Replace estimated_size with optional<size> for IDisk::readFile()

v2: rebase to fix conflicts in DiskEncrypted.cpp

src/Disks/DiskCacheWrapper.cpp

@@ -89,15 +89,15 @@ std::unique_ptr<ReadBufferFromFileBase>
 DiskCacheWrapper::readFile(
     const String & path,
     const ReadSettings & settings,
-    size_t estimated_size) const
+    std::optional<size_t> size) const
 {
     if (!cache_file_predicate(path))
-        return DiskDecorator::readFile(path, settings, estimated_size);
+        return DiskDecorator::readFile(path, settings, size);
 
     LOG_DEBUG(log, "Read file {} from cache", backQuote(path));
 
     if (cache_disk->exists(path))
-        return cache_disk->readFile(path, settings, estimated_size);
+        return cache_disk->readFile(path, settings, size);
 
     auto metadata = acquireDownloadMetadata(path);
 
@@ -131,7 +131,7 @@ DiskCacheWrapper::readFile(
 
                 auto tmp_path = path + ".tmp";
                 {
-                    auto src_buffer = DiskDecorator::readFile(path, settings, estimated_size);
+                    auto src_buffer = DiskDecorator::readFile(path, settings, size);
                     auto dst_buffer = cache_disk->writeFile(tmp_path, settings.local_fs_buffer_size, WriteMode::Rewrite);
                     copyData(*src_buffer, *dst_buffer);
                 }
@@ -155,9 +155,9 @@ DiskCacheWrapper::readFile(
     }
 
     if (metadata->status == DOWNLOADED)
-        return cache_disk->readFile(path, settings, estimated_size);
+        return cache_disk->readFile(path, settings, size);
 
-    return DiskDecorator::readFile(path, settings, estimated_size);
+    return DiskDecorator::readFile(path, settings, size);
 }
 
 std::unique_ptr<WriteBufferFromFileBase>

src/Disks/DiskCacheWrapper.h

@@ -37,7 +37,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
 
     std::unique_ptr<WriteBufferFromFileBase> writeFile(const String & path, size_t buf_size, WriteMode mode) override;
 

src/Disks/DiskDecorator.cpp

@@ -115,9 +115,9 @@ void DiskDecorator::listFiles(const String & path, std::vector<String> & file_na
 
 std::unique_ptr<ReadBufferFromFileBase>
 DiskDecorator::readFile(
-    const String & path, const ReadSettings & settings, size_t estimated_size) const
+    const String & path, const ReadSettings & settings, std::optional<size_t> size) const
 {
-    return delegate->readFile(path, settings, estimated_size);
+    return delegate->readFile(path, settings, size);
 }
 
 std::unique_ptr<WriteBufferFromFileBase>

src/Disks/DiskDecorator.h

@@ -38,7 +38,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
 
     std::unique_ptr<WriteBufferFromFileBase> writeFile(
         const String & path,

src/Disks/DiskEncrypted.cpp

@@ -252,10 +252,10 @@ void DiskEncrypted::copy(const String & from_path, const std::shared_ptr<IDisk>
 std::unique_ptr<ReadBufferFromFileBase> DiskEncrypted::readFile(
     const String & path,
     const ReadSettings & settings,
-    size_t estimated_size) const
+    std::optional<size_t> size) const
 {
     auto wrapped_path = wrappedPath(path);
-    auto buffer = delegate->readFile(wrapped_path, settings, estimated_size);
+    auto buffer = delegate->readFile(wrapped_path, settings, size);
     if (buffer->eof())
     {
         /// File is empty, that's a normal case, see DiskEncrypted::truncateFile().

src/Disks/DiskEncrypted.h

@@ -122,7 +122,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
 
     std::unique_ptr<WriteBufferFromFileBase> writeFile(
         const String & path,

src/Disks/DiskLocal.cpp

@@ -259,9 +259,9 @@ void DiskLocal::replaceFile(const String & from_path, const String & to_path)
     fs::rename(from_file, to_file);
 }
 
-std::unique_ptr<ReadBufferFromFileBase> DiskLocal::readFile(const String & path, const ReadSettings & settings, size_t estimated_size) const
+std::unique_ptr<ReadBufferFromFileBase> DiskLocal::readFile(const String & path, const ReadSettings & settings, std::optional<size_t> size) const
 {
-    return createReadBufferFromFileBase(fs::path(disk_path) / path, settings, estimated_size);
+    return createReadBufferFromFileBase(fs::path(disk_path) / path, settings, size);
 }
 
 std::unique_ptr<WriteBufferFromFileBase>

src/Disks/DiskLocal.h

@@ -74,7 +74,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
 
     std::unique_ptr<WriteBufferFromFileBase> writeFile(
         const String & path,

src/Disks/DiskMemory.cpp

@@ -315,7 +315,7 @@ void DiskMemory::replaceFileImpl(const String & from_path, const String & to_pat
     files.insert(std::move(node));
 }
 
