Merge pull request #1009 from Altinity/simple_export_part

simple export part

Author: arthurpassos

src/Access/Common/AccessType.h

@@ -210,6 +210,7 @@ enum class AccessType : uint8_t
                                                                        enabled implicitly by the grant ALTER_TABLE */\
     M(ALTER_SETTINGS, "ALTER SETTING, ALTER MODIFY SETTING, MODIFY SETTING, RESET SETTING", TABLE, ALTER_TABLE) /* allows to execute ALTER MODIFY SETTING */\
     M(ALTER_MOVE_PARTITION, "ALTER MOVE PART, MOVE PARTITION, MOVE PART", TABLE, ALTER_TABLE) \
+    M(ALTER_EXPORT_PART, "ALTER EXPORT PART, EXPORT PART", TABLE, ALTER_TABLE) \
     M(ALTER_FETCH_PARTITION, "ALTER FETCH PART, FETCH PARTITION", TABLE, ALTER_TABLE) \
     M(ALTER_FREEZE_PARTITION, "FREEZE PARTITION, UNFREEZE", TABLE, ALTER_TABLE) \
     M(ALTER_UNLOCK_SNAPSHOT, "UNLOCK SNAPSHOT", TABLE, ALTER_TABLE) \

src/CMakeLists.txt

@@ -130,6 +130,7 @@ add_headers_and_sources(dbms Storages/ObjectStorage/Azure)
 add_headers_and_sources(dbms Storages/ObjectStorage/S3)
 add_headers_and_sources(dbms Storages/ObjectStorage/HDFS)
 add_headers_and_sources(dbms Storages/ObjectStorage/Local)
+add_headers_and_sources(dbms Storages/ObjectStorage/MergeTree)
 add_headers_and_sources(dbms Storages/ObjectStorage/DataLakes)
 add_headers_and_sources(dbms Storages/ObjectStorage/DataLakes/Iceberg)
 add_headers_and_sources(dbms Storages/ObjectStorage/DataLakes/DeltaLake)

src/Core/ServerSettings.cpp

@@ -112,6 +112,7 @@ namespace DB
     DECLARE(UInt64, max_unexpected_parts_loading_thread_pool_size, 8, R"(The number of threads to load inactive set of data parts (Unexpected ones) at startup.)", 0) \
     DECLARE(UInt64, max_parts_cleaning_thread_pool_size, 128, R"(The number of threads for concurrent removal of inactive data parts.)", 0) \
     DECLARE(UInt64, max_mutations_bandwidth_for_server, 0, R"(The maximum read speed of all mutations on server in bytes per second. Zero means unlimited.)", 0) \
+    DECLARE(UInt64, max_exports_bandwidth_for_server, 0, R"(The maximum read speed of all exports on server in bytes per second. Zero means unlimited.)", 0) \
     DECLARE(UInt64, max_merges_bandwidth_for_server, 0, R"(The maximum read speed of all merges on server in bytes per second. Zero means unlimited.)", 0) \
     DECLARE(UInt64, max_replicated_fetches_network_bandwidth_for_server, 0, R"(The maximum speed of data exchange over the network in bytes per second for replicated fetches. Zero means unlimited.)", 0) \
     DECLARE(UInt64, max_replicated_sends_network_bandwidth_for_server, 0, R"(The maximum speed of data exchange over the network in bytes per second for replicated sends. Zero means unlimited.)", 0) \

src/Core/Settings.cpp

@@ -7030,6 +7030,9 @@ Use Shuffle aggregation strategy instead of PartialAggregation + Merge in distri
     DECLARE_WITH_ALIAS(Bool, allow_experimental_time_series_aggregate_functions, false, R"(
 Experimental timeSeries* aggregate functions for Prometheus-like timeseries resampling, rate, delta calculation.
 )", EXPERIMENTAL, allow_experimental_ts_to_grid_aggregate_function) \
+    DECLARE_WITH_ALIAS(Bool, allow_experimental_export_merge_tree_part, false, R"(
+Experimental export merge tree part.
+)", EXPERIMENTAL, allow_experimental_export_merge_tree_part) \
     \
     DECLARE(String, promql_database, "", R"(
 Specifies the database name used by the 'promql' dialect. Empty string means the current database.

