Merge pull request #937 from Altinity/revert-930-forwardports/25.6.5/795_parquet_metadata_caching

Revert "Antalya 25.6.5: Forward port of #795 - Parquet Metadata Caching"

Author: arthurpassos

programs/server/Server.cpp

@@ -156,10 +156,6 @@
 #   include <azure/core/diagnostics/logger.hpp>
 #endif
 
-#if USE_PARQUET
-#   include <Processors/Formats/Impl/ParquetFileMetaDataCache.h>
-#endif
-
 
 #include <incbin.h>
 /// A minimal file used when the server is run without installation
@@ -330,7 +326,6 @@ namespace ServerSetting
     extern const ServerSettingsUInt64 os_cpu_busy_time_threshold;
     extern const ServerSettingsFloat min_os_cpu_wait_time_ratio_to_drop_connection;
     extern const ServerSettingsFloat max_os_cpu_wait_time_ratio_to_drop_connection;
-    extern const ServerSettingsUInt64 input_format_parquet_metadata_cache_max_size;
 }
 
 namespace ErrorCodes
@@ -2428,10 +2423,6 @@ try
 
     auto replicas_reconnector = ReplicasReconnector::init(global_context);
 
-#if USE_PARQUET
-    ParquetFileMetaDataCache::instance()->setMaxSizeInBytes(server_settings[ServerSetting::input_format_parquet_metadata_cache_max_size]);
-#endif
-
     /// Set current database name before loading tables and databases because
     /// system logs may copy global context.
     std::string default_database = server_settings[ServerSetting::default_database];

src/Access/Common/AccessType.h

@@ -184,7 +184,6 @@ enum class AccessType : uint8_t
     M(SYSTEM_DROP_SCHEMA_CACHE, "SYSTEM DROP SCHEMA CACHE, DROP SCHEMA CACHE", GLOBAL, SYSTEM_DROP_CACHE) \
     M(SYSTEM_DROP_FORMAT_SCHEMA_CACHE, "SYSTEM DROP FORMAT SCHEMA CACHE, DROP FORMAT SCHEMA CACHE", GLOBAL, SYSTEM_DROP_CACHE) \
     M(SYSTEM_DROP_S3_CLIENT_CACHE, "SYSTEM DROP S3 CLIENT, DROP S3 CLIENT CACHE", GLOBAL, SYSTEM_DROP_CACHE) \
-    M(SYSTEM_DROP_PARQUET_METADATA_CACHE, "SYSTEM DROP PARQUET METADATA CACHE", GLOBAL, SYSTEM_DROP_CACHE) \
     M(SYSTEM_DROP_CACHE, "DROP CACHE", GROUP, SYSTEM) \
     M(SYSTEM_RELOAD_CONFIG, "RELOAD CONFIG", GLOBAL, SYSTEM_RELOAD) \
     M(SYSTEM_RELOAD_USERS, "RELOAD USERS", GLOBAL, SYSTEM_RELOAD) \

src/Common/ProfileEvents.cpp

@@ -1041,8 +1041,7 @@ The server successfully detected this situation and will download merged part fr
     M(IndexGenericExclusionSearchAlgorithm, "Number of times the generic exclusion search algorithm is used over the index marks", ValueType::Number) \
     M(ParallelReplicasQueryCount, "Number of (sub)queries executed using parallel replicas during a query execution", ValueType::Number) \
     M(DistributedConnectionReconnectCount, "Number of reconnects to other servers done during distributed query execution. It can happen when a stale connection has been acquired from connection pool", ValueType::Number) \
-    M(ParquetMetaDataCacheHits, "Number of times the read from filesystem cache hit the cache.", ValueType::Number) \
-    M(ParquetMetaDataCacheMisses, "Number of times the read from filesystem cache miss the cache.", ValueType::Number) \
+
 
 #ifdef APPLY_FOR_EXTERNAL_EVENTS
     #define APPLY_FOR_EVENTS(M) APPLY_FOR_BUILTIN_EVENTS(M) APPLY_FOR_EXTERNAL_EVENTS(M)

src/Core/FormatFactorySettings.h

@@ -1348,7 +1348,8 @@ Limits the size of the blocks formed during data parsing in input formats in byt
     DECLARE(Bool, input_format_parquet_allow_geoparquet_parser, true, R"(
 Use geo column parser to convert Array(UInt8) into Point/Linestring/Polygon/MultiLineString/MultiPolygon types
 )", 0) \
-    DECLARE(Bool, input_format_parquet_use_metadata_cache, true, R"(Enable parquet file metadata caching)", 0) \
+
+
 // End of FORMAT_FACTORY_SETTINGS
 
