26.1 Antalya port - Alternative syntax for cluster functions

src/Analyzer/FunctionSecretArgumentsFinderTreeNode.h

@@ -71,8 +71,14 @@ class FunctionTreeNodeImpl : public AbstractFunction
     {
     public:
         explicit ArgumentsTreeNode(const QueryTreeNodes * arguments_) : arguments(arguments_) {}
-        size_t size() const override { return arguments ? arguments->size() : 0; }
-        std::unique_ptr<Argument> at(size_t n) const override { return std::make_unique<ArgumentTreeNode>(arguments->at(n).get()); }
+        size_t size() const override
+        { /// size withous skipped indexes
+            return arguments ? arguments->size() - skippedSize() : 0;
+        }
+        std::unique_ptr<Argument> at(size_t n) const override
+        { /// n is relative index, some can be skipped
+            return std::make_unique<ArgumentTreeNode>(arguments->at(getRealIndex(n)).get());
+        }
     private:
         const QueryTreeNodes * arguments = nullptr;
     };

src/Core/Settings.cpp

@@ -7441,6 +7441,15 @@ Enable PRQL - an alternative to SQL.
 )", EXPERIMENTAL) \
     DECLARE(Bool, enable_adaptive_memory_spill_scheduler, false, R"(
 Trigger processor to spill data into external storage adpatively. grace join is supported at present.
+)", EXPERIMENTAL) \
+    DECLARE(String, object_storage_cluster, "", R"(
+Cluster to make distributed requests to object storages with alternative syntax.
+)", EXPERIMENTAL) \
+    DECLARE(UInt64, object_storage_max_nodes, 0, R"(
+Limit for hosts used for request in object storage cluster table functions - azureBlobStorageCluster, s3Cluster, hdfsCluster, etc.
+Possible values:
+- Positive integer.
+- 0 — All hosts in cluster.
 )", EXPERIMENTAL) \
     DECLARE(Bool, allow_experimental_delta_kernel_rs, true, R"(
 Allow experimental delta-kernel-rs implementation.

src/Core/SettingsChangesHistory.cpp

@@ -39,6 +39,11 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
         /// controls new feature and it's 'true' by default, use 'false' as previous_value).
         /// It's used to implement `compatibility` setting (see https://github.com/ClickHouse/ClickHouse/issues/35972)
         /// Note: please check if the key already exists to prevent duplicate entries.
+        addSettingsChanges(settings_changes_history, "26.1.1.2000",
+        {
+            {"object_storage_cluster", "", "", "Antalya: New setting"},
+            {"object_storage_max_nodes", 0, 0, "Antalya: New setting"},
+        });
         addSettingsChanges(settings_changes_history, "26.1",
         {
             {"parallel_replicas_filter_pushdown", false, false, "New setting"},
@@ -312,6 +317,15 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
             {"allow_experimental_insert_into_iceberg", false, false, "New setting."},
             /// RELEASE CLOSED
         });
+        addSettingsChanges(settings_changes_history, "25.6.5.2000",
+        {
+            {"allow_experimental_database_iceberg", false, true, "Turned ON by default for Antalya"},
+            {"allow_experimental_database_unity_catalog", false, true, "Turned ON by default for Antalya"},
+            {"allow_experimental_database_glue_catalog", false, true, "Turned ON by default for Antalya"},
+            {"output_format_parquet_enum_as_byte_array", true, true, "Enable writing Enum as byte array in Parquet by default"},
+            {"object_storage_cluster", "", "", "New setting"},
+            {"object_storage_max_nodes", 0, 0, "New setting"},
+        });
         addSettingsChanges(settings_changes_history, "25.6",
         {
             /// RELEASE CLOSED

src/Databases/DataLake/DatabaseDataLake.cpp

@@ -55,6 +55,7 @@ namespace DatabaseDataLakeSetting
     extern const DatabaseDataLakeSettingsString oauth_server_uri;
     extern const DatabaseDataLakeSettingsBool oauth_server_use_request_body;
     extern const DatabaseDataLakeSettingsBool vended_credentials;
+    extern const DatabaseDataLakeSettingsString object_storage_cluster;
     extern const DatabaseDataLakeSettingsString aws_access_key_id;
     extern const DatabaseDataLakeSettingsString aws_secret_access_key;
     extern const DatabaseDataLakeSettingsString region;
@@ -241,7 +242,7 @@ std::shared_ptr<DataLake::ICatalog> DatabaseDataLake::getCatalog() const
     return catalog_impl;
 }
 
