Merge branch 'antalya-25.8' into frontport/antalya-25.8/iceberg_features

ianton-ru · web-flow · commit 708d59b36aee · 2025-10-14T15:44:43.000+02:00
diff --git a/programs/server/Server.cpp b/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>
@@ -342,6 +343,9 @@ namespace ServerSetting
     extern const ServerSettingsBool abort_on_logical_error;
     extern const ServerSettingsUInt64 jemalloc_flush_profile_interval_bytes;
     extern const ServerSettingsBool jemalloc_flush_profile_on_memory_exceeded;
+    extern const ServerSettingsUInt64 object_storage_list_objects_cache_ttl;
+    extern const ServerSettingsUInt64 object_storage_list_objects_cache_size;
+    extern const ServerSettingsUInt64 object_storage_list_objects_cache_max_entries;
     extern const ServerSettingsUInt64 input_format_parquet_metadata_cache_max_size;
 }
 
@@ -353,6 +357,9 @@ namespace ErrorCodes
 namespace FileCacheSetting
 {
     extern const FileCacheSettingsBool load_metadata_asynchronously;
+    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;
 }
 
 }
@@ -2527,6 +2534,10 @@ 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
diff --git a/src/Access/Common/AccessType.h b/src/Access/Common/AccessType.h
@@ -320,6 +320,7 @@ 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_OBJECT_STORAGE_LIST_OBJECTS_CACHE, "SYSTEM DROP OBJECT STORAGE LIST OBJECTS 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) \
diff --git a/src/Common/ProfileEvents.cpp b/src/Common/ProfileEvents.cpp
@@ -1139,6 +1139,10 @@ The server successfully detected this situation and will download merged part fr
     M(AsyncLoggingErrorFileLogDroppedMessages, "How many messages have been dropped from error file log due to the async log queue being full", ValueType::Number) \
     M(AsyncLoggingSyslogDroppedMessages, "How many messages have been dropped from the syslog due to the async log queue being full", ValueType::Number) \
     M(AsyncLoggingTextLogDroppedMessages, "How many messages have been dropped from text_log due to the async log queue being full", 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) \
     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) \
 
diff --git a/src/Common/TTLCachePolicy.h b/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.
diff --git a/src/Core/ServerSettings.cpp b/src/Core/ServerSettings.cpp
@@ -1139,6 +1139,9 @@ The policy on how to perform a scheduling of CPU slots specified by `concurrent_
     DECLARE(UInt64, threadpool_local_fs_reader_queue_size, 1000000, R"(The maximum number of jobs that can be scheduled on the thread pool for reading from local filesystem.)", 0) \
     DECLARE(NonZeroUInt64, threadpool_remote_fs_reader_pool_size, 250, R"(Number of threads in the Thread pool used for reading from remote filesystem when `remote_filesystem_read_method = 'threadpool'`.)", 0) \
     DECLARE(UInt64, threadpool_remote_fs_reader_queue_size, 1000000, R"(The maximum number of jobs that can be scheduled on the thread pool for reading from remote filesystem.)", 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)                   \
     DECLARE(UInt64, input_format_parquet_metadata_cache_max_size, 500000000, "Maximum size of parquet file metadata cache", 0) \
 // clang-format on
 
diff --git a/src/Core/Settings.cpp b/src/Core/Settings.cpp
@@ -7010,6 +7010,9 @@ Write full paths (including s3://) into iceberg metadata files.
 )", EXPERIMENTAL) \
     DECLARE(String, iceberg_metadata_compression_method, "", R"(
 Method to compress `.metadata.json` file.
+)", 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, make_distributed_plan, false, R"(
 Make distributed query plan.
diff --git a/src/Core/SettingsChangesHistory.cpp b/src/Core/SettingsChangesHistory.cpp
@@ -120,6 +120,7 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()
             {"allow_experimental_lightweight_update", false, true, "Lightweight updates were moved to Beta."},
             {"s3_slow_all_threads_after_retryable_error", false, false, "Added an alias for setting `backup_slow_all_threads_after_retryable_s3_error`"},
             {"iceberg_metadata_log_level", "none", "none", "New setting."},
+            {"use_object_storage_list_objects_cache", false, false, "New setting."},
         });
         addSettingsChanges(settings_changes_history, "25.7",
         {
diff --git a/src/Disks/ObjectStorages/AzureBlobStorage/AzureObjectStorage.h b/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.
diff --git a/src/Disks/ObjectStorages/IObjectStorage.h b/src/Disks/ObjectStorages/IObjectStorage.h
@@ -365,6 +365,14 @@ class IObjectStorage
     }
     virtual std::shared_ptr<const S3::Client> tryGetS3StorageClient() { return nullptr; }
 #endif
+
+
+    virtual bool supportsListObjectsCache() { return false; }
+
+private:
+    mutable std::mutex throttlers_mutex;
+    ThrottlerPtr remote_read_throttler;
+    ThrottlerPtr remote_write_throttler;
 };
 
