Merge branch 'antalya-25.8' into feature/antalya-25.8/iceberg_local_cluster

Author: ianton-ru

src/Client/MultiplexedConnections.cpp

@@ -232,7 +232,7 @@ void MultiplexedConnections::sendIgnoredPartUUIDs(const std::vector<UUID> & uuid
 void MultiplexedConnections::sendClusterFunctionReadTaskResponse(const ClusterFunctionReadTaskResponse & response)
 {
     std::lock_guard lock(cancel_mutex);
-    if (cancelled)
+    if (cancelled || !current_connection || !current_connection->isConnected())
         return;
     current_connection->sendClusterFunctionReadTaskResponse(response);
 }
@@ -241,7 +241,7 @@ void MultiplexedConnections::sendClusterFunctionReadTaskResponse(const ClusterFu
 void MultiplexedConnections::sendMergeTreeReadTaskResponse(const ParallelReadResponse & response)
 {
     std::lock_guard lock(cancel_mutex);
-    if (cancelled)
+    if (cancelled || !current_connection || !current_connection->isConnected())
         return;
     current_connection->sendMergeTreeReadTaskResponse(response);
 }
@@ -527,9 +527,12 @@ MultiplexedConnections::ReplicaState & MultiplexedConnections::getReplicaForRead
 
 void MultiplexedConnections::invalidateReplica(ReplicaState & state)
 {
+    Connection * old_connection = state.connection;
     state.connection = nullptr;
     state.pool_entry = IConnectionPool::Entry();
     --active_connection_count;
+    if (current_connection == old_connection)
+        current_connection = nullptr;
 }
 
 void MultiplexedConnections::setAsyncCallback(AsyncCallback async_callback)

src/Common/ProfileEvents.cpp

@@ -299,6 +299,11 @@
     M(IcebergTrivialCountOptimizationApplied, "Trivial count optimization applied while reading from Iceberg", ValueType::Number) \
     M(IcebergVersionHintUsed, "Number of times version-hint.text has been used.", ValueType::Number) \
     M(IcebergMinMaxIndexPrunedFiles, "Number of skipped files by using MinMax index in Iceberg", ValueType::Number) \
+    M(IcebergAvroFileParsing, "Number of times avro metadata files have been parsed.", ValueType::Number) \
+    M(IcebergAvroFileParsingMicroseconds, "Time spent for parsing avro metadata files for Iceberg tables.", ValueType::Microseconds) \
+    M(IcebergJsonFileParsing, "Number of times json metadata files have been parsed.", ValueType::Number) \
+    M(IcebergJsonFileParsingMicroseconds, "Time spent for parsing json metadata files for Iceberg tables.", ValueType::Microseconds) \
+    \
     M(JoinBuildTableRowCount, "Total number of rows in the build table for a JOIN operation.", ValueType::Number) \
     M(JoinProbeTableRowCount, "Total number of rows in the probe table for a JOIN operation.", ValueType::Number) \
     M(JoinResultRowCount, "Total number of rows in the result of a JOIN operation.", ValueType::Number) \
@@ -580,7 +585,9 @@ The server successfully detected this situation and will download merged part fr
     M(S3DeleteObjects, "Number of S3 API DeleteObject(s) calls.", ValueType::Number) \
     M(S3CopyObject, "Number of S3 API CopyObject calls.", ValueType::Number) \
     M(S3ListObjects, "Number of S3 API ListObjects calls.", ValueType::Number) \
+    M(S3ListObjectsMicroseconds, "Time of S3 API ListObjects execution.", ValueType::Microseconds) \
     M(S3HeadObject,  "Number of S3 API HeadObject calls.", ValueType::Number) \
+    M(S3HeadObjectMicroseconds,  "Time of S3 API HeadObject execution.", ValueType::Microseconds) \
     M(S3GetObjectAttributes, "Number of S3 API GetObjectAttributes calls.", ValueType::Number) \
     M(S3CreateMultipartUpload, "Number of S3 API CreateMultipartUpload calls.", ValueType::Number) \
     M(S3UploadPartCopy, "Number of S3 API UploadPartCopy calls.", ValueType::Number) \
@@ -634,6 +641,7 @@ The server successfully detected this situation and will download merged part fr
     M(AzureCopyObject, "Number of Azure blob storage API CopyObject calls", ValueType::Number) \
     M(AzureDeleteObjects, "Number of Azure blob storage API DeleteObject(s) calls.", ValueType::Number) \
     M(AzureListObjects, "Number of Azure blob storage API ListObjects calls.", ValueType::Number) \
+    M(AzureListObjectsMicroseconds, "Time of Azure blob storage API ListObjects execution.", ValueType::Microseconds) \
     M(AzureGetProperties, "Number of Azure blob storage API GetProperties calls.", ValueType::Number) \
     M(AzureCreateContainer, "Number of Azure blob storage API CreateContainer calls.", ValueType::Number) \
     \

