::loadTable);
return table;
}

@Override
Expand Down
38 changes: 38 additions & 0 deletions core/src/test/java/org/apache/iceberg/hadoop/TestCachingCatalog.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@
import java.util.concurrent.Executors;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.atomic.AtomicInteger;
import org.apache.iceberg.BaseMetadataTable;
import org.apache.iceberg.CachingCatalog;
import org.apache.iceberg.CatalogProperties;
import org.apache.iceberg.MetadataTableType;
Expand All @@ -41,6 +42,7 @@
import org.apache.iceberg.catalog.Catalog;
import org.apache.iceberg.catalog.Namespace;
import org.apache.iceberg.catalog.TableIdentifier;
import org.apache.iceberg.exceptions.NoSuchTableException;
import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.util.FakeTicker;
Expand Down Expand Up @@ -166,6 +168,42 @@ public void testTableName() throws Exception {
.isEqualTo("hadoop.db.ns1.ns2.tbl.snapshots");
}

@Test
public void testNonExistingTable() throws Exception {
Catalog catalog = CachingCatalog.wrap(hadoopCatalog());

TableIdentifier tableIdent = TableIdentifier.of("otherDB", "otherTbl");

assertThatThrownBy(() -> catalog.loadTable(tableIdent))
.isInstanceOf(NoSuchTableException.class);
}

@Test
public void testTableWithMetadataTableName() throws Exception {
TestableCachingCatalog catalog =
TestableCachingCatalog.wrap(hadoopCatalog(), EXPIRATION_TTL, ticker);
TableIdentifier tableIdent = TableIdentifier.of("db", "ns1", "ns2", "partitions");
TableIdentifier metaTableIdent =
TableIdentifier.of("db", "ns1", "ns2", "partitions", "partitions");

catalog.createTable(tableIdent, SCHEMA, SPEC, ImmutableMap.of("key2", "value2"));
catalog.cache().invalidateAll();

Table table = catalog.loadTable(tableIdent);
assertThat(table.name()).isEqualTo("hadoop.db.ns1.ns2.partitions");
assertThat(catalog.cache().asMap()).containsKey(tableIdent);
assertThat(catalog.cache().asMap()).doesNotContainKey(metaTableIdent);

catalog.cache().invalidateAll();
assertThat(catalog.cache().asMap()).doesNotContainKey(tableIdent);

Table metaTable = catalog.loadTable(metaTableIdent);
assertThat(metaTable).isInstanceOf(BaseMetadataTable.class);
assertThat(metaTable.name()).isEqualTo("hadoop.db.ns1.ns2.partitions.partitions");
assertThat(catalog.cache().asMap()).containsKey(tableIdent);
assertThat(catalog.cache().asMap()).containsKey(metaTableIdent);
}

@Test
public void testTableExpiresAfterInterval() throws IOException {
TestableCachingCatalog catalog =
Expand Down