datastore/programs/local/LocalServer.cpp

#include <LocalServer.h>

#include <sys/resource.h>
#include <Common/Config/getLocalConfigPath.h>
#include <Common/CurrentMemoryTracker.h>
#include <Common/logger_useful.h>
#include <Common/formatReadable.h>
#include <Core/Settings.h>
#include <Core/UUID.h>
#include <base/getMemoryAmount.h>
#include <Poco/Util/XMLConfiguration.h>
#include <Poco/String.h>
#include <Poco/Logger.h>
#include <Poco/NullChannel.h>
#include <Poco/SimpleFileChannel.h>
#include <Databases/registerDatabases.h>
#include <Databases/DatabaseFilesystem.h>
#include <Databases/DatabaseMemory.h>
#include <Databases/DatabaseAtomic.h>
#include <Databases/DatabaseOverlay.h>
#include <Storages/System/attachSystemTables.h>
#include <Storages/System/attachInformationSchemaTables.h>
#include <Interpreters/DatabaseCatalog.h>
#include <Interpreters/JIT/CompiledExpressionCache.h>
#include <Interpreters/ProcessList.h>
#include <Interpreters/SystemLog.h>
#include <Interpreters/loadMetadata.h>
#include <Interpreters/registerInterpreters.h>
#include <Access/AccessControl.h>
#include <Access/DiskAccessStorage.h>
#include <Access/MemoryAccessStorage.h>
#include <Common/PoolId.h>
#include <Common/Exception.h>
#include <base/errnoToString.h>
#include <Common/Macros.h>
#include <Common/Config/ConfigProcessor.h>
#include <Common/ThreadStatus.h>
#include <Common/TLDListsHolder.h>
#include <Common/quoteString.h>
#include <Common/ThreadPool.h>
#include <Common/CurrentMetrics.h>
#include <Common/NamedCollections/NamedCollectionsFactory.h>
#include <Common/Jemalloc.h>
#include <Common/StackTrace.h>
#include <Interpreters/FileCache/FileCacheFactory.h>
#include <Loggers/OwnFormattingChannel.h>
#include <Loggers/OwnPatternFormatter.h>
#include <Loggers/OwnSplitChannel.h>
#include <IO/ReadBufferFromFile.h>
#include <IO/ReadBufferFromString.h>
#include <IO/SharedThreadPools.h>
#include <Parsers/ASTAlterQuery.h>
#include <Parsers/ASTInsertQuery.h>
#include <Common/ErrorHandlers.h>
#include <Functions/UserDefined/IUserDefinedSQLObjectsStorage.h>
#include <Functions/registerFunctions.h>
#include <AggregateFunctions/registerAggregateFunctions.h>
#include <TableFunctions/registerTableFunctions.h>
#include <Storages/registerStorages.h>
#include <Dictionaries/registerDictionaries.h>
#include <Disks/registerDisks.h>
#include <Formats/registerFormats.h>
#include <boost/program_options/options_description.hpp>
#include <base/argsToConfig.h>
#include <filesystem>
#include <Common/filesystemHelpers.h>

#include "config.h"

#if USE_AZURE_BLOB_STORAGE
#   include <azure/storage/common/internal/xml_wrapper.hpp>
#endif


namespace fs = std::filesystem;

namespace CurrentMetrics
{
    extern const Metric MemoryTracking;
}

namespace DB
{

namespace Setting
{
    extern const SettingsBool allow_introspection_functions;
    extern const SettingsBool implicit_select;
    extern const SettingsLocalFSReadMethod storage_file_read_method;
}

namespace ServerSetting
{
    extern const ServerSettingsUInt32 allow_feature_tier;
    extern const ServerSettingsDouble cache_size_to_ram_max_ratio;
    extern const ServerSettingsBool jemalloc_collect_global_profile_samples_in_trace_log;
    extern const ServerSettingsBool jemalloc_enable_background_threads;
    extern const ServerSettingsBool jemalloc_enable_global_profiler;
    extern const ServerSettingsUInt64 jemalloc_max_background_threads_num;
    extern const ServerSettingsUInt64 jemalloc_profiler_sampling_rate;
    extern const ServerSettingsUInt64 compiled_expression_cache_elements_size;
    extern const ServerSettingsUInt64 compiled_expression_cache_size;
    extern const ServerSettingsUInt64 database_catalog_drop_table_concurrency;
    extern const ServerSettingsString default_database;
    extern const ServerSettingsString index_mark_cache_policy;
    extern const ServerSettingsUInt64 index_mark_cache_size;
    extern const ServerSettingsDouble index_mark_cache_size_ratio;
    extern const ServerSettingsString index_uncompressed_cache_policy;
    extern const ServerSettingsUInt64 index_uncompressed_cache_size;
    extern const ServerSettingsDouble index_uncompressed_cache_size_ratio;
    extern const ServerSettingsString vector_similarity_index_cache_policy;
    extern const ServerSettingsUInt64 vector_similarity_index_cache_size;
    extern const ServerSettingsUInt64 vector_similarity_index_cache_max_entries;
    extern const ServerSettingsDouble vector_similarity_index_cache_size_ratio;
    extern const ServerSettingsString text_index_tokens_cache_policy;
    extern const ServerSettingsUInt64 text_index_tokens_cache_size;
    extern const ServerSettingsUInt64 text_index_tokens_cache_max_entries;
    extern const ServerSettingsDouble text_index_tokens_cache_size_ratio;
    extern const ServerSettingsString text_index_header_cache_policy;
    extern const ServerSettingsUInt64 text_index_header_cache_size;
    extern const ServerSettingsUInt64 text_index_header_cache_max_entries;
    extern const ServerSettingsDouble text_index_header_cache_size_ratio;
    extern const ServerSettingsString text_index_postings_cache_policy;
    extern const ServerSettingsUInt64 text_index_postings_cache_size;
    extern const ServerSettingsUInt64 text_index_postings_cache_max_entries;
    extern const ServerSettingsDouble text_index_postings_cache_size_ratio;
    extern const ServerSettingsUInt64 io_thread_pool_queue_size;
    extern const ServerSettingsString mark_cache_policy;
    extern const ServerSettingsUInt64 mark_cache_size;
    extern const ServerSettingsDouble mark_cache_size_ratio;
    extern const ServerSettingsString iceberg_metadata_files_cache_policy;
    extern const ServerSettingsUInt64 iceberg_metadata_files_cache_size;
    extern const ServerSettingsUInt64 iceberg_metadata_files_cache_max_entries;
    extern const ServerSettingsDouble iceberg_metadata_files_cache_size_ratio;
    extern const ServerSettingsString parquet_metadata_cache_policy;
    extern const ServerSettingsUInt64 parquet_metadata_cache_size;
    extern const ServerSettingsUInt64 parquet_metadata_cache_max_entries;
    extern const ServerSettingsDouble parquet_metadata_cache_size_ratio;
    extern const ServerSettingsUInt64 max_active_parts_loading_thread_pool_size;
    extern const ServerSettingsUInt64 max_io_thread_pool_free_size;
    extern const ServerSettingsUInt64 max_io_thread_pool_size;
    extern const ServerSettingsUInt64 max_outdated_parts_loading_thread_pool_size;
    extern const ServerSettingsUInt64 max_parts_cleaning_thread_pool_size;
    extern const ServerSettingsUInt64 max_server_memory_usage;
    extern const ServerSettingsDouble max_server_memory_usage_to_ram_ratio;
    extern const ServerSettingsUInt64 max_thread_pool_free_size;
    extern const ServerSettingsUInt64 max_thread_pool_size;
    extern const ServerSettingsUInt64 max_unexpected_parts_loading_thread_pool_size;
    extern const ServerSettingsUInt64 min_allocation_size_to_throw_on_memory_limit;
    extern const ServerSettingsUInt64 mmap_cache_size;
    extern const ServerSettingsBool show_addresses_in_stack_traces;
    extern const ServerSettingsUInt64 thread_pool_queue_size;
    extern const ServerSettingsString uncompressed_cache_policy;
    extern const ServerSettingsUInt64 uncompressed_cache_size;
    extern const ServerSettingsDouble uncompressed_cache_size_ratio;
    extern const ServerSettingsString primary_index_cache_policy;
    extern const ServerSettingsUInt64 primary_index_cache_size;
    extern const ServerSettingsDouble primary_index_cache_size_ratio;
    extern const ServerSettingsUInt64 max_prefixes_deserialization_thread_pool_size;
    extern const ServerSettingsUInt64 max_prefixes_deserialization_thread_pool_free_size;
    extern const ServerSettingsUInt64 prefixes_deserialization_thread_pool_thread_pool_queue_size;
    extern const ServerSettingsUInt64 max_format_parsing_thread_pool_size;
    extern const ServerSettingsUInt64 max_format_parsing_thread_pool_free_size;
    extern const ServerSettingsUInt64 format_parsing_thread_pool_queue_size;
    extern const ServerSettingsUInt64 page_cache_history_window_ms;
    extern const ServerSettingsString page_cache_policy;
    extern const ServerSettingsDouble page_cache_size_ratio;
    extern const ServerSettingsUInt64 page_cache_min_size;
    extern const ServerSettingsUInt64 page_cache_max_size;
    extern const ServerSettingsDouble page_cache_free_memory_ratio;
    extern const ServerSettingsUInt64 page_cache_shards;
    extern const ServerSettingsUInt64 memory_worker_period_ms;
    extern const ServerSettingsDouble memory_worker_purge_dirty_pages_threshold_ratio;
    extern const ServerSettingsDouble memory_worker_purge_total_memory_threshold_ratio;
    extern const ServerSettingsBool memory_worker_correct_memory_tracker;
    extern const ServerSettingsUInt64 memory_worker_decay_adjustment_period_ms;
    extern const ServerSettingsBool memory_worker_use_cgroup;
    extern const ServerSettingsString allowed_disks_for_table_engines;
}