 #define OBSOLETE_FORMAT_SETTINGS(M, ALIAS) \

src/Core/ServerSettings.cpp

@@ -1064,7 +1064,8 @@ The policy on how to perform a scheduling of CPU slots specified by `concurrent_
     See [Controlling behavior on server CPU overload](/operations/settings/server-overload) for more details.
     )", 0) \
     DECLARE(Float, distributed_cache_keep_up_free_connections_ratio, 0.1f, "Soft limit for number of active connection distributed cache will try to keep free. After the number of free connections goes below distributed_cache_keep_up_free_connections_ratio * max_connections, connections with oldest activity will be closed until the number goes above the limit.", 0) \
-    DECLARE(UInt64, input_format_parquet_metadata_cache_max_size, 500000000, "Maximum size of parquet file metadata cache", 0) \
+
+
 // clang-format on
 
 /// If you add a setting which can be updated at runtime, please update 'changeable_settings' map in dumpToSystemServerSettingsColumns below

src/Core/SettingsChangesHistory.cpp

@@ -182,11 +182,6 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
             {"parallel_hash_join_threshold", 0, 0, "New setting"},
             /// Release closed. Please use 25.4
         });
-        addSettingsChanges(settings_changes_history, "24.12.2.20000",
-        {
-            // Altinity Antalya modifications atop of 24.12
-            {"input_format_parquet_use_metadata_cache", true, true, "New setting, turned ON by default"}, // https://github.com/Altinity/ClickHouse/pull/586
-        });
         addSettingsChanges(settings_changes_history, "25.2",
         {
             /// Release closed. Please use 25.3

src/Interpreters/InterpreterSystemQuery.cpp

@@ -79,10 +79,6 @@
 #include <Formats/ProtobufSchemas.h>
 #endif
 
-#if USE_PARQUET
-#include <Processors/Formats/Impl/ParquetFileMetaDataCache.h>
-#endif
-
 #if USE_AWS_S3
 #include <IO/S3/Client.h>
 #endif
@@ -437,16 +433,6 @@ BlockIO InterpreterSystemQuery::execute()
             getContext()->clearQueryResultCache(query.query_result_cache_tag);
             break;
         }
-        case Type::DROP_PARQUET_METADATA_CACHE:
-        {
-#if USE_PARQUET
-            getContext()->checkAccess(AccessType::SYSTEM_DROP_PARQUET_METADATA_CACHE);
-            ParquetFileMetaDataCache::instance()->clear();
-            break;
-#else
-            throw Exception(ErrorCodes::SUPPORT_IS_DISABLED, "The server was compiled without the support for Parquet");
-#endif
-        }
         case Type::DROP_COMPILED_EXPRESSION_CACHE:
 #if USE_EMBEDDED_COMPILER
             getContext()->checkAccess(AccessType::SYSTEM_DROP_COMPILED_EXPRESSION_CACHE);
@@ -1547,7 +1533,6 @@ AccessRightsElements InterpreterSystemQuery::getRequiredAccessForDDLOnCluster()
         case Type::DROP_PAGE_CACHE:
         case Type::DROP_SCHEMA_CACHE:
         case Type::DROP_FORMAT_SCHEMA_CACHE:
-        case Type::DROP_PARQUET_METADATA_CACHE:
         case Type::DROP_S3_CLIENT_CACHE:
         {
             required_access.emplace_back(AccessType::SYSTEM_DROP_CACHE);

src/Parsers/ASTSystemQuery.cpp

@@ -467,7 +467,6 @@ void ASTSystemQuery::formatImpl(WriteBuffer & ostr, const FormatSettings & setti
         case Type::DROP_COMPILED_EXPRESSION_CACHE:
         case Type::DROP_S3_CLIENT_CACHE:
         case Type::DROP_ICEBERG_METADATA_CACHE:
-        case Type::DROP_PARQUET_METADATA_CACHE:
         case Type::RESET_COVERAGE:
         case Type::RESTART_REPLICAS:
         case Type::JEMALLOC_PURGE:

src/Parsers/ASTSystemQuery.h

@@ -42,7 +42,6 @@ class ASTSystemQuery : public IAST, public ASTQueryWithOnCluster
         DROP_SCHEMA_CACHE,
         DROP_FORMAT_SCHEMA_CACHE,
         DROP_S3_CLIENT_CACHE,
-        DROP_PARQUET_METADATA_CACHE,
         STOP_LISTEN,
         START_LISTEN,
         RESTART_REPLICAS,

src/Processors/Formats/IInputFormat.h

@@ -70,9 +70,6 @@ class IInputFormat : public SourceWithKeyCondition
 
     void needOnlyCount() { need_only_count = true; }
 
-    /// Set additional info/key/id related to underlying storage of the ReadBuffer
-    virtual void setStorageRelatedUniqueKey(const Settings & /*settings*/, const String & /*key*/) {}
-
 protected:
     ReadBuffer & getReadBuffer() const { chassert(in); return *in; }