Antalya 26.1: Remote initiator improvements

src/Analyzer/FunctionNode.cpp

@@ -12,6 +12,7 @@
 #include <DataTypes/DataTypeSet.h>
 
 #include <Parsers/ASTFunction.h>
+#include <Parsers/ASTSetQuery.h>
 
 #include <Functions/IFunction.h>
 
@@ -164,14 +165,21 @@ void FunctionNode::dumpTreeImpl(WriteBuffer & buffer, FormatState & format_state
         buffer << '\n' << std::string(indent + 2, ' ') << "WINDOW\n";
         getWindowNode()->dumpTreeImpl(buffer, format_state, indent + 4);
     }
+
+    if (!settings_changes.empty())
+    {
+        buffer << '\n' << std::string(indent + 2, ' ') << "SETTINGS";
+        for (const auto & change : settings_changes)
+            buffer << fmt::format(" {}={}", change.name, fieldToString(change.value));
+    }
 }
 
 bool FunctionNode::isEqualImpl(const IQueryTreeNode & rhs, CompareOptions compare_options) const
 {
     const auto & rhs_typed = assert_cast<const FunctionNode &>(rhs);
     if (function_name != rhs_typed.function_name || isAggregateFunction() != rhs_typed.isAggregateFunction()
         || isOrdinaryFunction() != rhs_typed.isOrdinaryFunction() || isWindowFunction() != rhs_typed.isWindowFunction()
-        || nulls_action != rhs_typed.nulls_action)
+        || nulls_action != rhs_typed.nulls_action || settings_changes != rhs_typed.settings_changes)
         return false;
 
     /// is_operator is ignored here because it affects only AST formatting
@@ -206,6 +214,17 @@ void FunctionNode::updateTreeHashImpl(HashState & hash_state, CompareOptions com
     hash_state.update(isWindowFunction());
     hash_state.update(nulls_action);
 
+    hash_state.update(settings_changes.size());
+    for (const auto & change : settings_changes)
+    {
+        hash_state.update(change.name.size());
+        hash_state.update(change.name);
+
+        const auto & value_dump = change.value.dump();
+        hash_state.update(value_dump.size());
+        hash_state.update(value_dump);
+    }
+
     /// is_operator is ignored here because it affects only AST formatting
 
     if (!compare_options.compare_types)
@@ -230,6 +249,7 @@ QueryTreeNodePtr FunctionNode::cloneImpl() const
     result_function->nulls_action = nulls_action;
     result_function->wrap_with_nullable = wrap_with_nullable;
     result_function->is_operator = is_operator;
+    result_function->settings_changes = settings_changes;
 
     return result_function;
 }
@@ -292,6 +312,14 @@ ASTPtr FunctionNode::toASTImpl(const ConvertToASTOptions & options) const
             function_ast->window_definition = window_node->toAST(new_options);
     }
 
+    if (!settings_changes.empty())
+    {
+        auto settings_ast = make_intrusive<ASTSetQuery>();
+        settings_ast->changes = settings_changes;
+        settings_ast->is_standalone = false;
+        function_ast->arguments->children.push_back(settings_ast);
+    }
+
     return function_ast;
 }
 

src/Analyzer/FunctionNode.h

@@ -10,6 +10,7 @@
 #include <Functions/IFunction.h>
 #include <Parsers/NullsAction.h>
 #include <Common/typeid_cast.h>
+#include <Common/SettingsChanges.h>
 
 namespace DB
 {
@@ -204,6 +205,18 @@ class FunctionNode final : public IQueryTreeNode
             wrap_with_nullable = true;
     }
 
+    /// Get settings changes passed to table function
+    const SettingsChanges & getSettingsChanges() const
+    {
+        return settings_changes;
+    }
+
+    /// Set settings changes passed as last argument to table function
+    void setSettingsChanges(SettingsChanges settings_changes_)
+    {
+        settings_changes = std::move(settings_changes_);
+    }
+
     void dumpTreeImpl(WriteBuffer & buffer, FormatState & format_state, size_t indent) const override;
 
 protected:
@@ -228,6 +241,8 @@ class FunctionNode final : public IQueryTreeNode
     static constexpr size_t arguments_child_index = 1;
     static constexpr size_t window_child_index = 2;
     static constexpr size_t children_size = window_child_index + 1;
+
+    SettingsChanges settings_changes;
 };
 