src/Core/Settings.cpp

@@ -6873,6 +6873,16 @@ Use roaring bitmap for iceberg positional deletes.
 )", 0) \
     DECLARE(Bool, export_merge_tree_part_overwrite_file_if_exists, false, R"(
 Overwrite file if it already exists when exporting a merge tree part
+)", 0) \
+    DECLARE(Timezone, iceberg_timezone_for_timestamptz, "UTC", R"(
+Timezone for Iceberg timestamptz field.
+
+Possible values:
+
+- Any valid timezone, e.g. `Europe/Berlin`, `UTC` or `Zulu`
+- `` (empty value) - use session timezone
+
+Default value is `UTC`.
 )", 0) \
     \
     /* ####################################################### */ \

src/Core/SettingsChangesHistory.cpp

@@ -47,6 +47,7 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
             {"allow_retries_in_cluster_requests", false, false, "New setting"},
             {"object_storage_remote_initiator", false, false, "New setting."},
             {"allow_experimental_export_merge_tree_part", false, true, "Turned ON by default for Antalya."},
+            {"iceberg_timezone_for_timestamptz", "UTC", "UTC", "New setting."}
         });
         addSettingsChanges(settings_changes_history, "25.8",
         {

src/Databases/DataLake/Common.cpp

@@ -61,14 +61,14 @@ std::vector<String> splitTypeArguments(const String & type_str)
     return args;
 }
 
-DB::DataTypePtr getType(const String & type_name, bool nullable, const String & prefix)
+DB::DataTypePtr getType(const String & type_name, bool nullable, DB::ContextPtr context, const String & prefix)
 {
     String name = trim(type_name);
 
     if (name.starts_with("array<") && name.ends_with(">"))
     {
         String inner = name.substr(6, name.size() - 7);
-        return std::make_shared<DB::DataTypeArray>(getType(inner, nullable));
+        return std::make_shared<DB::DataTypeArray>(getType(inner, nullable, context));
     }
 
     if (name.starts_with("map<") && name.ends_with(">"))
@@ -79,7 +79,7 @@ DB::DataTypePtr getType(const String & type_name, bool nullable, const String &
         if (args.size() != 2)
             throw DB::Exception(DB::ErrorCodes::DATALAKE_DATABASE_ERROR, "Invalid data type {}", type_name);
 
-        return std::make_shared<DB::DataTypeMap>(getType(args[0], false), getType(args[1], nullable));
+        return std::make_shared<DB::DataTypeMap>(getType(args[0], false, context), getType(args[1], nullable, context));
     }
 
     if (name.starts_with("struct<") && name.ends_with(">"))
@@ -101,13 +101,13 @@ DB::DataTypePtr getType(const String & type_name, bool nullable, const String &
             String full_field_name = prefix.empty() ? field_name : prefix + "." + field_name;
 
             field_names.push_back(full_field_name);
-            field_types.push_back(getType(field_type, nullable, full_field_name));
+            field_types.push_back(getType(field_type, nullable, context, full_field_name));
         }
         return std::make_shared<DB::DataTypeTuple>(field_types, field_names);
     }
 
-    return nullable ? DB::makeNullable(DB::Iceberg::IcebergSchemaProcessor::getSimpleType(name))
-                    : DB::Iceberg::IcebergSchemaProcessor::getSimpleType(name);
+    return nullable ? DB::makeNullable(DB::Iceberg::IcebergSchemaProcessor::getSimpleType(name, context))
+                    : DB::Iceberg::IcebergSchemaProcessor::getSimpleType(name, context);
 }
 
 std::pair<std::string, std::string> parseTableName(const std::string & name)

src/Databases/DataLake/Common.h

@@ -2,6 +2,7 @@
 
 #include <Core/NamesAndTypes.h>
 #include <Core/Types.h>
+#include <Interpreters/Context_fwd.h>
 
 namespace DataLake
 {
@@ -10,7 +11,7 @@ String trim(const String & str);
 
 std::vector<String> splitTypeArguments(const String & type_str);
 
-DB::DataTypePtr getType(const String & type_name, bool nullable, const String & prefix = "");
+DB::DataTypePtr getType(const String & type_name, bool nullable, DB::ContextPtr context, const String & prefix = "");
 
 /// Parse a string, containing at least one dot, into a two substrings:
 /// A.B.C.D.E -> A.B.C.D and E, where

src/Databases/DataLake/DatabaseDataLake.cpp

@@ -326,7 +326,7 @@ StoragePtr DatabaseDataLake::tryGetTableImpl(const String & name, ContextPtr con
 
     auto [namespace_name, table_name] = DataLake::parseTableName(name);
 