-std::shared_ptr<StorageObjectStorageConfiguration> DatabaseDataLake::getConfiguration(
+StorageObjectStorageConfigurationPtr DatabaseDataLake::getConfiguration(
     DatabaseDataLakeStorageType type,
     DataLakeStorageSettingsPtr storage_settings) const
 {
@@ -567,7 +568,7 @@ StoragePtr DatabaseDataLake::tryGetTableImpl(const String & name, ContextPtr con
 
     /// with_table_structure = false: because there will be
     /// no table structure in table definition AST.
-    StorageObjectStorageConfiguration::initialize(*configuration, args, context_copy, /* with_table_structure */false);
+    configuration->initialize(args, context_copy, /* with_table_structure */false);
 
     const auto & query_settings = context_->getSettingsRef();
 
@@ -579,49 +580,34 @@ StoragePtr DatabaseDataLake::tryGetTableImpl(const String & name, ContextPtr con
 
     const auto is_secondary_query = context_->getClientInfo().query_kind == ClientInfo::QueryKind::SECONDARY_QUERY;
 
-    if (can_use_parallel_replicas && !is_secondary_query)
-    {
-        auto storage_cluster = std::make_shared<StorageObjectStorageCluster>(
-            parallel_replicas_cluster_name,
-            configuration,
-            configuration->createObjectStorage(context_copy, /* is_readonly */ false),
-            StorageID(getDatabaseName(), name),
-            columns,
-            ConstraintsDescription{},
-            nullptr,
-            context_,
-            /// Use is_table_function = true,
-            /// because this table is actually stateless like a table function.
-            /* is_table_function */true);
-
-        storage_cluster->startup();
-        return storage_cluster;
-    }
+    std::string cluster_name = configuration->isClusterSupported() ? settings[DatabaseDataLakeSetting::object_storage_cluster].value : "";
 
-    bool can_use_distributed_iterator =
-        context_->getClientInfo().collaborate_with_initiator &&
-        can_use_parallel_replicas;
+    if (cluster_name.empty() && can_use_parallel_replicas && !is_secondary_query)
+        cluster_name = parallel_replicas_cluster_name;
 
-    return std::make_shared<StorageObjectStorage>(
+    auto storage_cluster = std::make_shared<StorageObjectStorageCluster>(
+        cluster_name,
         configuration,
         configuration->createObjectStorage(context_copy, /* is_readonly */ false),
-        context_copy,
         StorageID(getDatabaseName(), name),
         /* columns */columns,
         /* constraints */ConstraintsDescription{},
-        /* comment */"",
+        /* partition_by */nullptr,
+        /* order_by */nullptr,
+        context_copy,
+        /* comment */ "",
         getFormatSettings(context_copy),
         LoadingStrictnessLevel::CREATE,
         getCatalog(),
         /* if_not_exists*/true,
         /* is_datalake_query*/true,
-        /* distributed_processing */can_use_distributed_iterator,
-        /* partition_by */nullptr,
-        /* order_by */nullptr,
         /// Use is_table_function = true,
         /// because this table is actually stateless like a table function.
         /* is_table_function */true,
         /* lazy_init */true);
+
+    storage_cluster->startup();
+    return storage_cluster;
 }
 
 void DatabaseDataLake::dropTable( /// NOLINT

src/Databases/DataLake/DatabaseDataLake.h

@@ -84,7 +84,7 @@ class DatabaseDataLake final : public IDatabase, WithContext
     void validateSettings();
     std::shared_ptr<DataLake::ICatalog> getCatalog() const;
 
-    std::shared_ptr<StorageObjectStorageConfiguration> getConfiguration(
+    StorageObjectStorageConfigurationPtr getConfiguration(
         DatabaseDataLakeStorageType type,
         DataLakeStorageSettingsPtr storage_settings) const;
 

src/Databases/DataLake/GlueCatalog.cpp

@@ -513,7 +513,7 @@ GlueCatalog::ObjectStorageWithPath GlueCatalog::createObjectStorageForEarlyTable
     auto storage_settings = std::make_shared<DB::DataLakeStorageSettings>();
     storage_settings->loadFromSettingsChanges(settings.allChanged());
     auto configuration = std::make_shared<DB::StorageS3IcebergConfiguration>(storage_settings);
-    DB::StorageObjectStorageConfiguration::initialize(*configuration, args, getContext(), false);
+    configuration->initialize(args, getContext(), false);
 
     auto object_storage = configuration->createObjectStorage(getContext(), true);
 