 }

src/Analyzer/QueryTreeBuilder.cpp

@@ -699,7 +699,12 @@ QueryTreeNodePtr QueryTreeBuilder::buildExpression(const ASTPtr & expression, co
                 {
                     const auto & function_arguments_list = function->arguments->as<ASTExpressionList>()->children;
                     for (const auto & argument : function_arguments_list)
-                        function_node->getArguments().getNodes().push_back(buildExpression(argument, context));
+                    {
+                        if (const auto * ast_set = argument->as<ASTSetQuery>())
+                            function_node->setSettingsChanges(ast_set->changes);
+                        else
+                            function_node->getArguments().getNodes().push_back(buildExpression(argument, context));
+                    }
                 }
 
                 if (function->is_window_function)

src/Analyzer/Resolve/QueryAnalyzer.cpp

@@ -3861,6 +3861,7 @@ void QueryAnalyzer::resolveTableFunction(QueryTreeNodePtr & table_function_node,
             {
                 auto table_function_node_to_resolve_typed = std::make_shared<TableFunctionNode>(table_function_argument_function_name);
                 table_function_node_to_resolve_typed->getArgumentsNode() = table_function_argument_function->getArgumentsNode();
+                table_function_node_to_resolve_typed->setSettingsChanges(table_function_argument_function->getSettingsChanges());
 
                 QueryTreeNodePtr table_function_node_to_resolve = std::move(table_function_node_to_resolve_typed);
                 if (table_function_argument_function_name == "view")

src/Core/Settings.cpp

@@ -7640,6 +7640,9 @@ Rewrite expressions like 'x IN subquery' to JOIN. This might be useful for optim
 )", EXPERIMENTAL) \
     DECLARE(Bool, object_storage_remote_initiator, false, R"(
 Execute request to object storage as remote on one of object_storage_cluster nodes.
+)", EXPERIMENTAL) \
+    DECLARE(String, object_storage_remote_initiator_cluster, "", R"(
+Cluster to choose remote initiator, when `object_storage_remote_initiator` is true. When empty, `object_storage_cluster` is used.
 )", EXPERIMENTAL) \
     DECLARE(Bool, allow_experimental_iceberg_read_optimization, true, R"(
 Allow Iceberg read optimization based on Iceberg metadata.

src/Core/SettingsChangesHistory.cpp

@@ -42,9 +42,9 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
         addSettingsChanges(settings_changes_history, "26.1.3.20001.altinityantalya",
         {
             {"iceberg_partition_timezone", "", "", "New setting."},
-            // {"object_storage_max_nodes", 0, 0, "Antalya: New setting"},
             {"s3_propagate_credentials_to_other_storages", false, false, "New setting"},
             {"export_merge_tree_part_filename_pattern", "", "{part_name}_{checksum}", "New setting"},
+            {"object_storage_remote_initiator_cluster", "", "", "New setting."},
         });
         addSettingsChanges(settings_changes_history, "26.1",
         {
@@ -245,26 +245,19 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
             {"object_storage_cluster_join_mode", "allow", "allow", "New setting"},
             {"lock_object_storage_task_distribution_ms", 500, 500, "New setting."},
             {"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."},
             {"export_merge_tree_part_overwrite_file_if_exists", false, false, "New setting."},
             {"export_merge_tree_partition_force_export", false, false, "New setting."},
             {"export_merge_tree_partition_max_retries", 3, 3, "New setting."},
             {"export_merge_tree_partition_manifest_ttl", 180, 180, "New setting."},
             {"export_merge_tree_part_file_already_exists_policy", "skip", "skip", "New setting."},
-        //     {"iceberg_timezone_for_timestamptz", "UTC", "UTC", "New setting."},
             {"hybrid_table_auto_cast_columns", true, true, "New setting to automatically cast Hybrid table columns when segments disagree on types. Default enabled."},
             {"allow_experimental_hybrid_table", false, false, "Added new setting to allow the Hybrid table engine."},
             {"enable_alias_marker", true, true, "New setting."},
-        //     {"input_format_parquet_use_native_reader_v3", false, true, "Seems stable"},
-        //     {"input_format_parquet_verify_checksums", true, true, "New setting."},
-        //     {"output_format_parquet_write_checksums", false, true, "New setting."},
             {"export_merge_tree_part_max_bytes_per_file", 0, 0, "New setting."},
             {"export_merge_tree_part_max_rows_per_file", 0, 0, "New setting."},
             {"export_merge_tree_partition_lock_inside_the_task", false, false, "New setting."},
             {"export_merge_tree_partition_system_table_prefer_remote_information", true, true, "New setting."},
-        //     {"cluster_table_function_split_granularity", "file", "file", "New setting."},
-        //     {"cluster_table_function_buckets_batch_size", 0, 0, "New setting."},
             {"export_merge_tree_part_throw_on_pending_mutations", true, true, "New setting."},
             {"export_merge_tree_part_throw_on_pending_patch_parts", true, true, "New setting."},
             {"object_storage_cluster", "", "", "Antalya: New setting"},