namespace ErrorCodes
{
    extern const int BAD_ARGUMENTS;
    extern const int CANNOT_LOAD_CONFIG;
    extern const int FILE_ALREADY_EXISTS;
    extern const int INVALID_CONFIG_PARAMETER;
}

namespace
{

void applySettingsOverridesForLocal(ContextMutablePtr context)
{
    Settings settings = context->getSettingsCopy();

    settings[Setting::allow_introspection_functions] = true;
    settings[Setting::storage_file_read_method] = LocalFSReadMethod::mmap;
    settings[Setting::implicit_select] = true;

    context->setSettings(settings);
}

}

Poco::Util::LayeredConfiguration & LocalServer::getClientConfiguration()
{
    return config();
}

void LocalServer::processError(std::string_view) const
{
    if (ignore_error)
        return;

    if (is_interactive)
    {
        String message;
        if (server_exception)
        {
            message = getExceptionMessageForLogging(*server_exception, print_stack_trace, true);
        }
        else if (client_exception)
        {
            message = client_exception->message();
        }

        /// musl defines `stderr` as `(stderr)` which triggers `-Wdisabled-macro-expansion`.
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wdisabled-macro-expansion"
        fmt::print(stderr, "Received exception:\n{}\n", message);
        fmt::print(stderr, "\n");
#pragma clang diagnostic pop
    }
    else
    {
        if (server_exception)
            server_exception->rethrow();
        if (client_exception)
            client_exception->rethrow();
    }
}


void LocalServer::initialize(Poco::Util::Application & self)
{
    Poco::Util::Application::initialize(self);

    const char * home_path_cstr = getenv("HOME"); // NOLINT(concurrency-mt-unsafe)
    if (home_path_cstr)
        home_path = home_path_cstr;

    /// Load config files if exists
    std::string config_path;
    if (getClientConfiguration().has("config-file"))
        config_path = getClientConfiguration().getString("config-file");
    else if (config_path.empty() && fs::exists("config.xml"))
        config_path = "config.xml";
    else if (config_path.empty())
        config_path = getLocalConfigPath(home_path).value_or("");

    if (fs::exists(config_path))
    {
        ConfigProcessor config_processor(config_path);
        ConfigProcessor::setConfigPath(fs::path(config_path).parent_path());
        auto loaded_config = config_processor.loadConfig();
        getClientConfiguration().add(loaded_config.configuration.duplicate(), PRIO_DEFAULT, false);
        loaded_config_path = config_path;
    }

    server_settings.loadSettingsFromConfig(config());

#if USE_JEMALLOC
    Jemalloc::setup(
        server_settings[ServerSetting::jemalloc_enable_global_profiler],
        server_settings[ServerSetting::jemalloc_enable_background_threads],
        server_settings[ServerSetting::jemalloc_max_background_threads_num],
        server_settings[ServerSetting::jemalloc_collect_global_profile_samples_in_trace_log],
        server_settings[ServerSetting::jemalloc_profiler_sampling_rate]);
#endif

    GlobalThreadPool::initialize(
        server_settings[ServerSetting::max_thread_pool_size],
        server_settings[ServerSetting::max_thread_pool_free_size],
        server_settings[ServerSetting::thread_pool_queue_size]);

#if USE_AZURE_BLOB_STORAGE
    /// See the explanation near the same line in Server.cpp
    GlobalThreadPool::instance().addOnDestroyCallback([]
    {
        Azure::Storage::_internal::XmlGlobalDeinitialize();
    });
#endif

    getIOThreadPool().initialize(
        server_settings[ServerSetting::max_io_thread_pool_size],
        server_settings[ServerSetting::max_io_thread_pool_free_size],
        server_settings[ServerSetting::io_thread_pool_queue_size]);

    const size_t active_parts_loading_threads = server_settings[ServerSetting::max_active_parts_loading_thread_pool_size];
    getActivePartsLoadingThreadPool().initialize(
        active_parts_loading_threads,
        0, // We don't need any threads one all the parts will be loaded
        active_parts_loading_threads);

    const size_t outdated_parts_loading_threads = server_settings[ServerSetting::max_outdated_parts_loading_thread_pool_size];
    getOutdatedPartsLoadingThreadPool().initialize(
        outdated_parts_loading_threads,
        0, // We don't need any threads one all the parts will be loaded
        outdated_parts_loading_threads);

    getOutdatedPartsLoadingThreadPool().setMaxTurboThreads(active_parts_loading_threads);

    const size_t unexpected_parts_loading_threads = server_settings[ServerSetting::max_unexpected_parts_loading_thread_pool_size];
    getUnexpectedPartsLoadingThreadPool().initialize(
        unexpected_parts_loading_threads,
        0, // We don't need any threads one all the parts will be loaded
        unexpected_parts_loading_threads);

    getUnexpectedPartsLoadingThreadPool().setMaxTurboThreads(active_parts_loading_threads);

    const size_t cleanup_threads = server_settings[ServerSetting::max_parts_cleaning_thread_pool_size];
    getPartsCleaningThreadPool().initialize(
        cleanup_threads,
        0, // We don't need any threads one all the parts will be deleted
        cleanup_threads);

    getDatabaseCatalogDropTablesThreadPool().initialize(
        server_settings[ServerSetting::database_catalog_drop_table_concurrency],
        0, // We don't need any threads if there are no DROP queries.
        server_settings[ServerSetting::database_catalog_drop_table_concurrency]);

    getMergeTreePrefixesDeserializationThreadPool().initialize(
        server_settings[ServerSetting::max_prefixes_deserialization_thread_pool_size],
        server_settings[ServerSetting::max_prefixes_deserialization_thread_pool_free_size],
        server_settings[ServerSetting::prefixes_deserialization_thread_pool_thread_pool_queue_size]);

    getFormatParsingThreadPool().initialize(
        server_settings[ServerSetting::max_format_parsing_thread_pool_size],
        server_settings[ServerSetting::max_format_parsing_thread_pool_free_size],
        server_settings[ServerSetting::format_parsing_thread_pool_queue_size]);
}


namespace
{

DatabasePtr createMemoryDatabaseIfNotExists(ContextPtr context, const String & database_name)
{
    DatabasePtr system_database = DatabaseCatalog::instance().tryGetDatabase(database_name);
    if (!system_database)
    {
        /// TODO: add attachTableDelayed into DatabaseMemory to speedup loading
        system_database = std::make_shared<DatabaseMemory>(database_name, context);
        DatabaseCatalog::instance().attachDatabase(database_name, system_database);
    }
    return system_database;
}

