Merge remote-tracking branch 'altinity/forwardports/25.6.5/743_list_objects_object_storage_cache' into ports/25.6/amalgamation_of_metadata_prs

Author: Enmk

programs/server/Server.cpp

@@ -83,6 +83,7 @@
 #include <Storages/System/attachSystemTables.h>
 #include <Storages/System/attachInformationSchemaTables.h>
 #include <Storages/Cache/registerRemoteFileMetadatas.h>
+#include <Storages/Cache/ObjectStorageListObjectsCache.h>
 #include <AggregateFunctions/registerAggregateFunctions.h>
 #include <Functions/UserDefined/IUserDefinedSQLObjectsStorage.h>
 #include <Functions/registerFunctions.h>
@@ -331,6 +332,10 @@ namespace ServerSetting
     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;
+    extern const ServerSettingsUInt64 object_storage_list_objects_cache_size;
+    extern const ServerSettingsUInt64 object_storage_list_objects_cache_max_entries;
+    extern const ServerSettingsUInt64 object_storage_list_objects_cache_ttl;
+
 }
 
 namespace ErrorCodes
@@ -418,6 +423,7 @@ namespace ErrorCodes
     extern const int NETWORK_ERROR;
     extern const int CORRUPTED_DATA;
     extern const int BAD_ARGUMENTS;
+    extern const int STARTUP_SCRIPTS_ERROR;
 }
 
 
@@ -2426,6 +2432,10 @@ try
     if (dns_cache_updater)
         dns_cache_updater->start();
 
+    ObjectStorageListObjectsCache::instance().setMaxSizeInBytes(server_settings[ServerSetting::object_storage_list_objects_cache_size]);
+    ObjectStorageListObjectsCache::instance().setMaxCount(server_settings[ServerSetting::object_storage_list_objects_cache_max_entries]);
+    ObjectStorageListObjectsCache::instance().setTTL(server_settings[ServerSetting::object_storage_list_objects_cache_ttl]);
+
     auto replicas_reconnector = ReplicasReconnector::init(global_context);
 
 #if USE_PARQUET

src/Access/Common/AccessType.h

@@ -185,6 +185,7 @@ enum class AccessType : uint8_t
     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_OBJECT_STORAGE_LIST_OBJECTS_CACHE, "SYSTEM DROP OBJECT STORAGE LIST OBJECTS 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

@@ -1043,6 +1043,10 @@ The server successfully detected this situation and will download merged part fr
     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) \
+    M(ObjectStorageListObjectsCacheHits, "Number of times object storage list objects operation hit the cache.", ValueType::Number) \
+    M(ObjectStorageListObjectsCacheMisses, "Number of times object storage list objects operation miss the cache.", ValueType::Number)                                                                                                                                                                                                                                  \
+    M(ObjectStorageListObjectsCacheExactMatchHits, "Number of times object storage list objects operation hit the cache with an exact match.", ValueType::Number) \
+    M(ObjectStorageListObjectsCachePrefixMatchHits, "Number of times object storage list objects operation miss the cache using prefix matching.", ValueType::Number) \
 
 #ifdef APPLY_FOR_EXTERNAL_EVENTS
     #define APPLY_FOR_EVENTS(M) APPLY_FOR_BUILTIN_EVENTS(M) APPLY_FOR_EXTERNAL_EVENTS(M)

src/Common/TTLCachePolicy.h

@@ -271,10 +271,10 @@ class TTLCachePolicy : public ICachePolicy<Key, Mapped, HashFunction, WeightFunc
         return res;
     }
 
-private:
+protected:
     using Cache = std::unordered_map<Key, MappedPtr, HashFunction>;
     Cache cache;
-
+private:
     /// TODO To speed up removal of stale entries, we could also add another container sorted on expiry times which maps keys to iterators
     /// into the cache. To insert an entry, add it to the cache + add the iterator to the sorted container. To remove stale entries, do a
     /// binary search on the sorted container and erase all left of the found key.

src/Core/ServerSettings.cpp

@@ -1065,6 +1065,10 @@ The policy on how to perform a scheduling of CPU slots specified by `concurrent_
     )", 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) \
+    DECLARE(UInt64, object_storage_list_objects_cache_size, 500000000, "Maximum size of ObjectStorage list objects cache in bytes. Zero means disabled.", 0)                            \
+    DECLARE(UInt64, object_storage_list_objects_cache_max_entries, 1000, "Maximum size of ObjectStorage list objects cache in entries. Zero means disabled.", 0)                      \
+    DECLARE(UInt64, object_storage_list_objects_cache_ttl, 3600, "Time to live of records in ObjectStorage list objects cache in seconds. Zero means unlimited", 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/Settings.cpp

@@ -6865,6 +6865,9 @@ Default number of buckets for distributed shuffle-hash-join.
 )", EXPERIMENTAL) \
     DECLARE(UInt64, distributed_plan_default_reader_bucket_count, 8, R"(
 Default number of tasks for parallel reading in distributed query. Tasks are spread across between replicas.
+)", EXPERIMENTAL) \
+    DECLARE(Bool, use_object_storage_list_objects_cache, false, R"(
+Cache the list of objects returned by list objects calls in object storage
 )", EXPERIMENTAL) \
     DECLARE(Bool, distributed_plan_optimize_exchanges, true, R"(
 Removes unnecessary exchanges in distributed query plan. Disable it for debugging.

src/Core/SettingsChangesHistory.cpp

@@ -173,6 +173,10 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
             {"parallel_hash_join_threshold", 0, 0, "New setting"},
             {"function_date_trunc_return_type_behavior", 1, 0, "Change the result type for dateTrunc function for DateTime64/Date32 arguments to DateTime64/Date32 regardless of time unit to get correct result for negative values"},
             /// Release closed. Please use 25.5
+            // Altinity Antalya modifications atop of 25.2
+            {"object_storage_cluster", "", "", "New setting"},
+            {"object_storage_max_nodes", 0, 0, "New setting"},
+            {"use_object_storage_list_objects_cache", true, false, "New setting."},
         });
         addSettingsChanges(settings_changes_history, "25.3",
         {

src/Disks/ObjectStorages/AzureBlobStorage/AzureObjectStorage.h

@@ -35,6 +35,8 @@ class AzureObjectStorage : public IObjectStorage
         const String & description_,
         const String & common_key_prefix_);
 
+    bool supportsListObjectsCache() override { return true; }
+
     void listObjects(const std::string & path, RelativePathsWithMetadata & children, size_t max_keys) const override;
 
     /// Sanitizer build may crash with max_keys=1; this looks like a false positive.

src/Disks/ObjectStorages/IObjectStorage.h

@@ -317,6 +317,8 @@ class IObjectStorage
 #endif
 
 
+    virtual bool supportsListObjectsCache() { return false; }
+
 private:
     mutable std::mutex throttlers_mutex;
     ThrottlerPtr remote_read_throttler;

src/Disks/ObjectStorages/S3/S3ObjectStorage.h

@@ -61,6 +61,8 @@ class S3ObjectStorage : public IObjectStorage
 
     ObjectStorageType getType() const override { return ObjectStorageType::S3; }
 
+    bool supportsListObjectsCache() override { return true; }
+
     bool exists(const StoredObject & object) const override;
 
     std::unique_ptr<ReadBufferFromFileBase> readObject( /// NOLINT