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

Support Glue catalog in Iceberg connector #10151

Closed
wants to merge 1 commit into from
Closed

Support Glue catalog in Iceberg connector #10151

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
2 changes: 1 addition & 1 deletion plugin/trino-hive/src/main/java/io/trino/plugin/hive/metastore/glue/GlueHiveMetastore.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -201,7 +201,7 @@ public GlueHiveMetastore(
this.columnStatisticsProvider = columnStatisticsProviderFactory.createGlueColumnStatisticsProvider(glueClient, stats);
}

private static AWSGlueAsync createAsyncGlueClient(GlueHiveMetastoreConfig config, Optional<RequestHandler2> requestHandler, RequestMetricCollector metricsCollector)
public static AWSGlueAsync createAsyncGlueClient(GlueHiveMetastoreConfig config, Optional<RequestHandler2> requestHandler, RequestMetricCollector metricsCollector)
{
ClientConfiguration clientConfig = new ClientConfiguration()
.withMaxConnections(config.getMaxGlueConnections())
Expand Down
16 changes: 16 additions & 0 deletions plugin/trino-hive/src/main/java/io/trino/plugin/hive/metastore/glue/GlueMetastoreStats.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,8 @@ public class GlueMetastoreStats
private final GlueMetastoreApiStats createTable = new GlueMetastoreApiStats();
private final GlueMetastoreApiStats dropTable = new GlueMetastoreApiStats();
private final GlueMetastoreApiStats replaceTable = new GlueMetastoreApiStats();
private final GlueMetastoreApiStats updateTable = new GlueMetastoreApiStats();
private final GlueMetastoreApiStats renameTable = new GlueMetastoreApiStats();
private final GlueMetastoreApiStats getPartitionNames = new GlueMetastoreApiStats();
private final GlueMetastoreApiStats getPartitions = new GlueMetastoreApiStats();
private final GlueMetastoreApiStats getPartition = new GlueMetastoreApiStats();
Expand Down Expand Up @@ -140,6 +142,20 @@ public GlueMetastoreApiStats getReplaceTable()
return replaceTable;
}

@Managed
@Nested
public GlueMetastoreApiStats getUpdateTable()
{
return updateTable;
}

@Managed
@Nested
public GlueMetastoreApiStats getRenameTable()
{
return renameTable;
}

@Managed
@Nested
public GlueMetastoreApiStats getGetPartitionNames()
Expand Down
54 changes: 54 additions & 0 deletions plugin/trino-iceberg/pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,11 @@
<artifactId>bootstrap</artifactId>
</dependency>

<dependency>
<groupId>io.airlift</groupId>
<artifactId>concurrent</artifactId>
</dependency>

<dependency>
<groupId>io.airlift</groupId>
<artifactId>configuration</artifactId>
Expand All @@ -84,6 +89,16 @@
<artifactId>units</artifactId>
</dependency>

<dependency>
<groupId>com.amazonaws</groupId>
<artifactId>aws-java-sdk-core</artifactId>
</dependency>

<dependency>
<groupId>com.amazonaws</groupId>
<artifactId>aws-java-sdk-glue</artifactId>
</dependency>

<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
Expand Down Expand Up @@ -301,4 +316,43 @@
</plugins>
</pluginManagement>
</build>

<profiles>
<profile>
<id>default</id>
<activation>
<activeByDefault>true</activeByDefault>
</activation>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<configuration>
<excludes>
<exclude>**/TestIcebergGlueCatalogConnectorSmokeTest.java</exclude>
</excludes>
</configuration>
</plugin>
</plugins>
</build>
</profile>

<profile>
<id>test-iceberg-glue</id>
Copy link
Member

Choose a reason for hiding this comment

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

This needs to be run on CI.

Maybe instead of a profile with single test, let's have a profile with all tests (no exclusions).

trino/.github/workflows/ci.yml

Line 351 in 3c0cf0b

- ":trino-iceberg,:trino-druid"

would become

- ":trino-iceberg -P test-all,:trino-druid"

also, we should move trino-druid to a different group, maybe with kudu (need to check running times)

<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<configuration>
<includes>
<include>**/TestIcebergGlueCatalogConnectorSmokeTest.java</include>
</includes>
</configuration>
</plugin>
</plugins>
</build>
</profile>
</profiles>
</project>
17 changes: 17 additions & 0 deletions plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/IcebergConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,8 @@
import javax.validation.constraints.Min;
import javax.validation.constraints.NotNull;

import java.util.Optional;

import static io.trino.plugin.hive.HiveCompressionCodec.ZSTD;
import static io.trino.plugin.iceberg.CatalogType.HIVE_METASTORE;
import static io.trino.plugin.iceberg.IcebergFileFormat.ORC;
Expand All @@ -38,6 +40,7 @@ public class IcebergConfig
private Duration dynamicFilteringWaitTimeout = new Duration(0, SECONDS);
private boolean tableStatisticsEnabled = true;
private boolean projectionPushdownEnabled = true;
private Optional<String> defaultSchemaLocation = Optional.empty();

public CatalogType getCatalogType()
{
Expand Down Expand Up @@ -167,4 +170,18 @@ public IcebergConfig setProjectionPushdownEnabled(boolean projectionPushdownEnab
this.projectionPushdownEnabled = projectionPushdownEnabled;
return this;
}