DatabasePtr createClickHouseLocalDatabaseOverlay(const String & name_, ContextPtr context)
{
    auto overlay = std::make_shared<DatabaseOverlay>(name_, context);

    UUID default_database_uuid;

    /// Look up the persisted UUID via the per-database metadata symlink that
    /// `DatabaseAtomic` creates at `metadata/<escapeForFileName(name)>`.
    /// Using a hardcoded `"default"` here means a non-default `default_database`
    /// (e.g. `--default_database=mydb`) silently loses data on restart because
    /// the lookup misses the previous run's symlink and a fresh UUID is picked.
    fs::path existing_path_symlink = fs::weakly_canonical(context->getPath()) / DatabaseCatalog::getMetadataDirPath(name_);
    if (FS::isSymlinkNoThrow(existing_path_symlink))
    {
        auto symlink_path = FS::readSymlink(existing_path_symlink);
        /// If symlink ends with '/':
        if (!symlink_path.has_filename() && symlink_path.has_parent_path())
            symlink_path = symlink_path.parent_path();
        default_database_uuid = parse<UUID>(symlink_path.filename());
    }
    else
        default_database_uuid = UUIDHelpers::generateV4();

    fs::path default_database_metadata_path = fs::weakly_canonical(context->getPath()) /
        DatabaseCatalog::getStoreDirPath(default_database_uuid);

    overlay->registerNextDatabase(std::make_shared<DatabaseAtomic>(name_, default_database_metadata_path, default_database_uuid, context));
    overlay->registerNextDatabase(std::make_shared<DatabaseFilesystem>(name_, "", context));
    return overlay;
}

}

/// If path is specified and not empty, will try to setup server environment and load existing metadata
void LocalServer::tryInitPath()
{
    std::string path;

    if (getClientConfiguration().has("path"))
    {
        /// User-supplied path.
        path = getClientConfiguration().getString("path");
        Poco::trimInPlace(path);

        if (path.empty())
        {
            throw Exception(ErrorCodes::BAD_ARGUMENTS,
                "Cannot work with empty storage path that is explicitly specified"
                " by the --path option. Please check the program options and"
                " correct the --path.");
        }
    }
    else
    {
        /// The user requested to use a temporary path - use a unique path in the system temporary directory
        /// (or in the current dir if a temporary doesn't exist)
        LoggerRawPtr log = &logger();
        std::filesystem::path parent_folder;
        std::filesystem::path default_path;

        try
        {
            /// Try to guess a tmp folder name, and check if it's a directory (throw an exception otherwise).
            parent_folder = std::filesystem::temp_directory_path();

        }
        catch (const fs::filesystem_error & e)
        {
            // The tmp folder doesn't exist? Is it a misconfiguration? Or chroot?
            LOG_DEBUG(log, "Can not get temporary folder: {}", e.what());
            parent_folder = std::filesystem::current_path();

            (void)std::filesystem::is_directory(parent_folder); // checks the path is accessible (may throw on I/O error)
            LOG_DEBUG(log, "Will create working directory inside current directory: {}", parent_folder.string());
        }

        /// we can have another clickhouse-local running simultaneously, even with the same PID (for ex. - several dockers mounting the same folder)
        /// or it can be some leftovers from other clickhouse-local runs
        /// as we can't accurately distinguish those situations we don't touch any existent folders
        /// we just try to pick some free name for our working folder

        default_path = parent_folder / fmt::format("clickhouse-local-{}", UUIDHelpers::generateV4());

        if (fs::exists(default_path))
            throw Exception(ErrorCodes::FILE_ALREADY_EXISTS, "Unsuccessful attempt to set up the working directory: {} already exists.", default_path.string());

        /// The directory can be created lazily during the runtime.
        temporary_directory_to_delete = default_path;

        path = default_path.string();
        LOG_DEBUG(log, "Working directory will be created as needed: {}", path);
    }

    fs::create_directories(path);

    global_context->setPath(fs::path(path) / "");

    global_context->setTemporaryStoragePath(fs::path(path) / "tmp" / "", 1_GiB);
    global_context->setFlagsPath(fs::path(path) / "flags" / "");

    global_context->setUserFilesPath(""); /// user's files are everywhere

    std::string user_scripts_path = getClientConfiguration().getString("user_scripts_path", fs::path(path) / "user_scripts" / "");
    global_context->setUserScriptsPath(user_scripts_path);

    /// Set path for filesystem caches
    String filesystem_caches_path(getClientConfiguration().getString("filesystem_caches_path", fs::path(path) / "cache" / ""));
    if (!filesystem_caches_path.empty())
        global_context->setFilesystemCachesPath(filesystem_caches_path);

    /// top_level_domains_lists
    const std::string & top_level_domains_path = getClientConfiguration().getString("top_level_domains_path", fs::path(path) / "top_level_domains/");
    if (!top_level_domains_path.empty())
        TLDListsHolder::getInstance().parseConfig(fs::path(top_level_domains_path) / "", getClientConfiguration());
}


void LocalServer::cleanup()
{
    try
    {
        connection.reset();

        /// Stop the memory worker before shutting down context, as it references the page cache.
        memory_worker.reset();

        /// Suggestions are loaded async in a separate thread and it can use global context.
        /// We should reset it before resetting global_context.
        if (suggest)
            suggest.reset();

        client_context.reset();

        if (global_context)
        {
            global_context->shutdown();
            global_context.reset();
        }

        /// thread status should be destructed before shared context because it relies on process list.

        status.reset();

        // Delete the temporary directory if needed.
        if (temporary_directory_to_delete)
        {
            LOG_DEBUG(&logger(), "Removing temporary directory: {}", temporary_directory_to_delete->string());
            fs::remove_all(*temporary_directory_to_delete);
            temporary_directory_to_delete.reset();
        }
    }
    catch (...)
    {
        tryLogCurrentException(__PRETTY_FUNCTION__);
    }
}


std::pair<std::string, std::string> LocalServer::getInitialCreateTableQuery()
{
    /// The input data can be specified explicitly with any of the `file`, `structure`, `input-format` command line arguments,
    /// or it can be implicitly specified in stdin - then the structure and format is autodetected.
    /// But if queries were not specified in the command line, they might me in stdin, and this means that stdin is not input data.

    if (!getClientConfiguration().has("table-structure")
        && !getClientConfiguration().has("table-file")
        && !getClientConfiguration().has("table-data-format")
        && (queries.empty() || !isFileDescriptorSuitableForInput(stdin_fd))) /// In we know that there is data in stdin, we can auto-detect the format.
        return {};

    auto table_name = getClientConfiguration().getString("table-name", "table");
    auto table_structure = getClientConfiguration().getString("table-structure", "auto");

    String table_file;
    String compression = "auto";
    if (!getClientConfiguration().has("table-file") || getClientConfiguration().getString("table-file") == "-")
    {
        /// Use Unix tools stdin naming convention
        table_file = "stdin";
        if (default_input_compression_method != CompressionMethod::None)
            compression = toContentEncodingName(default_input_compression_method);
    }
    else
    {
        /// Use regular file
        auto file_name = getClientConfiguration().getString("table-file");
        table_file = quoteString(file_name);
    }