src/Storages/IStorageCluster.cpp

@@ -49,11 +49,10 @@ namespace Setting
     extern const SettingsBool async_query_sending_for_remote;
     extern const SettingsBool async_socket_for_remote;
     extern const SettingsBool skip_unavailable_shards;
-    extern const SettingsBool parallel_replicas_local_plan;
-    extern const SettingsString cluster_for_parallel_replicas;
     extern const SettingsNonZeroUInt64 max_parallel_replicas;
     extern const SettingsUInt64 object_storage_max_nodes;
     extern const SettingsBool object_storage_remote_initiator;
+    extern const SettingsString object_storage_remote_initiator_cluster;
     extern const SettingsObjectStorageClusterJoinMode object_storage_cluster_join_mode;
 }
 
@@ -330,8 +329,6 @@ void IStorageCluster::read(
 
     const auto & settings = context->getSettingsRef();
 
-    auto cluster = getClusterImpl(context, cluster_name_from_settings, isObjectStorage() ? settings[Setting::object_storage_max_nodes] : 0);
-
     /// Calculate the header. This is significant, because some columns could be thrown away in some cases like query with count(*)
 
     SharedHeader sample_block;
@@ -354,7 +351,11 @@ void IStorageCluster::read(
 
     if (settings[Setting::object_storage_remote_initiator])
     {
-        auto storage_and_context = convertToRemote(cluster, context, cluster_name_from_settings, query_to_send);
+        auto remote_initiator_cluster_name = settings[Setting::object_storage_remote_initiator_cluster].value;
+        if (remote_initiator_cluster_name.empty())
+            remote_initiator_cluster_name = cluster_name_from_settings;
+        auto remote_initiator_cluster = getClusterImpl(context, remote_initiator_cluster_name);
+        auto storage_and_context = convertToRemote(remote_initiator_cluster, context, remote_initiator_cluster_name, query_to_send);
         auto src_distributed = std::dynamic_pointer_cast<StorageDistributed>(storage_and_context.storage);
         auto modified_query_info = query_info;
         modified_query_info.cluster = src_distributed->getCluster();
@@ -363,6 +364,8 @@ void IStorageCluster::read(
         return;
     }
 
+    auto cluster = getClusterImpl(context, cluster_name_from_settings, isObjectStorage() ? settings[Setting::object_storage_max_nodes] : 0);
+
     RestoreQualifiedNamesVisitor::Data data;
     data.distributed_table = DatabaseAndTableWithAlias(*getTableExpression(query_to_send->as<ASTSelectQuery &>(), 0));
     data.remote_table.database = context->getCurrentDatabase();
@@ -396,6 +399,10 @@ IStorageCluster::RemoteCallVariables IStorageCluster::convertToRemote(
     const std::string & cluster_name_from_settings,
     ASTPtr query_to_send)
 {
+    /// TODO: Allow to use secret for remote queries
+    if (!cluster->getSecret().empty())
+        throw Exception(ErrorCodes::NOT_IMPLEMENTED, "Can't convert query to remote when cluster uses secret");
+
     auto host_addresses = cluster->getShardsAddresses();
     if (host_addresses.empty())
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Empty cluster {}", cluster_name_from_settings);
@@ -436,7 +443,18 @@ IStorageCluster::RemoteCallVariables IStorageCluster::convertToRemote(
     if (!table_expression)
         throw Exception(ErrorCodes::LOGICAL_ERROR, "Can't find table expression");
 