@NotNull
public Optional<String> getDefaultSchemaLocation()
{
return defaultSchemaLocation;
}

@Config("iceberg.default-schema-location")
Copy link
Member

Choose a reason for hiding this comment

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

This is applicable to Glue only, so should be in a config class that's bound only when Glue catalog is used.
it should start with iceberg.glue.

@ConfigDescription("The default base location to create a new schema")
public IcebergConfig setDefaultSchemaLocation(String defaultSchemaLocation)
{
this.defaultSchemaLocation = Optional.ofNullable(defaultSchemaLocation);
return this;
}
}
2 changes: 2 additions & 0 deletions plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/IcebergErrorCode.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,8 @@ public enum IcebergErrorCode
ICEBERG_CURSOR_ERROR(9, EXTERNAL),
ICEBERG_WRITE_VALIDATION_FAILED(10, INTERNAL_ERROR),
ICEBERG_INVALID_SNAPSHOT_ID(11, USER_ERROR),
ICEBERG_CATALOG_ERROR(12, EXTERNAL),
ICEBERG_COMMIT_ERROR(13, EXTERNAL)
Copy link
Member

Choose a reason for hiding this comment

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

Extract commit introducing this error code.
It should be used in io.trino.plugin.iceberg.catalog.hms.AbstractMetastoreTableOperations#commitNewTable and io.trino.plugin.iceberg.catalog.hms.HiveMetastoreTableOperations#commitToExistingTable

/**/;

private final ErrorCode errorCode;
Expand Down
3 changes: 2 additions & 1 deletion plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/IcebergMetadata.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
import io.trino.plugin.hive.HiveApplyProjectionUtil;
import io.trino.plugin.hive.HiveApplyProjectionUtil.ProjectedColumnRepresentation;
import io.trino.plugin.hive.HiveWrittenPartitions;
import io.trino.plugin.iceberg.catalog.TrinoCatalog;
import io.trino.spi.TrinoException;
import io.trino.spi.connector.Assignment;
import io.trino.spi.connector.CatalogSchemaName;
Expand Down Expand Up @@ -118,9 +119,9 @@
import static io.trino.plugin.iceberg.PartitionFields.parsePartitionFields;
import static io.trino.plugin.iceberg.PartitionFields.toPartitionFields;
import static io.trino.plugin.iceberg.TableType.DATA;
import static io.trino.plugin.iceberg.TrinoHiveCatalog.DEPENDS_ON_TABLES;
import static io.trino.plugin.iceberg.TypeConverter.toIcebergType;
import static io.trino.plugin.iceberg.TypeConverter.toTrinoType;
import static io.trino.plugin.iceberg.catalog.hms.TrinoHiveCatalog.DEPENDS_ON_TABLES;
import static io.trino.spi.StandardErrorCode.NOT_SUPPORTED;
import static io.trino.spi.type.BigintType.BIGINT;
import static java.util.Collections.singletonList;
Expand Down
1 change: 1 addition & 0 deletions plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/IcebergMetadataFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
package io.trino.plugin.iceberg;

import io.airlift.json.JsonCodec;
import io.trino.plugin.iceberg.catalog.TrinoCatalogFactory;
import io.trino.spi.type.TypeManager;

import javax.inject.Inject;
Expand Down
1 change: 0 additions & 1 deletion plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/IcebergModule.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,6 @@ public void configure(Binder binder)
configBinder(binder).bindConfig(ParquetReaderConfig.class);
configBinder(binder).bindConfig(ParquetWriterConfig.class);

binder.bind(TrinoCatalogFactory.class).in(Scopes.SINGLETON);
binder.bind(IcebergMetadataFactory.class).in(Scopes.SINGLETON);

