Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixed #5954 Uploading large files with S3 - Multipart Upload #6341

Merged
merged 4 commits into from
Nov 6, 2019
Merged

Fixed #5954 Uploading large files with S3 - Multipart Upload #6341

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8392376
Fixed #5954 Uploading large files with S3
Nov 4, 2019
4291fda
Merge branch 'develop' of https://github.com/IQSS/dataverse into 5954…
Nov 5, 2019
d5ee4fd
add note: S3 multipart upload support for files over 4GB #5954
pdurbin Nov 5, 2019
c3fabf8
Merge pull request #1 from IQSS/5954-docs
mderuijter Nov 6, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 12 additions & 4 deletions src/main/java/edu/harvard/iq/dataverse/dataaccess/S3AccessIO.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@
import com.amazonaws.services.s3.model.ResponseHeaderOverrides;
import com.amazonaws.services.s3.model.S3Object;
import com.amazonaws.services.s3.model.S3ObjectSummary;
import com.amazonaws.services.s3.transfer.TransferManager;
import com.amazonaws.services.s3.transfer.TransferManagerBuilder;
import edu.harvard.iq.dataverse.DataFile;
import edu.harvard.iq.dataverse.Dataset;
import edu.harvard.iq.dataverse.Dataverse;
Expand Down Expand Up @@ -91,6 +93,11 @@ public S3AccessIO(T dvObject, DataAccessRequest req) {

// let's build the client :-)
this.s3 = s3CB.build();

// building a TransferManager instance to support multipart uploading for files over 4gb.
this.tm = TransferManagerBuilder.standard()
.withS3Client(this.s3)
.build();
} catch (Exception e) {
throw new AmazonClientException(
"Cannot instantiate a S3 client; check your AWS credentials and region",
Expand All @@ -115,6 +122,7 @@ public S3AccessIO(T dvObject, DataAccessRequest req, @NotNull AmazonS3 s3client)
public static String S3_IDENTIFIER_PREFIX = "s3";

private AmazonS3 s3 = null;
private TransferManager tm = null;
/**
* Pass in a URL pointing to your S3 compatible storage.
* For possible values see https://docs.aws.amazon.com/AWSJavaSDK/latest/javadoc/com/amazonaws/client/builder/AwsClientBuilder.EndpointConfiguration.html
Expand Down Expand Up @@ -277,14 +285,13 @@ public void savePath(Path fileSystemPath) throws IOException {
try {
File inputFile = fileSystemPath.toFile();
if (dvObject instanceof DataFile) {
s3.putObject(new PutObjectRequest(bucketName, key, inputFile));

tm.upload(new PutObjectRequest(bucketName, key, inputFile)).waitForCompletion();
newFileSize = inputFile.length();
} else {
throw new IOException("DvObject type other than datafile is not yet supported");
}

} catch (SdkClientException ioex) {
} catch (SdkClientException | InterruptedException ioex ) {
String failureMsg = ioex.getMessage();
if (failureMsg == null) {
failureMsg = "S3AccessIO: Unknown exception occured while uploading a local file into S3Object "+key;
Expand All @@ -293,6 +300,7 @@ public void savePath(Path fileSystemPath) throws IOException {
throw new IOException(failureMsg);
}


// if it has uploaded successfully, we can reset the size
// of the object:
setSize(newFileSize);
Expand All @@ -314,7 +322,7 @@ public void savePath(Path fileSystemPath) throws IOException {
* Swift driver.
*
* @param inputStream InputStream we want to save
* @param auxItemTag String representing this Auxiliary type ("extension")
* @param filesize Long representing the filesize
* @throws IOException if anything goes wrong.
*/
@Override
Expand Down