    String data_format;

    if (default_input_format == "auto" && getClientConfiguration().has("table-structure"))
        data_format = "TabSeparated";   /// Compatibility with older versions when format inference was not available.
    else
        data_format = backQuoteIfNeed(default_input_format);

    if (table_structure == "auto")
        table_structure = "";
    else
        table_structure = "(" + table_structure + ")";

    return
    {
        table_name,
        fmt::format("CREATE TEMPORARY TABLE {} {} ENGINE = File({}, {}, {});",
            backQuote(table_name), table_structure, data_format, table_file, compression)
    };
}


namespace
{

ConfigurationPtr getConfigurationFromXMLString(const char * xml_data)
{
    std::stringstream ss{std::string{xml_data}};    // STYLE_CHECK_ALLOW_STD_STRING_STREAM
    Poco::XML::InputSource input_source{ss};
    return {new Poco::Util::XMLConfiguration{&input_source}};
}

}


void LocalServer::setupUsers()
{
    static const char * minimal_default_user_xml =
        "<clickhouse>"
        "    <profiles>"
        "        <default></default>"
        "    </profiles>"
        "    <users>"
        "        <default>"
        "            <password></password>"
        "            <networks>"
        "                <ip>::/0</ip>"
        "            </networks>"
        "            <profile>default</profile>"
        "            <quota>default</quota>"
        "            <access_management>1</access_management>"
        "            <named_collection_control>1</named_collection_control>"
        "        </default>"
        "    </users>"
        "    <quotas>"
        "        <default></default>"
        "    </quotas>"
        "</clickhouse>";

    ConfigurationPtr users_config;
    auto & access_control = global_context->getAccessControl();
    access_control.setNoPasswordAllowed(getClientConfiguration().getBool("allow_no_password", true));
    access_control.setPlaintextPasswordAllowed(getClientConfiguration().getBool("allow_plaintext_password", true));

    /// Enable all access control improvements by default; can be overridden via config.
    auto & config = getClientConfiguration();
    access_control.setEnabledUsersWithoutRowPoliciesCanReadRows(config.getBool("access_control_improvements.users_without_row_policies_can_read_rows", true));
    access_control.setOnClusterQueriesRequireClusterGrant(config.getBool("access_control_improvements.on_cluster_queries_require_cluster_grant", true));
    access_control.setSelectFromSystemDatabaseRequiresGrant(config.getBool("access_control_improvements.select_from_system_db_requires_grant", true));
    access_control.setSelectFromInformationSchemaRequiresGrant(config.getBool("access_control_improvements.select_from_information_schema_requires_grant", true));
    access_control.setSettingsConstraintsReplacePrevious(config.getBool("access_control_improvements.settings_constraints_replace_previous", true));
    access_control.setTableEnginesRequireGrant(config.getBool("access_control_improvements.table_engines_require_grant", true));
    access_control.setEnableReadWriteGrants(config.getBool("access_control_improvements.enable_read_write_grants", true));
    access_control.setEnableUserNameAccessType(config.getBool("access_control_improvements.enable_user_name_access_type", true));
    access_control.setThrowOnInvalidReplicatedAccessEntities(config.getBool("access_control_improvements.throw_on_invalid_replicated_access_entities", true));

    /// Apply user-level configuration from a loaded config file (including those
    /// auto-discovered via `getLocalConfigPath`, e.g. `~/.clickhouse-local/config.xml`).
    if (!loaded_config_path.empty())
    {
        const auto config_dir = fs::path{loaded_config_path}.remove_filename().string();
        bool has_user_directories = getClientConfiguration().has("user_directories");
        String users_config_path = getClientConfiguration().getString("users_config", "");

        if (users_config_path.empty() && has_user_directories)
            users_config_path = getClientConfiguration().getString("user_directories.users_xml.path");

        /// Anchor relative paths to the config's directory, not the cwd.
        /// Otherwise a missing `users.xml` silently falls back to `./users.xml`,
        /// which could grant `access_management` to the default user.
        if (!users_config_path.empty() && fs::path(users_config_path).is_relative())
            users_config_path = fs::path(config_dir) / users_config_path;

        if (users_config_path.empty())
            users_config = getConfigurationFromXMLString(minimal_default_user_xml);
        else
        {
            ConfigProcessor config_processor(users_config_path);
            const auto loaded_config = config_processor.loadConfig();
            users_config = loaded_config.configuration;
        }
    }
    else
        users_config = getConfigurationFromXMLString(minimal_default_user_xml);
    if (users_config)
        global_context->setUsersConfig(users_config);
    else
        throw Exception(ErrorCodes::CANNOT_LOAD_CONFIG, "Can't load config for users");

    /// Add a writeable storage for SQL-based access management.
    /// This allows creating users, roles, row policies, etc. via SQL queries.
    if (getClientConfiguration().has("path"))
    {
        /// Use disk storage for persistence when --path is specified.
        String access_path = fs::path(global_context->getPath()) / "access" / "";
        access_control.addDiskStorage(DiskAccessStorage::STORAGE_TYPE, access_path, /* readonly= */ false, /* allow_backup= */ false);
    }
    else
    {
        /// Use in-memory storage for temporary/ephemeral mode.
        access_control.addMemoryStorage(MemoryAccessStorage::STORAGE_TYPE, /* allow_backup= */ false);
    }
}

void LocalServer::connect()
{
    connection_parameters = ConnectionParameters(
        config(),
        ConnectionParameters::Host{"localhost"},
        ConnectionParameters::Database{default_database}
    );

    /// This is needed for table function input(...).
    ReadBuffer * in;
    auto table_file = getClientConfiguration().getString("table-file", "-");
    if (table_file == "-" || table_file == "stdin")
    {
        in = std_in.get();
    }
    else
    {
        input = std::make_unique<ReadBufferFromFile>(table_file);
        in = input.get();
    }
    connection = LocalConnection::createConnection(
        connection_parameters, client_context, in, need_render_progress, need_render_profile_events, server_display_name);
}


int LocalServer::main(const std::vector<std::string> & /*args*/)
try
{
    StackTrace::setShowAddresses(server_settings[ServerSetting::show_addresses_in_stack_traces]);

    setupSignalHandler();

    std::cout << std::fixed << std::setprecision(3);
    std::cerr << std::fixed << std::setprecision(3);

    /// Try to increase limit on number of open files.
    {
        rlimit rlim;
        if (getrlimit(RLIMIT_NOFILE, &rlim))
            throw Poco::Exception("Cannot getrlimit");

        if (rlim.rlim_cur < rlim.rlim_max)
        {
            rlim.rlim_cur = getClientConfiguration().getUInt("max_open_files", static_cast<unsigned>(rlim.rlim_max));
            int rc = setrlimit(RLIMIT_NOFILE, &rlim);
            if (rc != 0)
                std::cerr << fmt::format("Cannot set max number of file descriptors to {}. Try to specify max_open_files according to your system limits. error: {}", rlim.rlim_cur, errnoToString()) << '\n';
        }
    }

    is_interactive = stdin_is_a_tty
        && (getClientConfiguration().hasOption("interactive")
            || (queries.empty() && !getClientConfiguration().has("table-structure") && queries_files.empty() && !getClientConfiguration().has("table-file")));

    if (!is_interactive)
    {
        /// We will terminate process on error
        static KillingErrorHandler error_handler;
        Poco::ErrorHandler::set(&error_handler);
    }

    registerInterpreters();
    /// Don't initialize DateLUT
    registerFunctions();
    registerAggregateFunctions();
    registerTableFunctions();
    registerDatabases();
    registerStorages();
    registerDictionaries();
    registerDisks(/* global_skip_access_check= */ true);
    registerFormats();

    processConfig();

    SCOPE_EXIT({ cleanup(); });

    initTTYBuffer(toProgressOption(getClientConfiguration().getString("progress", "default")),
        toProgressOption(config().getString("progress-table", "default")));
    initKeystrokeInterceptor();

    /// try to load user defined executable functions, throw on error and die
    try
    {
        global_context->loadOrReloadUserDefinedExecutableFunctions(getClientConfiguration());
    }
    catch (...)
    {
        tryLogCurrentException(&logger(), "Caught exception while loading user defined executable functions.");
        throw;
    }