 using ObjectStoragePtr = std::shared_ptr<IObjectStorage>;
diff --git a/src/Disks/ObjectStorages/S3/S3ObjectStorage.h b/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
diff --git a/src/Interpreters/InterpreterSystemQuery.cpp b/src/Interpreters/InterpreterSystemQuery.cpp
@@ -48,6 +48,7 @@
 #include <Parsers/ASTSetQuery.h>
 #include <Parsers/ASTSystemQuery.h>
 #include <Processors/Sources/SourceFromSingleChunk.h>
+#include <Storages/Cache/ObjectStorageListObjectsCache.h>
 #include <Storages/Freeze.h>
 #include <Storages/MaterializedView/RefreshTask.h>
 #include <Storages/ObjectStorage/Azure/Configuration.h>
@@ -440,6 +441,12 @@ BlockIO InterpreterSystemQuery::execute()
             getContext()->clearQueryResultCache(query.query_result_cache_tag);
             break;
         }
+        case Type::DROP_OBJECT_STORAGE_LIST_OBJECTS_CACHE:
+        {
+            getContext()->checkAccess(AccessType::SYSTEM_DROP_OBJECT_STORAGE_LIST_OBJECTS_CACHE);
+            ObjectStorageListObjectsCache::instance().clear();
+            break;
+        }
         case Type::DROP_PARQUET_METADATA_CACHE:
         {
 #if USE_PARQUET
@@ -1603,6 +1610,7 @@ AccessRightsElements InterpreterSystemQuery::getRequiredAccessForDDLOnCluster()
         case Type::DROP_PAGE_CACHE:
         case Type::DROP_SCHEMA_CACHE:
         case Type::DROP_FORMAT_SCHEMA_CACHE:
+        case Type::DROP_OBJECT_STORAGE_LIST_OBJECTS_CACHE:
         case Type::DROP_PARQUET_METADATA_CACHE:
         case Type::DROP_S3_CLIENT_CACHE:
         {
diff --git a/src/Parsers/ASTSystemQuery.cpp b/src/Parsers/ASTSystemQuery.cpp
@@ -484,6 +484,7 @@ 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_OBJECT_STORAGE_LIST_OBJECTS_CACHE:
         case Type::DROP_PARQUET_METADATA_CACHE:
         case Type::RESET_COVERAGE:
         case Type::RESTART_REPLICAS:
diff --git a/src/Parsers/ASTSystemQuery.h b/src/Parsers/ASTSystemQuery.h
@@ -41,6 +41,7 @@ class ASTSystemQuery : public IAST, public ASTQueryWithOnCluster
         DROP_SCHEMA_CACHE,
         DROP_FORMAT_SCHEMA_CACHE,
         DROP_S3_CLIENT_CACHE,
+        DROP_OBJECT_STORAGE_LIST_OBJECTS_CACHE,
         DROP_PARQUET_METADATA_CACHE,
         STOP_LISTEN,
         START_LISTEN,
diff --git a/src/Storages/Cache/ObjectStorageListObjectsCache.cpp b/src/Storages/Cache/ObjectStorageListObjectsCache.cpp
@@ -0,0 +1,210 @@
+#include <Storages/Cache/ObjectStorageListObjectsCache.h>
+#include <Common/TTLCachePolicy.h>
+#include <Common/ProfileEvents.h>
+#include <boost/functional/hash.hpp>
+
+namespace ProfileEvents
+{
+extern const Event ObjectStorageListObjectsCacheHits;
+extern const Event ObjectStorageListObjectsCacheMisses;
+extern const Event ObjectStorageListObjectsCacheExactMatchHits;
+extern const Event ObjectStorageListObjectsCachePrefixMatchHits;
+}
+
+namespace DB
+{
+
+template <typename Key, typename Mapped, typename HashFunction, typename WeightFunction, typename IsStaleFunction>
+class ObjectStorageListObjectsCachePolicy : public TTLCachePolicy<Key, Mapped, HashFunction, WeightFunction, IsStaleFunction>
+{
+public:
+    using BasePolicy = TTLCachePolicy<Key, Mapped, HashFunction, WeightFunction, IsStaleFunction>;
+    using typename BasePolicy::MappedPtr;
+    using typename BasePolicy::KeyMapped;
+    using BasePolicy::cache;
+
+    ObjectStorageListObjectsCachePolicy()
+        : BasePolicy(CurrentMetrics::end(), CurrentMetrics::end(), std::make_unique<NoCachePolicyUserQuota>())
