Merge pull request #71640 from ClickHouse/cache-allow-to-disable-memory-buffer-increase-in-fs-cache

Allow to disable memory buffer increase for filesystem cache

src/Core/Settings.cpp

@@ -4875,6 +4875,9 @@ Limit on size of a single batch of file segments that a read buffer can request
 )", 0) \
     DECLARE(UInt64, filesystem_cache_reserve_space_wait_lock_timeout_milliseconds, 1000, R"(
 Wait time to lock cache for space reservation in filesystem cache
+)", 0) \
+    DECLARE(Bool, filesystem_cache_prefer_bigger_buffer_size, true, R"(
+Prefer bigger buffer size if filesystem cache is enabled to avoid writing small file segments which deteriorate cache performance. On the other hand, enabling this setting might increase memory usage.
 )", 0) \
     DECLARE(UInt64, temporary_data_in_cache_reserve_space_wait_lock_timeout_milliseconds, (10 * 60 * 1000), R"(
 Wait time to lock cache for space reservation for temporary data in filesystem cache

src/Core/SettingsChangesHistory.cpp

@@ -77,6 +77,7 @@ static std::initializer_list<std::pair<ClickHouseVersion, SettingsChangesHistory
             {"backup_restore_keeper_max_retries_while_handling_error", 0, 20, "New setting."},
             {"backup_restore_finish_timeout_after_error_sec", 0, 180, "New setting."},
             {"parallel_replicas_local_plan", false, true, "Use local plan for local replica in a query with parallel replicas"},
+            {"filesystem_cache_prefer_bigger_buffer_size", true, true, "New setting"},
             {"read_in_order_use_virtual_row", false, false, "Use virtual row while reading in order of primary key or its monotonic function fashion. It is useful when searching over multiple parts as only relevant ones are touched."},
         }
     },

src/Disks/ObjectStorages/DiskObjectStorage.cpp

@@ -642,7 +642,10 @@ std::unique_ptr<ReadBufferFromFileBase> DiskObjectStorage::readFile(
     };
 
     /// Avoid cache fragmentation by choosing bigger buffer size.
-    bool prefer_bigger_buffer_size = object_storage->supportsCache() && read_settings.enable_filesystem_cache;
+    bool prefer_bigger_buffer_size = read_settings.filesystem_cache_prefer_bigger_buffer_size
+        && object_storage->supportsCache()
+        && read_settings.enable_filesystem_cache;
+
     size_t buffer_size = prefer_bigger_buffer_size
         ? std::max<size_t>(settings.remote_fs_buffer_size, DBMS_DEFAULT_BUFFER_SIZE)
         : settings.remote_fs_buffer_size;

src/IO/ReadSettings.h

@@ -61,6 +61,7 @@ struct ReadSettings
     bool filesystem_cache_allow_background_download = true;
     bool filesystem_cache_allow_background_download_for_metadata_files_in_packed_storage = true;
     bool filesystem_cache_allow_background_download_during_fetch = true;
+    bool filesystem_cache_prefer_bigger_buffer_size = true;
 
     bool use_page_cache_for_disks_without_file_cache = false;
     bool read_from_page_cache_if_exists_otherwise_bypass_cache = false;

src/Interpreters/Context.cpp

@@ -196,6 +196,7 @@ namespace Setting
     extern const SettingsUInt64 filesystem_cache_segments_batch_size;
     extern const SettingsBool filesystem_cache_enable_background_download_for_metadata_files_in_packed_storage;
     extern const SettingsBool filesystem_cache_enable_background_download_during_fetch;
+    extern const SettingsBool filesystem_cache_prefer_bigger_buffer_size;
     extern const SettingsBool http_make_head_request;
     extern const SettingsUInt64 http_max_fields;
     extern const SettingsUInt64 http_max_field_name_size;
@@ -5751,6 +5752,7 @@ ReadSettings Context::getReadSettings() const
     res.filesystem_cache_allow_background_download_for_metadata_files_in_packed_storage
         = settings_ref[Setting::filesystem_cache_enable_background_download_for_metadata_files_in_packed_storage];
     res.filesystem_cache_allow_background_download_during_fetch = settings_ref[Setting::filesystem_cache_enable_background_download_during_fetch];
+    res.filesystem_cache_prefer_bigger_buffer_size = settings_ref[Setting::filesystem_cache_prefer_bigger_buffer_size];
 
     res.filesystem_cache_max_download_size = settings_ref[Setting::filesystem_cache_max_download_size];
     res.skip_download_if_exceeds_query_cache = settings_ref[Setting::skip_download_if_exceeds_query_cache];

src/Storages/ObjectStorage/StorageObjectStorageSource.cpp

@@ -517,7 +517,7 @@ std::unique_ptr<ReadBufferFromFileBase> StorageObjectStorageSource::createReadBu
 
     LOG_TRACE(log, "Downloading object of size {} with initial prefetch", object_size);
 
-    bool prefer_bigger_buffer_size = impl->isCached();
+    bool prefer_bigger_buffer_size = read_settings.filesystem_cache_prefer_bigger_buffer_size && impl->isCached();
     size_t buffer_size = prefer_bigger_buffer_size
         ? std::max<size_t>(read_settings.remote_fs_buffer_size, DBMS_DEFAULT_BUFFER_SIZE)
         : read_settings.remote_fs_buffer_size;