    /// Must be called after we stopped initializing the global context and changing its settings.
    /// After this point the global context must be stayed almost unchanged till shutdown,
    /// and all necessary changes must be made to the client context instead.
    initClientContext(Context::createCopy(global_context));
    /// Note, QueryScope will be initialized in the LocalConnection

    if (is_interactive)
    {
        clearTerminal();
        showClientVersion();
        std::cerr << std::endl;
    }

    auto [table_name, initial_query] = getInitialCreateTableQuery();
    if (!table_name.empty())
        client_context->setSetting("implicit_table_at_top_level", table_name);

    connect();

    if (!table_name.empty())
    {
        // Set option to false for hidden query to prevent double-printing time
        bool orig_print_time_to_stderr = getClientConfiguration().getBool("print-time-to-stderr", false);
        getClientConfiguration().setBool("print-time-to-stderr", false);

        processQueryText(initial_query);

        getClientConfiguration().setBool("print-time-to-stderr", orig_print_time_to_stderr);
    }

#if USE_FUZZING_MODE
    runLibFuzzer();
#else
    if (is_interactive && !delayed_interactive)
    {
        runInteractive();
    }
    else
    {
        runNonInteractive();

        if (delayed_interactive)
            runInteractive();
    }
#endif

    return Application::EXIT_OK;
}
catch (DB::Exception & e)
{
    bool need_print_stack_trace = getClientConfiguration().getBool("stacktrace", false);
    std::cerr << getExceptionMessageForLogging(e, need_print_stack_trace, true) << std::endl;
    auto code = DB::getCurrentExceptionCode();
    return static_cast<UInt8>(code) ? code : 1;
}
catch (...)
{
    std::cerr << DB::getCurrentExceptionMessage(true) << '\n';
    auto code = DB::getCurrentExceptionCode();
    return static_cast<UInt8>(code) ? code : 1;
}

void LocalServer::updateLoggerLevel(const String & logs_level)
{
    getClientConfiguration().setString("logger.level", logs_level);
    updateLevels(getClientConfiguration(), logger());
}

void LocalServer::processConfig()
{
    if (!queries.empty() && !queries_files.empty())
        throw Exception(ErrorCodes::BAD_ARGUMENTS, "Options '--query' and '--queries-file' cannot be specified at the same time");

    pager = getClientConfiguration().getString("pager", "");

    delayed_interactive = getClientConfiguration().has("interactive") && (!queries.empty() || !queries_files.empty());
    if (!is_interactive || delayed_interactive)
    {
        echo_queries = getClientConfiguration().hasOption("echo") || getClientConfiguration().hasOption("verbose");
        ignore_error = getClientConfiguration().getBool("ignore-error", false);
    }

    print_stack_trace = getClientConfiguration().getBool("stacktrace", false);
    const std::string clickhouse_dialect{"clickhouse"};
    load_suggestions = (is_interactive || delayed_interactive) && !getClientConfiguration().getBool("disable_suggestion", false)
        && getClientConfiguration().getString("dialect", clickhouse_dialect) == clickhouse_dialect;
    wait_for_suggestions_to_load = getClientConfiguration().getBool("wait_for_suggestions_to_load", false);

    auto logging = (getClientConfiguration().has("logger.console")
                    || getClientConfiguration().has("logger.level")
                    || getClientConfiguration().has("log-level")
                    || getClientConfiguration().has("logger.log"));

    auto level = getClientConfiguration().getString("log-level", getClientConfiguration().getString("send_logs_level", "trace"));

    if (getClientConfiguration().has("server_logs_file"))
    {
        auto poco_logs_level = Poco::Logger::parseLevel(level);
        Poco::Logger::root().setLevel(poco_logs_level);
        Poco::AutoPtr<OwnPatternFormatter> pf = new OwnPatternFormatter;
        Poco::AutoPtr<OwnFormattingChannel> log = new OwnFormattingChannel(pf, new Poco::SimpleFileChannel(server_logs_file));
        Poco::Logger::root().setChannel(log);
    }
    else
    {
        getClientConfiguration().setString("logger", "logger");
        getClientConfiguration().setString("logger.level", logging ? level : "fatal");
        buildLoggers(getClientConfiguration(), logger(), "clickhouse-local");
    }

    shared_context = Context::createShared();
    global_context = Context::createGlobal(shared_context.get());
    global_context->makeGlobalContext();
    global_context->setApplicationType(Context::ApplicationType::LOCAL);

    tryInitPath();

    LoggerRawPtr log = &logger();

    /// Maybe useless
    if (getClientConfiguration().has("macros"))
        global_context->setMacros(std::make_unique<Macros>(getClientConfiguration(), "macros", log));

    setDefaultFormatsAndCompressionFromConfiguration();

    /// Sets external authenticators config (LDAP, Kerberos).
    global_context->setExternalAuthenticatorsConfig(getClientConfiguration());

    setupUsers();

    /// Limit on total number of concurrently executing queries.
    /// There is no need for concurrent queries, override max_concurrent_queries.
    global_context->getProcessList().setMaxSize(0);

    size_t max_server_memory_usage = server_settings[ServerSetting::max_server_memory_usage];
    const double max_server_memory_usage_to_ram_ratio = server_settings[ServerSetting::max_server_memory_usage_to_ram_ratio];
    const size_t physical_server_memory = getMemoryAmount();
    const size_t default_max_server_memory_usage = static_cast<size_t>(static_cast<double>(physical_server_memory) * max_server_memory_usage_to_ram_ratio);

    if (max_server_memory_usage == 0)
    {
        max_server_memory_usage = default_max_server_memory_usage;
        LOG_INFO(log, "Changed setting 'max_server_memory_usage' to {}"
                      " ({} available memory * {:.2f} max_server_memory_usage_to_ram_ratio)",
                 formatReadableSizeWithBinarySuffix(max_server_memory_usage),
                 formatReadableSizeWithBinarySuffix(physical_server_memory),
                 max_server_memory_usage_to_ram_ratio);
    }
    else if (max_server_memory_usage > default_max_server_memory_usage)
    {
        max_server_memory_usage = default_max_server_memory_usage;
        LOG_INFO(log, "Lowered setting 'max_server_memory_usage' to {}"
                      " because the system has little few memory. The new value was"
                      " calculated as {} available memory * {:.2f} max_server_memory_usage_to_ram_ratio",
                 formatReadableSizeWithBinarySuffix(max_server_memory_usage),
                 formatReadableSizeWithBinarySuffix(physical_server_memory),
                 max_server_memory_usage_to_ram_ratio);
    }

    total_memory_tracker.setHardLimit(max_server_memory_usage);
    total_memory_tracker.setDescription("(total)");
    total_memory_tracker.setMetric(CurrentMetrics::MemoryTracking);

    CurrentMemoryTracker::setMinAllocationSizeBytesToThrow(
        server_settings[ServerSetting::min_allocation_size_to_throw_on_memory_limit]);

    size_t page_cache_min_size = server_settings[ServerSetting::page_cache_min_size];
    size_t page_cache_max_size = server_settings[ServerSetting::page_cache_max_size];
    if (page_cache_max_size != 0 && (page_cache_min_size > page_cache_max_size))
    {
        throw Exception(
            ErrorCodes::INVALID_CONFIG_PARAMETER,
            "Invalid page cache configuration: page_cache_min_size ({}) is greater than page_cache_max_size ({}).",
            page_cache_min_size,
            page_cache_max_size);
    }

    if (page_cache_max_size != 0)
    {
        global_context->setPageCache(
            std::chrono::milliseconds(Int64(server_settings[ServerSetting::page_cache_history_window_ms])),
            server_settings[ServerSetting::page_cache_policy],
            server_settings[ServerSetting::page_cache_size_ratio],
            server_settings[ServerSetting::page_cache_min_size],
            server_settings[ServerSetting::page_cache_max_size],
            server_settings[ServerSetting::page_cache_free_memory_ratio],
            server_settings[ServerSetting::page_cache_shards]);
        total_memory_tracker.setPageCache(global_context->getPageCache().get());
    }