src/Disks/DiskType.cpp

@@ -10,7 +10,7 @@ namespace ErrorCodes
     extern const int LOGICAL_ERROR;
 }
 
-MetadataStorageType metadataTypeFromString(const String & type)
+MetadataStorageType metadataTypeFromString(const std::string & type)
 {
     auto check_type = Poco::toLower(type);
     if (check_type == "local")
@@ -58,25 +58,7 @@ String DataSourceDescription::name() const
         case DataSourceType::RAM:
             return "memory";
         case DataSourceType::ObjectStorage:
-        {
-            switch (object_storage_type)
-            {
-                case ObjectStorageType::S3:
-                    return "s3";
-                case ObjectStorageType::HDFS:
-                    return "hdfs";
-                case ObjectStorageType::Azure:
-                    return "azure_blob_storage";
-                case ObjectStorageType::Local:
-                    return "local_blob_storage";
-                case ObjectStorageType::Web:
-                    return "web";
-                case ObjectStorageType::None:
-                    return "none";
-                case ObjectStorageType::Max:
-                    throw Exception(ErrorCodes::LOGICAL_ERROR, "Unexpected object storage type: Max");
-            }
-        }
+            return DB::toString(object_storage_type);
     }
 }
 
@@ -86,4 +68,45 @@ String DataSourceDescription::toString() const
                        name(), description, is_encrypted, is_cached, zookeeper_name);
 }
 
+ObjectStorageType objectStorageTypeFromString(const std::string & type)
+{
+    auto check_type = Poco::toLower(type);
+    if (check_type == "s3")
+        return ObjectStorageType::S3;
+    if (check_type == "hdfs")
+        return ObjectStorageType::HDFS;
+    if (check_type == "azure_blob_storage" || check_type == "azure")
+        return ObjectStorageType::Azure;
+    if (check_type == "local_blob_storage" || check_type == "local")
+        return ObjectStorageType::Local;
+    if (check_type == "web")
+        return ObjectStorageType::Web;
+    if (check_type == "none")
+        return ObjectStorageType::None;
+
+    throw Exception(ErrorCodes::UNKNOWN_ELEMENT_IN_CONFIG,
+        "Unknown object storage type: {}", type);
+}
+
+std::string toString(ObjectStorageType type)
+{
+    switch (type)
+    {
+        case ObjectStorageType::S3:
+            return "s3";
+        case ObjectStorageType::HDFS:
+            return "hdfs";
+        case ObjectStorageType::Azure:
+            return "azure_blob_storage";
+        case ObjectStorageType::Local:
+            return "local_blob_storage";
+        case ObjectStorageType::Web:
+            return "web";
+        case ObjectStorageType::None:
+            return "none";
+        case ObjectStorageType::Max:
+            throw Exception(ErrorCodes::LOGICAL_ERROR, "Unexpected object storage type: Max");
+    }
+}
+
 }

src/Disks/DiskType.h

@@ -36,7 +36,10 @@ enum class MetadataStorageType : uint8_t
     Memory,
 };
 
-MetadataStorageType metadataTypeFromString(const String & type);
+MetadataStorageType metadataTypeFromString(const std::string & type);
+
+ObjectStorageType objectStorageTypeFromString(const std::string & type);
+std::string toString(ObjectStorageType type);
 
 struct DataSourceDescription
 {

src/Interpreters/Cluster.cpp

@@ -741,9 +741,9 @@ void Cluster::initMisc()
     }
 }
 
-std::unique_ptr<Cluster> Cluster::getClusterWithReplicasAsShards(const Settings & settings, size_t max_replicas_from_shard) const
+std::unique_ptr<Cluster> Cluster::getClusterWithReplicasAsShards(const Settings & settings, size_t max_replicas_from_shard, size_t max_hosts) const
 {
-    return std::unique_ptr<Cluster>{ new Cluster(ReplicasAsShardsTag{}, *this, settings, max_replicas_from_shard)};
+    return std::unique_ptr<Cluster>{ new Cluster(ReplicasAsShardsTag{}, *this, settings, max_replicas_from_shard, max_hosts)};
 }
 
 std::unique_ptr<Cluster> Cluster::getClusterWithSingleShard(size_t index) const
@@ -792,7 +792,7 @@ void shuffleReplicas(std::vector<Cluster::Address> & replicas, const Settings &
 