jsonCodecBinder(binder).bindJsonCodec(CommitTaskData.class);
Expand Down
25 changes: 19 additions & 6 deletions plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/IcebergUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,9 @@
import io.airlift.slice.Slice;
import io.airlift.slice.SliceUtf8;
import io.airlift.slice.Slices;
import io.trino.plugin.hive.metastore.HiveMetastore;
import io.trino.plugin.iceberg.catalog.IcebergTableOperations;
import io.trino.plugin.iceberg.catalog.IcebergTableOperationsProvider;
import io.trino.plugin.iceberg.catalog.TrinoCatalog;
import io.trino.spi.TrinoException;
import io.trino.spi.connector.ColumnMetadata;
import io.trino.spi.connector.ConnectorSession;
Expand Down Expand Up @@ -105,7 +105,10 @@
import static org.apache.iceberg.LocationProviders.locationsFor;
import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT;
import static org.apache.iceberg.TableProperties.DEFAULT_FILE_FORMAT_DEFAULT;
import static org.apache.iceberg.TableProperties.OBJECT_STORE_PATH;
import static org.apache.iceberg.TableProperties.WRITE_LOCATION_PROVIDER_IMPL;
import static org.apache.iceberg.TableProperties.WRITE_METADATA_LOCATION;
import static org.apache.iceberg.TableProperties.WRITE_NEW_DATA_LOCATION;
import static org.apache.iceberg.types.Type.TypeID.BINARY;
import static org.apache.iceberg.types.Type.TypeID.FIXED;

Expand All @@ -120,10 +123,10 @@ public static boolean isIcebergTable(io.trino.plugin.hive.metastore.Table table)
return ICEBERG_TABLE_TYPE_VALUE.equalsIgnoreCase(table.getParameters().get(TABLE_TYPE_PROP));
}

public static Table loadIcebergTable(HiveMetastore metastore, IcebergTableOperationsProvider tableOperationsProvider, ConnectorSession session, SchemaTableName table)
public static Table loadIcebergTable(TrinoCatalog catalog, IcebergTableOperationsProvider tableOperationsProvider, ConnectorSession session, SchemaTableName table)
{
TableOperations operations = tableOperationsProvider.createTableOperations(
metastore,
catalog,
session,
table.getSchemaName(),
table.getTableName(),
Expand All @@ -133,14 +136,14 @@ public static Table loadIcebergTable(HiveMetastore metastore, IcebergTableOperat
}

public static Table getIcebergTableWithMetadata(
HiveMetastore metastore,
TrinoCatalog catalog,
IcebergTableOperationsProvider tableOperationsProvider,
ConnectorSession session,
SchemaTableName table,
TableMetadata tableMetadata)
{
IcebergTableOperations operations = tableOperationsProvider.createTableOperations(
metastore,
catalog,
session,
table.getSchemaName(),
table.getTableName(),
Expand Down Expand Up @@ -229,7 +232,7 @@ public static Optional<String> getTableComment(Table table)
return Optional.ofNullable(table.properties().get(TABLE_COMMENT));
}

private static String quotedTableName(SchemaTableName name)
public static String quotedTableName(SchemaTableName name)
{
return quotedName(name.getSchemaName()) + "." + quotedName(name.getTableName());
}
Expand Down Expand Up @@ -397,4 +400,14 @@ public static Transaction newCreateTableTransaction(TrinoCatalog catalog, Connec

return catalog.newCreateTableTransaction(session, schemaTableName, schema, partitionSpec, targetPath, propertiesBuilder.build());
}

public static void validateTableCanBeDropped(Table table, SchemaTableName schemaTableName)
{
// TODO: support path override in Iceberg table creation: https://github.com/trinodb/trino/issues/8861
if (table.properties().containsKey(OBJECT_STORE_PATH) ||
table.properties().containsKey(WRITE_NEW_DATA_LOCATION) ||
table.properties().containsKey(WRITE_METADATA_LOCATION)) {
throw new TrinoException(NOT_SUPPORTED, "Table " + schemaTableName + " contains Iceberg path override properties and cannot be dropped from Trino");
}
}
}
1 change: 1 addition & 0 deletions .../trino-iceberg/src/main/java/io/trino/plugin/iceberg/InternalIcebergConnectorFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@
import io.trino.plugin.hive.gcs.HiveGcsModule;
import io.trino.plugin.hive.metastore.HiveMetastore;
import io.trino.plugin.hive.s3.HiveS3Module;
import io.trino.plugin.iceberg.catalog.IcebergCatalogModule;
Copy link
Member

Choose a reason for hiding this comment

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

Extract commit that introduces io.trino.plugin.iceberg.catalog package.

import io.trino.spi.NodeManager;
import io.trino.spi.PageIndexerFactory;
import io.trino.spi.classloader.ThreadContextClassLoader;
Expand Down
1 change: 1 addition & 0 deletions plugin/trino-iceberg/src/main/java/io/trino/plugin/iceberg/RollbackToSnapshotProcedure.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
package io.trino.plugin.iceberg;

import com.google.common.collect.ImmutableList;
import io.trino.plugin.iceberg.catalog.TrinoCatalogFactory;
import io.trino.spi.connector.ConnectorSession;
import io.trino.spi.connector.SchemaTableName;
import io.trino.spi.procedure.Procedure;
Expand Down
Loading