    /// MemoryWorker periodically updates RSS in the memory tracker, resizes the userspace page
    /// cache based on available memory, and purges jemalloc dirty pages under memory pressure.
    /// It is required for the page cache to function correctly: without it the cache stays stuck
    /// at `page_cache_min_size` and never grows, causing severe thrashing.
    {
        MemoryWorkerConfig memory_worker_config{
            .rss_update_period_ms = server_settings[ServerSetting::memory_worker_period_ms],
            .purge_dirty_pages_threshold_ratio = server_settings[ServerSetting::memory_worker_purge_dirty_pages_threshold_ratio],
            .purge_total_memory_threshold_ratio = server_settings[ServerSetting::memory_worker_purge_total_memory_threshold_ratio],
            .correct_tracker = server_settings[ServerSetting::memory_worker_correct_memory_tracker],
            .decay_adjustment_period_ms = server_settings[ServerSetting::memory_worker_decay_adjustment_period_ms],
            .use_cgroup = server_settings[ServerSetting::memory_worker_use_cgroup],
        };
        memory_worker.emplace(memory_worker_config, global_context->getPageCache());
        memory_worker->start();
    }

    const double cache_size_to_ram_max_ratio = server_settings[ServerSetting::cache_size_to_ram_max_ratio];
    const size_t max_cache_size = static_cast<size_t>(static_cast<double>(physical_server_memory) * cache_size_to_ram_max_ratio);

    String uncompressed_cache_policy = server_settings[ServerSetting::uncompressed_cache_policy];
    size_t uncompressed_cache_size = server_settings[ServerSetting::uncompressed_cache_size];
    double uncompressed_cache_size_ratio = server_settings[ServerSetting::uncompressed_cache_size_ratio];
    if (uncompressed_cache_size > max_cache_size)
    {
        uncompressed_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered uncompressed cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(uncompressed_cache_size));
    }
    global_context->setUncompressedCache(uncompressed_cache_policy, uncompressed_cache_size, uncompressed_cache_size_ratio);

    String mark_cache_policy = server_settings[ServerSetting::mark_cache_policy];
    size_t mark_cache_size = server_settings[ServerSetting::mark_cache_size];
    double mark_cache_size_ratio = server_settings[ServerSetting::mark_cache_size_ratio];
    if (!mark_cache_size)
        LOG_ERROR(log, "Too low mark cache size will lead to severe performance degradation.");
    if (mark_cache_size > max_cache_size)
    {
        mark_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered mark cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(mark_cache_size));
    }
    global_context->setMarkCache(mark_cache_policy, mark_cache_size, mark_cache_size_ratio);

    String index_uncompressed_cache_policy = server_settings[ServerSetting::index_uncompressed_cache_policy];
    size_t index_uncompressed_cache_size = server_settings[ServerSetting::index_uncompressed_cache_size];
    double index_uncompressed_cache_size_ratio = server_settings[ServerSetting::index_uncompressed_cache_size_ratio];
    if (index_uncompressed_cache_size > max_cache_size)
    {
        index_uncompressed_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered index uncompressed cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(index_uncompressed_cache_size));
    }
    global_context->setIndexUncompressedCache(index_uncompressed_cache_policy, index_uncompressed_cache_size, index_uncompressed_cache_size_ratio);

    String index_mark_cache_policy = server_settings[ServerSetting::index_mark_cache_policy];
    size_t index_mark_cache_size = server_settings[ServerSetting::index_mark_cache_size];
    double index_mark_cache_size_ratio = server_settings[ServerSetting::index_mark_cache_size_ratio];
    if (index_mark_cache_size > max_cache_size)
    {
        index_mark_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered index mark cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(index_mark_cache_size));
    }
    global_context->setIndexMarkCache(index_mark_cache_policy, index_mark_cache_size, index_mark_cache_size_ratio);

    String primary_index_cache_policy = server_settings[ServerSetting::primary_index_cache_policy];
    size_t primary_index_cache_size = server_settings[ServerSetting::primary_index_cache_size];
    double primary_index_cache_size_ratio = server_settings[ServerSetting::primary_index_cache_size_ratio];
    if (primary_index_cache_size > max_cache_size)
    {
        primary_index_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered primary index cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(primary_index_cache_size));
    }
    global_context->setPrimaryIndexCache(primary_index_cache_policy, primary_index_cache_size, primary_index_cache_size_ratio);

    String vector_similarity_index_cache_policy = server_settings[ServerSetting::vector_similarity_index_cache_policy];
    size_t vector_similarity_index_cache_size = server_settings[ServerSetting::vector_similarity_index_cache_size];
    size_t vector_similarity_index_cache_max_count = server_settings[ServerSetting::vector_similarity_index_cache_max_entries];
    double vector_similarity_index_cache_size_ratio = server_settings[ServerSetting::vector_similarity_index_cache_size_ratio];
    if (vector_similarity_index_cache_size > max_cache_size)
    {
        vector_similarity_index_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered vector similarity index cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(vector_similarity_index_cache_size));
    }
    global_context->setVectorSimilarityIndexCache(vector_similarity_index_cache_policy, vector_similarity_index_cache_size, vector_similarity_index_cache_max_count, vector_similarity_index_cache_size_ratio);

    String text_index_tokens_cache_policy = server_settings[ServerSetting::text_index_tokens_cache_policy];
    size_t text_index_tokens_cache_size = server_settings[ServerSetting::text_index_tokens_cache_size];
    size_t text_index_tokens_cache_max_count = server_settings[ServerSetting::text_index_tokens_cache_max_entries];
    double text_index_tokens_cache_size_ratio = server_settings[ServerSetting::text_index_tokens_cache_size_ratio];
    if (text_index_tokens_cache_size > max_cache_size)
    {
        text_index_tokens_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered text index tokens cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(text_index_tokens_cache_size));
    }
    global_context->setTextIndexTokensCache(text_index_tokens_cache_policy, text_index_tokens_cache_size, text_index_tokens_cache_max_count, text_index_tokens_cache_size_ratio);

    String text_index_header_cache_policy = server_settings[ServerSetting::text_index_header_cache_policy];
    size_t text_index_header_cache_size = server_settings[ServerSetting::text_index_header_cache_size];
    size_t text_index_header_cache_max_count = server_settings[ServerSetting::text_index_header_cache_max_entries];
    double text_index_header_cache_size_ratio = server_settings[ServerSetting::text_index_header_cache_size_ratio];
    if (text_index_header_cache_size > max_cache_size)
    {
        text_index_header_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered text index header cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(text_index_header_cache_size));
    }
    global_context->setTextIndexHeaderCache(text_index_header_cache_policy, text_index_header_cache_size, text_index_header_cache_max_count, text_index_header_cache_size_ratio);

    String text_index_postings_cache_policy = server_settings[ServerSetting::text_index_postings_cache_policy];
    size_t text_index_postings_cache_size = server_settings[ServerSetting::text_index_postings_cache_size];
    size_t text_index_postings_cache_max_count = server_settings[ServerSetting::text_index_postings_cache_max_entries];
    double text_index_postings_cache_size_ratio = server_settings[ServerSetting::text_index_postings_cache_size_ratio];
    if (text_index_postings_cache_size > max_cache_size)
    {
        text_index_postings_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered text index posting list cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(text_index_postings_cache_size));
    }
    global_context->setTextIndexPostingsCache(text_index_postings_cache_policy, text_index_postings_cache_size, text_index_postings_cache_max_count, text_index_postings_cache_size_ratio);

    size_t mmap_cache_size = server_settings[ServerSetting::mmap_cache_size];
    if (mmap_cache_size > max_cache_size)
    {
        mmap_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered mmap file cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(mmap_cache_size));
    }
    global_context->setMMappedFileCache(mmap_cache_size);