-std::unique_ptr<ReadBufferFromFileBase> DiskMemory::readFile(const String & path, const ReadSettings &, size_t) const
+std::unique_ptr<ReadBufferFromFileBase> DiskMemory::readFile(const String & path, const ReadSettings &, std::optional<size_t>) const
 {
     std::lock_guard lock(mutex);
 

src/Disks/DiskMemory.h

@@ -65,7 +65,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
 
     std::unique_ptr<WriteBufferFromFileBase> writeFile(
         const String & path,

src/Disks/DiskRestartProxy.cpp

@@ -187,10 +187,10 @@ void DiskRestartProxy::listFiles(const String & path, std::vector<String> & file
 }
 
 std::unique_ptr<ReadBufferFromFileBase> DiskRestartProxy::readFile(
-    const String & path, const ReadSettings & settings, size_t estimated_size) const
+    const String & path, const ReadSettings & settings, std::optional<size_t> size) const
 {
     ReadLock lock (mutex);
-    auto impl = DiskDecorator::readFile(path, settings, estimated_size);
+    auto impl = DiskDecorator::readFile(path, settings, size);
     return std::make_unique<RestartAwareReadBuffer>(*this, std::move(impl));
 }
 

src/Disks/DiskRestartProxy.h

@@ -46,7 +46,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
     std::unique_ptr<WriteBufferFromFileBase> writeFile(const String & path, size_t buf_size, WriteMode mode) override;
     void removeFile(const String & path) override;
     void removeFileIfExists(const String & path) override;

src/Disks/DiskWebServer.cpp

@@ -182,7 +182,7 @@ bool DiskWebServer::exists(const String & path) const
 }
 
 
-std::unique_ptr<ReadBufferFromFileBase> DiskWebServer::readFile(const String & path, const ReadSettings & read_settings, size_t) const
+std::unique_ptr<ReadBufferFromFileBase> DiskWebServer::readFile(const String & path, const ReadSettings & read_settings, std::optional<size_t>) const
 {
     LOG_TRACE(log, "Read from path: {}", path);
     auto iter = files.find(path);

src/Disks/DiskWebServer.h

@@ -63,7 +63,7 @@ public:
 
     std::unique_ptr<ReadBufferFromFileBase> readFile(const String & path,
                                                      const ReadSettings & settings,
-                                                     size_t estimated_size) const override;
+                                                     std::optional<size_t> size) const override;
 
     /// Disk info
 

src/Disks/HDFS/DiskHDFS.cpp

@@ -94,7 +94,7 @@ DiskHDFS::DiskHDFS(
 }
 
 
-std::unique_ptr<ReadBufferFromFileBase> DiskHDFS::readFile(const String & path, const ReadSettings & read_settings, size_t) const
+std::unique_ptr<ReadBufferFromFileBase> DiskHDFS::readFile(const String & path, const ReadSettings & read_settings, std::optional<size_t>) const
 {
     auto metadata = readMeta(path);
 

src/Disks/HDFS/DiskHDFS.h

@@ -50,7 +50,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
 
     std::unique_ptr<WriteBufferFromFileBase> writeFile(const String & path, size_t buf_size, WriteMode mode) override;
 

src/Disks/IDisk.h

@@ -166,7 +166,7 @@ public:
     virtual std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings = ReadSettings{},
-        size_t estimated_size = 0) const = 0;
+        std::optional<size_t> size = {}) const = 0;
 
     /// Open the file for write and return WriteBufferFromFileBase object.
     virtual std::unique_ptr<WriteBufferFromFileBase> writeFile(

src/Disks/S3/DiskS3.cpp

@@ -222,7 +222,7 @@ void DiskS3::moveFile(const String & from_path, const String & to_path, bool sen
     fs::rename(fs::path(metadata_path) / from_path, fs::path(metadata_path) / to_path);
 }
 
-std::unique_ptr<ReadBufferFromFileBase> DiskS3::readFile(const String & path, const ReadSettings & read_settings, size_t) const
+std::unique_ptr<ReadBufferFromFileBase> DiskS3::readFile(const String & path, const ReadSettings & read_settings, std::optional<size_t>) const
 {
     auto settings = current_settings.get();
     auto metadata = readMeta(path);

src/Disks/S3/DiskS3.h

@@ -77,7 +77,7 @@ public:
     std::unique_ptr<ReadBufferFromFileBase> readFile(
         const String & path,
         const ReadSettings & settings,
-        size_t estimated_size) const override;
+        std::optional<size_t> size) const override;
 
     std::unique_ptr<WriteBufferFromFileBase> writeFile(
         const String & path,

src/IO/createReadBufferFromFileBase.cpp

@@ -28,11 +28,13 @@ namespace ErrorCodes
 std::unique_ptr<ReadBufferFromFileBase> createReadBufferFromFileBase(
     const std::string & filename,
     const ReadSettings & settings,
-    size_t estimated_size,
+    std::optional<size_t> size,
     int flags,
     char * existing_memory,
     size_t alignment)
 {
+    size_t estimated_size = size.has_value() ? *size : 0;
+
     if (!existing_memory
         && settings.local_fs_method == ReadMethod::mmap
         && settings.mmap_threshold

src/IO/createReadBufferFromFileBase.h

@@ -10,12 +10,13 @@ namespace DB
 {
 
 /** Create an object to read data from a file.
-  * estimated_size - the number of bytes to read
+  *
+  * @param size - the number of bytes to read
   */
 std::unique_ptr<ReadBufferFromFileBase> createReadBufferFromFileBase(
     const std::string & filename,
     const ReadSettings & settings,
-    size_t estimated_size,
+    std::optional<size_t> size,
     int flags_ = -1,
     char * existing_memory = nullptr,
     size_t alignment = 0);