Merge pull request #15300 from ClickHouse/fix_race_on_default_database

Fix for default database race on server startup

programs/server/Server.cpp

@@ -671,6 +671,10 @@ int Server::main(const std::vector<std::string> & /*args*/)
     total_memory_tracker.setDescription("(total)");
     total_memory_tracker.setMetric(CurrentMetrics::MemoryTracking);
 
+    /// Set current database name before loading tables and databases because
+    /// system logs may copy global context.
+    global_context->setCurrentDatabaseNameInGlobalContext(default_database);
+
     LOG_INFO(log, "Loading metadata from {}", path);
 
     try
@@ -678,11 +682,14 @@ int Server::main(const std::vector<std::string> & /*args*/)
         loadMetadataSystem(*global_context);
         /// After attaching system databases we can initialize system log.
         global_context->initializeSystemLogs();
+        auto & database_catalog = DatabaseCatalog::instance();
         /// After the system database is created, attach virtual system tables (in addition to query_log and part_log)
-        attachSystemTablesServer(*DatabaseCatalog::instance().getSystemDatabase(), has_zookeeper);
+        attachSystemTablesServer(*database_catalog.getSystemDatabase(), has_zookeeper);
         /// Then, load remaining databases
         loadMetadata(*global_context, default_database);
-        DatabaseCatalog::instance().loadDatabases();
+        database_catalog.loadDatabases();
+        /// After loading validate that default database exists
+        database_catalog.assertDatabaseExists(default_database);
     }
     catch (...)
     {
@@ -745,8 +752,6 @@ int Server::main(const std::vector<std::string> & /*args*/)
         LOG_INFO(log, "Query Profiler and TraceCollector are disabled because they require PHDR cache to be created"
             " (otherwise the function 'dl_iterate_phdr' is not lock free and not async-signal safe).");
 
-    global_context->setCurrentDatabase(default_database);
-
     if (has_zookeeper && config().has("distributed_ddl"))
     {
         /// DDL worker should be started after all tables were loaded

src/Interpreters/Context.cpp

@@ -1088,6 +1088,18 @@ String Context::getInitialQueryId() const
 }
 
 
+void Context::setCurrentDatabaseNameInGlobalContext(const String & name)
+{
+    if (global_context != this)
+        throw Exception("Cannot set current database for non global context, this method should be used during server initialization", ErrorCodes::LOGICAL_ERROR);
+    auto lock = getLock();
+
+    if (!current_database.empty())
+        throw Exception("Default database name cannot be changed in global context without server restart", ErrorCodes::LOGICAL_ERROR);
+
+    current_database = name;
+}
+
 void Context::setCurrentDatabase(const String & name)
 {
     DatabaseCatalog::instance().assertDatabaseExists(name);

src/Interpreters/Context.h

@@ -359,6 +359,9 @@ public:
     String getInitialQueryId() const;
 
     void setCurrentDatabase(const String & name);
+    /// Set current_database for global context. We don't validate that database
+    /// exists because it should be set before databases loading.
+    void setCurrentDatabaseNameInGlobalContext(const String & name);
     void setCurrentQueryId(const String & query_id);
 
     void killCurrentQuery();

src/Interpreters/SystemLog.h

@@ -438,7 +438,7 @@ void SystemLog<LogElement>::flushImpl(const std::vector<LogElement> & to_flush,
         ASTPtr query_ptr(insert.release());
 
         // we need query context to do inserts to target table with MV containing subqueries or joins
-        auto insert_context = Context(context);
+        Context insert_context(context);
         insert_context.makeQueryContext();
 
         InterpreterInsertQuery interpreter(query_ptr, insert_context);