-    if (!catalog->tryGetTableMetadata(namespace_name, table_name, table_metadata))
+    if (!catalog->tryGetTableMetadata(namespace_name, table_name, context_, table_metadata))
         return nullptr;
 
     if (ignore_if_not_iceberg && !table_metadata.isDefaultReadableTable())
@@ -633,15 +633,15 @@ ASTPtr DatabaseDataLake::getCreateDatabaseQuery() const
 
 ASTPtr DatabaseDataLake::getCreateTableQueryImpl(
     const String & name,
-    ContextPtr /* context_ */,
+    ContextPtr context_,
     bool /* throw_on_error */) const
 {
     auto catalog = getCatalog();
     auto table_metadata = DataLake::TableMetadata().withLocation().withSchema();
 
     const auto [namespace_name, table_name] = DataLake::parseTableName(name);
 
-    if (!catalog->tryGetTableMetadata(namespace_name, table_name, table_metadata))
+    if (!catalog->tryGetTableMetadata(namespace_name, table_name, context_, table_metadata))
     {
         throw Exception(
             ErrorCodes::CANNOT_GET_CREATE_TABLE_QUERY, "Table `{}` doesn't exist", name);

src/Databases/DataLake/GlueCatalog.cpp

@@ -276,6 +276,7 @@ bool GlueCatalog::existsTable(const std::string & database_name, const std::stri
 bool GlueCatalog::tryGetTableMetadata(
     const std::string & database_name,
     const std::string & table_name,
+    DB::ContextPtr /* context_ */,
     TableMetadata & result) const
 {
     Aws::Glue::Model::GetTableRequest request;
@@ -372,7 +373,7 @@ bool GlueCatalog::tryGetTableMetadata(
                         column_type = "timestamptz";
                 }
 
-                schema.push_back({column.GetName(), getType(column_type, can_be_nullable)});
+                schema.push_back({column.GetName(), getType(column_type, can_be_nullable, getContext())});
             }
             result.setSchema(schema);
         }
@@ -394,9 +395,10 @@ bool GlueCatalog::tryGetTableMetadata(
 void GlueCatalog::getTableMetadata(
     const std::string & database_name,
     const std::string & table_name,
+    DB::ContextPtr context_,
     TableMetadata & result) const
 {
-    if (!tryGetTableMetadata(database_name, table_name, result))
+    if (!tryGetTableMetadata(database_name, table_name, context_, result))
     {
         throw DB::Exception(
             DB::ErrorCodes::DATALAKE_DATABASE_ERROR,

src/Databases/DataLake/GlueCatalog.h

@@ -40,11 +40,13 @@ class GlueCatalog final : public ICatalog, private DB::WithContext
     void getTableMetadata(
         const std::string & database_name,
         const std::string & table_name,
+        DB::ContextPtr context_,
         TableMetadata & result) const override;
 
     bool tryGetTableMetadata(
         const std::string & database_name,
         const std::string & table_name,
+        DB::ContextPtr context_,
         TableMetadata & result) const override;
 
     std::optional<StorageType> getStorageType() const override

src/Databases/DataLake/HiveCatalog.cpp

@@ -96,13 +96,21 @@ bool HiveCatalog::existsTable(const std::string & namespace_name, const std::str
     return true;
 }
 
-void HiveCatalog::getTableMetadata(const std::string & namespace_name, const std::string & table_name, TableMetadata & result) const
+void HiveCatalog::getTableMetadata(
+    const std::string & namespace_name,
+    const std::string & table_name,
+    DB::ContextPtr context_,
+    TableMetadata & result) const
 {
-    if (!tryGetTableMetadata(namespace_name, table_name, result))
+    if (!tryGetTableMetadata(namespace_name, table_name, context_, result))
         throw DB::Exception(DB::ErrorCodes::DATALAKE_DATABASE_ERROR, "No response from iceberg catalog");
 }
 
-bool HiveCatalog::tryGetTableMetadata(const std::string & namespace_name, const std::string & table_name, TableMetadata & result) const
+bool HiveCatalog::tryGetTableMetadata(
+    const std::string & namespace_name,
+    const std::string & table_name,
+    DB::ContextPtr context_,
+    TableMetadata & result) const
 {
     Apache::Hadoop::Hive::Table table;
 
@@ -130,7 +138,7 @@ bool HiveCatalog::tryGetTableMetadata(const std::string & namespace_name, const
         auto columns = table.sd.cols;
         for (const auto & column : columns)
         {
-            schema.push_back({column.name, getType(column.type, true)});
+            schema.push_back({column.name, getType(column.type, true, context_)});
         }
         result.setSchema(schema);
     }