-    auto remote_query = makeASTFunction(remote_function_name, make_intrusive<ASTLiteral>(host_name), table_expression->table_function);
+    boost::intrusive_ptr<ASTFunction> remote_query;
+
+    if (shard_addresses[0].user_specified)
+    {
+        remote_query = makeASTFunction(remote_function_name,
+            make_intrusive<ASTLiteral>(host_name),
+            table_expression->table_function,
+            make_intrusive<ASTLiteral>(shard_addresses[0].user),
+            make_intrusive<ASTLiteral>(shard_addresses[0].password));
+    }
+    else
+        remote_query = makeASTFunction(remote_function_name, make_intrusive<ASTLiteral>(host_name), table_expression->table_function);
 
     table_expression->table_function = remote_query;
 

src/Storages/StorageDistributed.cpp

@@ -1057,6 +1057,7 @@ QueryTreeNodePtr buildQueryTreeDistributed(SelectQueryInfo & query_info,
 
         auto table_function_node = std::make_shared<TableFunctionNode>(remote_table_function_node.getFunctionName());
         table_function_node->getArgumentsNode() = remote_table_function_node.getArgumentsNode();
+        table_function_node->setSettingsChanges(remote_table_function_node.getSettingsChanges());
 
         if (table_expression_modifiers)
             table_function_node->setTableExpressionModifiers(*table_expression_modifiers);

src/TableFunctions/ITableFunctionCluster.h

@@ -75,9 +75,11 @@ class ITableFunctionCluster : public Base
 
         /// Cluster name is always the first
         cluster_name = checkAndGetLiteralArgument<String>(args[0], "cluster_name");
-
-        if (!context->tryGetCluster(cluster_name))
-            throw Exception(ErrorCodes::CLUSTER_DOESNT_EXIST, "Requested cluster '{}' not found", cluster_name);
+        /// Remove check cluster existing here
+        /// In query like
+        /// remote('remote_host', xxxCluster('remote_cluster', ...))
+        /// 'remote_cluster' can be defined only on 'remote_host'
+        /// If cluster not exists, query falls later
 
         /// Just cut the first arg (cluster_name) and try to parse other table function arguments as is
         args.erase(args.begin());

tests/integration/test_s3_cluster/configs/cluster.xml

@@ -76,6 +76,39 @@
         </shard>
     </cluster_with_dots>
 
+    <cluster_with_username_and_password>
+        <shard>
+            <replica>
+                <host>s0_0_1</host>
+                <port>9000</port>
+                <user>foo</user>
+                <password>bar</password>
+            </replica>
+            <replica>
+                <host>s0_1_0</host>
+                <port>9000</port>
+                <user>foo</user>
+                <password>bar</password>
+            </replica>
+        </shard>
+    </cluster_with_username_and_password>
+
+    <cluster_with_secret>
+        <secret>baz</secret>
+        <shard>
+            <replica>
+                <host>s0_0_1</host>
+                <port>9000</port>
+                <user>foo</user>
+            </replica>
+            <replica>
+                <host>s0_1_0</host>
+                <port>9000</port>
+                <user>foo</user>
+            </replica>
+        </shard>
+    </cluster_with_secret>
+
     <cluster_all>
         <shard>
             <replica>

tests/integration/test_s3_cluster/configs/hidden_clusters.xml

@@ -0,0 +1,20 @@
+<clickhouse>
+  <remote_servers>
+    <hidden_cluster_with_username_and_password>
+        <shard>
+            <replica>
+                <host>s0_0_1</host>
+                <port>9000</port>
+                <user>foo</user>
+                <password>bar</password>
+            </replica>
+            <replica>
+                <host>s0_1_0</host>
+                <port>9000</port>
+                <user>foo</user>
+                <password>bar</password>
+            </replica>
+        </shard>
+    </hidden_cluster_with_username_and_password>
+  </remote_servers>
+</clickhouse>

tests/integration/test_s3_cluster/configs/users.xml

@@ -5,5 +5,9 @@
             <profile>default</profile>
             <named_collection_control>1</named_collection_control>
         </default>
+        <foo>
+            <password>bar</password>
+            <profile>default</profile>
+        </foo>
     </users>
 </clickhouse>