+    {
+    }
+
+    std::optional<KeyMapped> getWithKey(const Key & key) override
+    {
+        if (const auto it = cache.find(key); it != cache.end())
+        {
+            if (!IsStaleFunction()(it->first))
+            {
+                return std::make_optional<KeyMapped>({it->first, it->second});
+            }
+            // found a stale entry, remove it but don't return. We still want to perform the prefix matching search
+            BasePolicy::remove(it->first);
+        }
+
+        if (const auto it = findBestMatchingPrefixAndRemoveExpiredEntries(key); it != cache.end())
+        {
+            return std::make_optional<KeyMapped>({it->first, it->second});
+        }
+
+        return std::nullopt;
+    }
+
+private:
+    auto findBestMatchingPrefixAndRemoveExpiredEntries(Key key)
+    {
+        while (!key.prefix.empty())
+        {
+            if (const auto it = cache.find(key); it != cache.end())
+            {
+                if (IsStaleFunction()(it->first))
+                {
+                    BasePolicy::remove(it->first);
+                }
+                else
+                {
+                    return it;
+                }
+            }
+
+            key.prefix.pop_back();
+        }
+
+        return cache.end();
+    }
+};
+
+ObjectStorageListObjectsCache::Key::Key(
+    const String & storage_description_,
+    const String & bucket_,
+    const String & prefix_,
+    const std::chrono::steady_clock::time_point & expires_at_,
+    std::optional<UUID> user_id_)
+    : storage_description(storage_description_), bucket(bucket_), prefix(prefix_), expires_at(expires_at_), user_id(user_id_) {}
+
+bool ObjectStorageListObjectsCache::Key::operator==(const Key & other) const
+{
+    return storage_description == other.storage_description && bucket == other.bucket && prefix == other.prefix;
+}
+
+size_t ObjectStorageListObjectsCache::KeyHasher::operator()(const Key & key) const
+{
+    std::size_t seed = 0;
+
+    boost::hash_combine(seed, key.storage_description);
+    boost::hash_combine(seed, key.bucket);
+    boost::hash_combine(seed, key.prefix);
+
+    return seed;
+}
+
+bool ObjectStorageListObjectsCache::IsStale::operator()(const Key & key) const
+{
+    return key.expires_at < std::chrono::steady_clock::now();
+}
+
+size_t ObjectStorageListObjectsCache::WeightFunction::operator()(const Value & value) const
+{
+    std::size_t weight = 0;
+
+    for (const auto & object : value)
+    {
+        const auto object_metadata = object->metadata;
+        weight += object->relative_path.capacity() + sizeof(object_metadata);
+
+        // variable size
+        if (object_metadata)
+        {
+            weight += object_metadata->etag.capacity();
+            weight += object_metadata->attributes.size() * (sizeof(std::string) * 2);
+
+            for (const auto & [k, v] : object_metadata->attributes)
+            {
+                weight += k.capacity() + v.capacity();
+            }
+        }
+    }
+
+    return weight;
+}
+
+ObjectStorageListObjectsCache::ObjectStorageListObjectsCache()
+    : cache(std::make_unique<ObjectStorageListObjectsCachePolicy<Key, Value, KeyHasher, WeightFunction, IsStale>>())
+{
+}
+
+void ObjectStorageListObjectsCache::set(
+    const Key & key,
+    const std::shared_ptr<Value> & value)
+{
+    auto key_with_ttl = key;