src/Core/SettingsChangesHistory.cpp

@@ -132,6 +132,15 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
             {"distributed_plan_force_shuffle_aggregation", 0, 0, "New experimental setting"},
             {"allow_experimental_insert_into_iceberg", false, false, "New setting."},
             /// RELEASE CLOSED
+            {"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"},
+            {"lock_object_storage_task_distribution_ms", 0, 0, "New setting."},
+            {"object_storage_cluster", "", "", "New setting"},
+            {"object_storage_max_nodes", 0, 0, "New setting"},
+            {"object_storage_remote_initiator", false, false, "New setting."},
+            {"allow_experimental_export_merge_tree_part", false, false, "New setting."},
         });
         addSettingsChanges(settings_changes_history, "25.6",
         {

src/Databases/DatabaseReplicated.cpp

@@ -2245,7 +2245,8 @@ bool DatabaseReplicated::shouldReplicateQuery(const ContextPtr & query_context,
     if (const auto * alter = query_ptr->as<const ASTAlterQuery>())
     {
         if (alter->isAttachAlter() || alter->isFetchAlter() || alter->isDropPartitionAlter()
-            || is_keeper_map_table(query_ptr) || alter->isFreezeAlter() || alter->isUnlockSnapshot())
+            || is_keeper_map_table(query_ptr) || alter->isFreezeAlter() || alter->isUnlockSnapshot()
+            || alter->isExportPartAlter())
             return false;
 
         if (has_many_shards() || !is_replicated_table(query_ptr))

src/Disks/ObjectStorages/IObjectStorage.h

@@ -129,6 +129,8 @@ struct RelativePathWithMetadata
     virtual ~RelativePathWithMetadata() = default;
 
     virtual std::string getFileName() const { return std::filesystem::path(relative_path).filename(); }
+    virtual std::string getFileNameWithoutExtension() const { return std::filesystem::path(relative_path).stem(); }
+
     virtual std::string getPath() const { return relative_path; }
     virtual bool isArchive() const { return false; }
     virtual std::string getPathToArchive() const { throw Exception(ErrorCodes::LOGICAL_ERROR, "Not an archive"); }

src/Interpreters/Context.cpp

@@ -324,6 +324,7 @@ namespace ServerSetting
     extern const ServerSettingsUInt64 max_local_write_bandwidth_for_server;
     extern const ServerSettingsUInt64 max_merges_bandwidth_for_server;
     extern const ServerSettingsUInt64 max_mutations_bandwidth_for_server;
+    extern const ServerSettingsUInt64 max_exports_bandwidth_for_server;
     extern const ServerSettingsUInt64 max_remote_read_network_bandwidth_for_server;
     extern const ServerSettingsUInt64 max_remote_write_network_bandwidth_for_server;
     extern const ServerSettingsUInt64 max_replicated_fetches_network_bandwidth_for_server;
@@ -544,6 +545,8 @@ struct ContextSharedPart : boost::noncopyable
     mutable ThrottlerPtr mutations_throttler;               /// A server-wide throttler for mutations
     mutable ThrottlerPtr merges_throttler;                  /// A server-wide throttler for merges
 
+    mutable ThrottlerPtr exports_throttler;                /// A server-wide throttler for exports
+
     MultiVersion<Macros> macros;                            /// Substitutions extracted from config.
     std::unique_ptr<DDLWorker> ddl_worker TSA_GUARDED_BY(mutex); /// Process ddl commands from zk.
     LoadTaskPtr ddl_worker_startup_task;                         /// To postpone `ddl_worker->startup()` after all tables startup
@@ -1051,6 +1054,9 @@ struct ContextSharedPart : boost::noncopyable
 
         if (auto bandwidth = server_settings[ServerSetting::max_merges_bandwidth_for_server])
             merges_throttler = std::make_shared<Throttler>(bandwidth, ProfileEvents::MergesThrottlerBytes, ProfileEvents::MergesThrottlerSleepMicroseconds);
+
+        if (auto bandwidth = server_settings[ServerSetting::max_exports_bandwidth_for_server])
+            exports_throttler = std::make_shared<Throttler>(bandwidth, ProfileEvents::ExportsThrottlerBytes, ProfileEvents::ExportsThrottlerSleepMicroseconds);
     }
 };
 
@@ -4148,6 +4154,11 @@ ThrottlerPtr Context::getMergesThrottler() const
     return shared->merges_throttler;
 }
 
+ThrottlerPtr Context::getExportsThrottler() const
+{
+    return shared->exports_throttler;
+}
+
 void Context::reloadRemoteThrottlerConfig(size_t read_bandwidth, size_t write_bandwidth) const
 {
     if (read_bandwidth)

src/Interpreters/Context.h

@@ -1659,6 +1659,7 @@ class Context: public ContextData, public std::enable_shared_from_this<Context>
 
     ThrottlerPtr getMutationsThrottler() const;
     ThrottlerPtr getMergesThrottler() const;
+    ThrottlerPtr getExportsThrottler() const;
 
     void reloadRemoteThrottlerConfig(size_t read_bandwidth, size_t write_bandwidth) const;
     void reloadLocalThrottlerConfig(size_t read_bandwidth, size_t write_bandwidth) const;

src/Interpreters/DDLWorker.cpp

@@ -752,7 +752,8 @@ bool DDLWorker::taskShouldBeExecutedOnLeader(const ASTPtr & ast_ddl, const Stora
             alter->isFreezeAlter() ||
             alter->isUnlockSnapshot() ||
             alter->isMovePartitionToDiskOrVolumeAlter() ||
-            alter->isCommentAlter())
+            alter->isCommentAlter() ||
+            alter->isExportPartAlter())
             return false;
     }