Download a file in chunks concurrently

Use Transfer Manager to download a single large file in chunks, with concurrency.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Go

For more information, see the Cloud Storage Go API reference documentation.

To authenticate to Cloud Storage, set up Application Default Credentials. For more information, see Set up authentication for client libraries. 

package transfermanager

import (
	"context"
	"fmt"
	"io"
	"os"

	"cloud.google.com/go/storage"
	"cloud.google.com/go/storage/transfermanager"
)

// downloadChunksConcurrently downloads a single file in chunks, concurrently in a process pool.
func downloadChunksConcurrently(w io.Writer, bucketName, blobName, filename string) error {
	// bucketName := "your-bucket-name"
	// blobName := "target-file"
	// filename := "path/to/your/local/file.txt"

	// The chunkSize is the size of each chunk to be downloaded.
	// The performance impact of this value depends on the use case.
	// For example, for a slow network, using a smaller chunkSize may be better.
	// Providing this parameter is optional and the default value is 32 MiB.
	chunkSize := 16 * 1024 * 1024 // 16 MiB

	// The maximum number of workers to use for the operation.
	// Please note, providing this parameter is optional.
	// The performance impact of this value depends on the use case.
	// To download one large file, the default value: NumCPU / 2 is usually fine.
	workers := 8

	ctx := context.Background()
	client, err := storage.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("storage.NewClient: %w", err)
	}
	defer client.Close()

	d, err := transfermanager.NewDownloader(client, transfermanager.WithPartSize(int64(chunkSize)), transfermanager.WithWorkers(workers))
	if err != nil {
		return fmt.Errorf("transfermanager.NewDownloader: %w", err)
	}

	f, err := os.Create(filename)
	if err != nil {
		return fmt.Errorf("os.Create: %w", err)
	}
	defer f.Close()

	in := &transfermanager.DownloadObjectInput{
		Bucket:      bucketName,
		Object:      blobName,
		Destination: f,
	}

	if err := d.DownloadObject(ctx, in); err != nil {
		return fmt.Errorf("d.DownloadObject: %w", err)
	}

	// Wait for all downloads to complete and close the downloader.
	// This allows to synchronize the download processes.
	results, err := d.WaitAndClose()
	if err != nil {
		return fmt.Errorf("d.WaitAndClose: %w", err)
	}

	// Process the downloader result.
	if len(results) != 1 {
		return fmt.Errorf("expected 1 result, got %d", len(results))
	}
	result := results[0]
	if result.Err != nil {
		fmt.Fprintf(w, "download of %v failed with error %v\n", result.Object, result.Err)
		return result.Err
	}
	fmt.Fprintf(w, "Downloaded %v to %v.\n", blobName, filename)

	return nil
}

Java

For more information, see the Cloud Storage Java API reference documentation.

To authenticate to Cloud Storage, set up Application Default Credentials. For more information, see Set up authentication for client libraries. 

import com.google.cloud.storage.BlobInfo;
import com.google.cloud.storage.transfermanager.DownloadResult;
import com.google.cloud.storage.transfermanager.ParallelDownloadConfig;
import com.google.cloud.storage.transfermanager.TransferManager;
import com.google.cloud.storage.transfermanager.TransferManagerConfig;
import java.nio.file.Path;
import java.util.List;

class AllowDivideAndConquerDownload {

  public static void divideAndConquerDownloadAllowed(
      List<BlobInfo> blobs, String bucketName, Path destinationDirectory) {
    TransferManager transferManager =
        TransferManagerConfig.newBuilder()
            .setAllowDivideAndConquerDownload(true)
            .build()
            .getService();
    ParallelDownloadConfig parallelDownloadConfig =
        ParallelDownloadConfig.newBuilder()
            .setBucketName(bucketName)
            .setDownloadDirectory(destinationDirectory)
            .build();
    List<DownloadResult> results =
        transferManager.downloadBlobs(blobs, parallelDownloadConfig).getDownloadResults();

    for (DownloadResult result : results) {
      System.out.println(
          "Download of "
              + result.getInput().getName()
              + " completed with status "
              + result.getStatus());
    }
  }
}

Node.js

For more information, see the Cloud Storage Node.js API reference documentation.

To authenticate to Cloud Storage, set up Application Default Credentials. For more information, see Set up authentication for client libraries. 

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// The ID of your GCS bucket
// const bucketName = 'your-unique-bucket-name';

// The ID of the GCS file to download
// const fileName = 'your-file-name';

// The path to which the file should be downloaded
// const destFileName = '/local/path/to/file.txt';

// The size of each chunk to be downloaded
// const chunkSize = 1024;

// Imports the Google Cloud client library
const {Storage, TransferManager} = require('@google-cloud/storage');

// Creates a client
const storage = new Storage();

// Creates a transfer manager client
const transferManager = new TransferManager(storage.bucket(bucketName));

async function downloadFileInChunksWithTransferManager() {
  // Downloads the files
  await transferManager.downloadFileInChunks(fileName, {
    destination: destFileName,
    chunkSizeBytes: chunkSize,
  });

  console.log(
    `gs://${bucketName}/${fileName} downloaded to ${destFileName}.`
  );
}

downloadFileInChunksWithTransferManager().catch(console.error);

Python

For more information, see the Cloud Storage Python API reference documentation.

To authenticate to Cloud Storage, set up Application Default Credentials. For more information, see Set up authentication for client libraries. 

def download_chunks_concurrently(
    bucket_name, blob_name, filename, chunk_size=32 * 1024 * 1024, workers=8
):
    """Download a single file in chunks, concurrently in a process pool."""

    # The ID of your GCS bucket
    # bucket_name = "your-bucket-name"

    # The file to be downloaded
    # blob_name = "target-file"

    # The destination filename or path
    # filename = ""

    # The size of each chunk. The performance impact of this value depends on
    # the use case. The remote service has a minimum of 5 MiB and a maximum of
    # 5 GiB.
    # chunk_size = 32 * 1024 * 1024 (32 MiB)

    # The maximum number of processes to use for the operation. The performance
    # impact of this value depends on the use case, but smaller files usually
    # benefit from a higher number of processes. Each additional process occupies
    # some CPU and memory resources until finished. Threads can be used instead
    # of processes by passing `worker_type=transfer_manager.THREAD`.
    # workers=8

    from google.cloud.storage import Client, transfer_manager

    storage_client = Client()
    bucket = storage_client.bucket(bucket_name)
    blob = bucket.blob(blob_name)

    transfer_manager.download_chunks_concurrently(
        blob, filename, chunk_size=chunk_size, max_workers=workers
    )

    print("Downloaded {} to {}.".format(blob_name, filename))

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.