#if USE_AVRO
    String iceberg_metadata_files_cache_policy = server_settings[ServerSetting::iceberg_metadata_files_cache_policy];
    size_t iceberg_metadata_files_cache_size = server_settings[ServerSetting::iceberg_metadata_files_cache_size];
    size_t iceberg_metadata_files_cache_max_entries = server_settings[ServerSetting::iceberg_metadata_files_cache_max_entries];
    double iceberg_metadata_files_cache_size_ratio = server_settings[ServerSetting::iceberg_metadata_files_cache_size_ratio];
    if (iceberg_metadata_files_cache_size > max_cache_size)
    {
        iceberg_metadata_files_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered Iceberg metadata cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(iceberg_metadata_files_cache_size));
    }
    global_context->setIcebergMetadataFilesCache(iceberg_metadata_files_cache_policy, iceberg_metadata_files_cache_size, iceberg_metadata_files_cache_max_entries, iceberg_metadata_files_cache_size_ratio);
#endif
#if USE_PARQUET
    String parquet_metadata_cache_policy = server_settings[ServerSetting::parquet_metadata_cache_policy];
    size_t parquet_metadata_cache_size = server_settings[ServerSetting::parquet_metadata_cache_size];
    size_t parquet_metadata_cache_max_entries = server_settings[ServerSetting::parquet_metadata_cache_max_entries];
    double parquet_metadata_cache_size_ratio = server_settings[ServerSetting::parquet_metadata_cache_size_ratio];
    if (parquet_metadata_cache_size > max_cache_size)
    {
        parquet_metadata_cache_size = max_cache_size;
        LOG_INFO(log, "Lowered Parquet metadata cache size to {} because the system has limited RAM", formatReadableSizeWithBinarySuffix(parquet_metadata_cache_size));
    }
    global_context->setParquetMetadataCache(parquet_metadata_cache_policy, parquet_metadata_cache_size, parquet_metadata_cache_max_entries, parquet_metadata_cache_size_ratio);
#endif

    Names allowed_disks_table_engines;
    splitInto<','>(allowed_disks_table_engines, server_settings[ServerSetting::allowed_disks_for_table_engines].value);
    global_context->setAllowedDisksForTableEngines(std::unordered_set<String>(allowed_disks_table_engines.begin(), allowed_disks_table_engines.end()));

    /// Initialize a dummy query condition cache.
    global_context->setQueryConditionCache(DEFAULT_QUERY_CONDITION_CACHE_POLICY, 0, 0);

    /// Initialize a dummy query result cache.
    global_context->setQueryResultCache(0, 0, 0, 0);

    /// Initialize allowed tiers
    global_context->getAccessControl().setAllowTierSettings(server_settings[ServerSetting::allow_feature_tier]);

#if USE_EMBEDDED_COMPILER
    size_t compiled_expression_cache_max_size_in_bytes = server_settings[ServerSetting::compiled_expression_cache_size];
    size_t compiled_expression_cache_max_elements = server_settings[ServerSetting::compiled_expression_cache_elements_size];
    CompiledExpressionCacheFactory::instance().init(compiled_expression_cache_max_size_in_bytes, compiled_expression_cache_max_elements);
#endif

    NamedCollectionFactory::instance().loadIfNot();
    FileCacheFactory::instance().loadDefaultCaches(config(), global_context);

    /// NOTE: it is important to apply any overrides before
    /// `setDefaultProfiles` calls since it will copy current context (i.e.
    /// there is separate context for Buffer tables).
    adjustSettings(global_context);
    applySettingsOverridesForLocal(global_context);
    applyCmdOptions(global_context);

    /// Load global settings from default_profile and system_profile.
    global_context->setDefaultProfiles(getClientConfiguration());

    /// Command-line parameters can override settings from the default profile.
    applyCmdSettings(global_context);

    /// We load temporary database first, because projections need it.
    DatabaseCatalog::instance().initializeAndLoadTemporaryDatabase();

    std::string server_default_database = server_settings[ServerSetting::default_database];
    if (!server_default_database.empty())
    {
        DatabasePtr database = createClickHouseLocalDatabaseOverlay(server_default_database, global_context);
        if (UUID uuid = database->getUUID(); uuid != UUIDHelpers::Nil)
            DatabaseCatalog::instance().addUUIDMapping(uuid);
        DatabaseCatalog::instance().attachDatabase(server_default_database, database);
        global_context->setCurrentDatabase(server_default_database);
    }

    if (getClientConfiguration().has("path"))
    {
        attachInformationSchema(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::INFORMATION_SCHEMA));
        attachInformationSchema(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::INFORMATION_SCHEMA_UPPERCASE));

        /// Attaching "automatic" tables in the system database is done after attaching the system database.
        /// Consequently, it depends on whether we load it from the path.
        /// If it is loaded from a user-specified path, we load it as usual. If not, we create it as a memory (ephemeral) database.
        bool attached_system_database = false;

        String path = global_context->getPath();

        /// Lock path directory before read
        fs::create_directories(fs::path(path));
        status.emplace(fs::path(path) / "status", StatusFile::write_full_info);

        if (fs::exists(fs::path(path) / "metadata"))
        {
            LOG_DEBUG(log, "Loading metadata from {}", path);

            if (fs::exists(std::filesystem::path(path) / "metadata" / "system.sql"))
            {
                LoadTaskPtrs load_system_metadata_tasks = loadMetadataSystem(global_context);
                waitLoad(TablesLoaderForegroundPoolId, load_system_metadata_tasks);

                attachSystemTablesServer(global_context, *DatabaseCatalog::instance().tryGetDatabase(DatabaseCatalog::SYSTEM_DATABASE), false);
                attached_system_database = true;
            }

            if (!getClientConfiguration().has("only-system-tables"))
            {
                DatabaseCatalog::instance().createBackgroundTasks();
                waitLoad(loadMetadata(global_context));
                DatabaseCatalog::instance().startupBackgroundTasks();
            }

            LOG_DEBUG(log, "Loaded metadata.");
        }

        if (!attached_system_database)
            attachSystemTablesServer(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::SYSTEM_DATABASE), false);

        if (fs::exists(fs::path(path) / "user_defined"))
            global_context->getUserDefinedSQLObjectsStorage().loadObjects();
    }
    else if (!getClientConfiguration().has("no-system-tables"))
    {
        attachSystemTablesServer(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::SYSTEM_DATABASE), false);
        attachInformationSchema(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::INFORMATION_SCHEMA));
        attachInformationSchema(global_context, *createMemoryDatabaseIfNotExists(global_context, DatabaseCatalog::INFORMATION_SCHEMA_UPPERCASE));

        /// Create background tasks necessary for DDL operations like DROP VIEW SYNC,
        /// even in temporary mode (--path not set) without persistent storage
        DatabaseCatalog::instance().createBackgroundTasks();
        DatabaseCatalog::instance().startupBackgroundTasks();
    }
    else
    {
        /// Similarly, for other cases, create background tasks for DDL operations like
        /// DROP VIEW SYNC in temporaty mode (--path not set) without persistent storage
        DatabaseCatalog::instance().createBackgroundTasks();
        DatabaseCatalog::instance().startupBackgroundTasks();
    }

    /// Initialize system logs only when explicitly configured (e.g. `query_log`, `processors_profile_log`).
    /// Default `clickhouse-local` invocations have no system log sections in the config, and skipping
    /// initialization avoids a TSan-visible race between background pool task logging and `Context`
    /// teardown that would otherwise be triggered for short-lived processes.
    /// Also skip in `--only-system-tables` mode, which is intended for reading existing persisted
    /// system tables; spinning up the loggers there is unnecessary and can race with shutdown.
    /// This must happen after the system database is attached.
    if (!getClientConfiguration().has("no-system-tables")
        && !getClientConfiguration().has("only-system-tables")
        && hasAnySystemLogConfigured(config()))
        global_context->initializeSystemLogs();

    std::string default_database = getClientConfiguration().getString("database", server_default_database);
    if (default_database.empty())
        throw Exception(ErrorCodes::BAD_ARGUMENTS, "default_database cannot be empty");
    global_context->setCurrentDatabase(default_database);

    server_display_name = getClientConfiguration().getString("display_name", "");

    rainbow_parentheses = getClientConfiguration().getBool("rainbow_parentheses", true);

    if (getClientConfiguration().has("prompt"))
        prompt = getClientConfiguration().getString("prompt");
    else if (getClientConfiguration().has("prompt_by_server_display_name.default"))
        prompt = getClientConfiguration().getRawString("prompt_by_server_display_name.default");
    prompt = appendSmileyIfNeeded(prompt);
}