+    key_with_ttl.expires_at = std::chrono::steady_clock::now() + std::chrono::seconds(ttl_in_seconds);
+
+    cache.set(key_with_ttl, value);
+}
+
+void ObjectStorageListObjectsCache::clear()
+{
+    cache.clear();
+}
+
+std::optional<ObjectStorageListObjectsCache::Value> ObjectStorageListObjectsCache::get(const Key & key, bool filter_by_prefix)
+{
+    const auto pair = cache.getWithKey(key);
+
+    if (!pair)
+    {
+        ProfileEvents::increment(ProfileEvents::ObjectStorageListObjectsCacheMisses);
+        return {};
+    }
+
+    ProfileEvents::increment(ProfileEvents::ObjectStorageListObjectsCacheHits);
+
+    if (pair->key == key)
+    {
+        ProfileEvents::increment(ProfileEvents::ObjectStorageListObjectsCacheExactMatchHits);
+        return *pair->mapped;
+    }
+
+    ProfileEvents::increment(ProfileEvents::ObjectStorageListObjectsCachePrefixMatchHits);
+
+    if (!filter_by_prefix)
+    {
+        return *pair->mapped;
+    }
+
+    Value filtered_objects;
+
+    filtered_objects.reserve(pair->mapped->size());
+
+    for (const auto & object : *pair->mapped)
+    {
+        if (object->relative_path.starts_with(key.prefix))
+        {
+            filtered_objects.push_back(object);
+        }
+    }
+
+    return filtered_objects;
+}
+
+void ObjectStorageListObjectsCache::setMaxSizeInBytes(std::size_t size_in_bytes_)
+{
+    cache.setMaxSizeInBytes(size_in_bytes_);
+}
+
+void ObjectStorageListObjectsCache::setMaxCount(std::size_t count)
+{
+    cache.setMaxCount(count);
+}
+
+void ObjectStorageListObjectsCache::setTTL(std::size_t ttl_in_seconds_)
+{
+    ttl_in_seconds = ttl_in_seconds_;
+}
+
+ObjectStorageListObjectsCache & ObjectStorageListObjectsCache::instance()
+{
+    static ObjectStorageListObjectsCache instance;
+    return instance;
+}
+
+}
diff --git a/src/Storages/Cache/ObjectStorageListObjectsCache.h b/src/Storages/Cache/ObjectStorageListObjectsCache.h
diff --git a/src/Storages/Cache/tests/gtest_object_storage_list_objects_cache.cpp b/src/Storages/Cache/tests/gtest_object_storage_list_objects_cache.cpp
diff --git a/src/Storages/ObjectStorage/StorageObjectStorageSource.cpp b/src/Storages/ObjectStorage/StorageObjectStorageSource.cpp
diff --git a/src/Storages/ObjectStorage/StorageObjectStorageSource.h b/src/Storages/ObjectStorage/StorageObjectStorageSource.h
diff --git a/tests/queries/0_stateless/01271_show_privileges.reference b/tests/queries/0_stateless/01271_show_privileges.reference
diff --git a/tests/queries/0_stateless/03377_object_storage_list_objects_cache.reference b/tests/queries/0_stateless/03377_object_storage_list_objects_cache.reference
diff --git a/tests/queries/0_stateless/03377_object_storage_list_objects_cache.sql b/tests/queries/0_stateless/03377_object_storage_list_objects_cache.sql

Original file line number	Diff line number	Diff line change
`@@ -120,6 +120,7 @@ const VersionToSettingsChangesMap & getSettingsChangesHistory()`
`120`	`120`	`{"allow_experimental_lightweight_update", false, true, "Lightweight updates were moved to Beta."},`
`121`	`121`	{"s3_slow_all_threads_after_retryable_error", false, false, "Added an alias for setting `backup_slow_all_threads_after_retryable_s3_error`"},
`122`	`122`	`{"iceberg_metadata_log_level", "none", "none", "New setting."},`
	`123`	`+ {"use_object_storage_list_objects_cache", false, false, "New setting."},`
`123`	`124`	`});`
`124`	`125`	`addSettingsChanges(settings_changes_history, "25.7",`
`125`	`126`	`{`