 }
 
-Cluster::Cluster(Cluster::ReplicasAsShardsTag, const Cluster & from, const Settings & settings, size_t max_replicas_from_shard)
+Cluster::Cluster(Cluster::ReplicasAsShardsTag, const Cluster & from, const Settings & settings, size_t max_replicas_from_shard, size_t max_hosts)
 {
     if (from.addresses_with_failover.empty())
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Cluster is empty");
@@ -814,6 +814,7 @@ Cluster::Cluster(Cluster::ReplicasAsShardsTag, const Cluster & from, const Setti
 
                 if (address.is_local)
                     info.local_addresses.push_back(address);
+                addresses_with_failover.emplace_back(Addresses({address}));
 
                 auto pool = ConnectionPoolFactory::instance().get(
                     static_cast<unsigned>(settings[Setting::distributed_connections_pool_size]),
@@ -837,9 +838,6 @@ Cluster::Cluster(Cluster::ReplicasAsShardsTag, const Cluster & from, const Setti
                 info.per_replica_pools = {std::move(pool)};
                 info.default_database = address.default_database;
 
-                addresses_with_failover.emplace_back(Addresses{address});
-
-                slot_to_shard.insert(std::end(slot_to_shard), info.weight, shards_info.size());
                 shards_info.emplace_back(std::move(info));
             }
         };
@@ -861,10 +859,37 @@ Cluster::Cluster(Cluster::ReplicasAsShardsTag, const Cluster & from, const Setti
     secret = from.secret;
     name = from.name;
 
+    constrainShardInfoAndAddressesToMaxHosts(max_hosts);
+
+    for (size_t i = 0; i < shards_info.size(); ++i)
+        slot_to_shard.insert(std::end(slot_to_shard), shards_info[i].weight, i);
+
     initMisc();
 }
 
 
+void Cluster::constrainShardInfoAndAddressesToMaxHosts(size_t max_hosts)
+{
+    if (max_hosts == 0 || shards_info.size() <= max_hosts)
+        return;
+
+    pcg64_fast gen{randomSeed()};
+    std::shuffle(shards_info.begin(), shards_info.end(), gen);
+    shards_info.resize(max_hosts);
+
+    AddressesWithFailover addresses_with_failover_;
+
+    UInt32 shard_num = 0;
+    for (auto & shard_info : shards_info)
+    {
+        addresses_with_failover_.push_back(addresses_with_failover[shard_info.shard_num - 1]);
+        shard_info.shard_num = ++shard_num;
+    }
+
+    addresses_with_failover.swap(addresses_with_failover_);
+}
+
+
 Cluster::Cluster(Cluster::SubclusterTag, const Cluster & from, const std::vector<size_t> & indices)
 {
     for (size_t index : indices)

src/Interpreters/Cluster.h

@@ -270,7 +270,7 @@ class Cluster
     std::unique_ptr<Cluster> getClusterWithMultipleShards(const std::vector<size_t> & indices) const;
 
     /// Get a new Cluster that contains all servers (all shards with all replicas) from existing cluster as independent shards.
-    std::unique_ptr<Cluster> getClusterWithReplicasAsShards(const Settings & settings, size_t max_replicas_from_shard = 0) const;
+    std::unique_ptr<Cluster> getClusterWithReplicasAsShards(const Settings & settings, size_t max_replicas_from_shard = 0, size_t max_hosts = 0) const;
 
     /// Returns false if cluster configuration doesn't allow to use it for cross-replication.
     /// NOTE: true does not mean, that it's actually a cross-replication cluster.
@@ -296,7 +296,7 @@ class Cluster
 
     /// For getClusterWithReplicasAsShards implementation
     struct ReplicasAsShardsTag {};
-    Cluster(ReplicasAsShardsTag, const Cluster & from, const Settings & settings, size_t max_replicas_from_shard);
+    Cluster(ReplicasAsShardsTag, const Cluster & from, const Settings & settings, size_t max_replicas_from_shard, size_t max_hosts);
 
     void addShard(
         const Settings & settings,
@@ -308,6 +308,9 @@ class Cluster
         ShardInfoInsertPathForInternalReplication insert_paths = {},
         bool internal_replication = false);
 
+    /// Reduce size of cluster to max_hosts
+    void constrainShardInfoAndAddressesToMaxHosts(size_t max_hosts);
+
     /// Inter-server secret
     String secret;
 

src/Interpreters/InterpreterCreateQuery.cpp

@@ -1991,8 +1991,7 @@ bool InterpreterCreateQuery::doCreateTable(ASTCreateQuery & create,
         auto table_function_ast = create.getChild(*create.as_table_function);
         auto table_function = TableFunctionFactory::instance().get(table_function_ast, getContext());
 
-        if (!table_function->canBeUsedToCreateTable())
-            throw Exception(ErrorCodes::BAD_ARGUMENTS, "Table function '{}' cannot be used to create a table", table_function->getName());
+        table_function->validateUseToCreateTable();
 
         /// In case of CREATE AS table_function() query we should use global context
         /// in storage creation because there will be no query context on server startup