String LocalServer::getHelpHeader() const
{
    return fmt::format(
        "Usage: {0} [initial table definition] [--query <query>]\n\n"
        "{0} allows to execute SQL queries on your data files\n"
        "via single command line call.\n"
        "To do so, initially you need to define your data source and its format.\n"
        "After that, you can execute your SQL queries as usual.\n\n"
        "There are two ways to define initial table keeping your data.\n"
        "Either just in the first query like this:\n"
        "    CREATE TABLE <table> (<structure>) ENGINE = File(<input-format>, <file>);\n"
        "Either through corresponding command line parameters\n"
        "--table --structure --input-format and --file.",
        app_name);
}


String LocalServer::getHelpFooter() const
{
    return fmt::format(
        "Example printing memory used by each Unix user:\n"
        "    ps aux | tail -n +2 | awk '{{ printf(\"%s\\t%s\\n\", $1, $4) }}' | \\\n"
        "        {} -S \"user String, mem Float64\" -q \\\n"
        "        \"SELECT user, round(sum(mem), 2) as mem_total FROM table \\\n"
        "         GROUP BY user ORDER BY mem_total DESC FORMAT PrettyCompact\"",
        app_name);
}


void LocalServer::printHelpMessage(const OptionsDescription & options_description)
{
    output_stream << getHelpHeader() << "\n";
    if (options_description.main_description.has_value())
        output_stream << options_description.main_description.value() << "\n";
    output_stream << "All settings are documented at https://clickhouse.com/docs/operations/settings/settings.\n\n";
    output_stream << getHelpFooter() << "\n";
    output_stream << "In addition, --param_name=value can be specified for substitution of parameters for parameterized queries.\n";
    output_stream << "\nSee also: https://clickhouse.com/docs/en/operations/utilities/clickhouse-local/\n";
}


void LocalServer::addExtraOptions(OptionsDescription & options_description)
{
    options_description.main_description->add_options()
        ("table,N", po::value<std::string>(), "Name of the initial table")
        ("copy", "Shortcut for format conversion, equivalent to: --query 'SELECT * FROM table'")

        /// If structure argument is omitted then initial query is not generated
        ("structure,S", po::value<std::string>(), "Structure of the initial table (list of column and type names)")
        ("file,F", po::value<std::string>(), "Path to file with data of the initial table (stdin if not specified)")

        ("input-format", po::value<std::string>(), "Default input format. Takes precedence over --format.")

        ("logger.console", po::value<bool>()->implicit_value(true), "Log to console")
        ("logger.log", po::value<std::string>(), "Log file name")
        ("logger.level", po::value<std::string>(), "Log level")

        ("no-system-tables", "Do not attach system tables (better startup time)")
        ("path", po::value<std::string>(), "Storage path. If it was not specified, we will use a temporary directory, that is cleaned up on exit.")
        ("only-system-tables", "Attach only system tables from specified path")
        ("top_level_domains_path", po::value<std::string>(), "Path to lists with custom TLDs")
        ;
}


void LocalServer::applyCmdSettings(ContextMutablePtr context)
{
    context->applySettingsChanges(cmd_settings->changes());
}


void LocalServer::applyCmdOptions(ContextMutablePtr context)
{
    context->setDefaultFormat(getClientConfiguration().getString("output-format", getClientConfiguration().getString("format", is_interactive ? "PrettyCompact" : "TSV")));
    applyCmdSettings(context);
}


void LocalServer::processOptions(const OptionsDescription &, const CommandLineOptions & options, const std::vector<Arguments> &, const std::vector<Arguments> &)
{
    if (options.contains("path"))
        getClientConfiguration().setString("path", options["path"].as<std::string>());
    if (options.contains("table"))
        getClientConfiguration().setString("table-name", options["table"].as<std::string>());
    if (options.contains("file"))
        getClientConfiguration().setString("table-file", options["file"].as<std::string>());
    if (options.contains("structure"))
        getClientConfiguration().setString("table-structure", options["structure"].as<std::string>());
    if (options.contains("no-system-tables"))
        getClientConfiguration().setBool("no-system-tables", true);
    if (options.contains("only-system-tables"))
        getClientConfiguration().setBool("only-system-tables", true);

    if (options.contains("input-format"))
        getClientConfiguration().setString("table-data-format", options["input-format"].as<std::string>());
    if (options.contains("output-format"))
        getClientConfiguration().setString("output-format", options["output-format"].as<std::string>());

    if (options.contains("logger.console"))
        getClientConfiguration().setBool("logger.console", options["logger.console"].as<bool>());
    if (options.contains("logger.log"))
        getClientConfiguration().setString("logger.log", options["logger.log"].as<std::string>());
    if (options.contains("logger.level"))
        getClientConfiguration().setString("logger.level", options["logger.level"].as<std::string>());
    if (options.contains("send_logs_level"))
        getClientConfiguration().setString("send_logs_level", options["send_logs_level"].as<std::string>());
    if (options.contains("wait_for_suggestions_to_load"))
        getClientConfiguration().setBool("wait_for_suggestions_to_load", true);
    if (options.contains("copy"))
    {
        if (!queries.empty())
            throw Exception(ErrorCodes::BAD_ARGUMENTS, "Options '--copy' and '--query' cannot be specified at the same time");
        queries.emplace_back("SELECT * FROM table");
    }
}

void LocalServer::readArguments(int argc, char ** argv, Arguments & common_arguments, std::vector<Arguments> &, std::vector<Arguments> &)
{
    for (int arg_num = 1; arg_num < argc; ++arg_num)
    {
        std::string_view arg = argv[arg_num];

        /// Parameter arg after underline or dash.
        if (arg.starts_with("--param_") || arg.starts_with("--param-"))
        {
            auto param_continuation = arg.substr(strlen("--param_"));
            auto equal_pos = param_continuation.find_first_of('=');

            if (equal_pos == std::string::npos)
            {
                /// param_name value
                ++arg_num;
                if (arg_num >= argc)
                    throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter requires value");
                arg = argv[arg_num];
                query_parameters.emplace(String(param_continuation), String(arg));
            }
            else
            {
                if (equal_pos == 0)
                    throw Exception(ErrorCodes::BAD_ARGUMENTS, "Parameter name cannot be empty");

                /// param_name=value
                query_parameters.emplace(param_continuation.substr(0, equal_pos), param_continuation.substr(equal_pos + 1));
            }
        }
        else
        {
            common_arguments.emplace_back(arg);
        }
    }
}

}

int mainEntryClickHouseLocal(int argc, char ** argv);

int mainEntryClickHouseLocal(int argc, char ** argv)
{
    DB::MainThreadStatus::getInstance();

    try
    {
        DB::LocalServer app;
        app.init(argc, argv);
        return app.run();
    }
    catch (DB::Exception & e)
    {
        std::cerr << DB::getExceptionMessageForLogging(e, false) << std::endl;
        auto code = DB::getCurrentExceptionCode();
        return static_cast<UInt8>(code) ? code : 1;
    }
    catch (const boost::program_options::error & e)
    {
        std::cerr << "Bad arguments: " << e.what() << std::endl;
        return DB::ErrorCodes::BAD_ARGUMENTS;
    }
    catch (...)
    {
        std::cerr << DB::getCurrentExceptionMessage(true) << '\n';
        auto code = DB::getCurrentExceptionCode();
        return static_cast<UInt8>(code) ? code : 1;
    }
}