ctrlaltdilj commented on code in PR #27026:
URL: https://github.com/apache/flink/pull/27026#discussion_r2415270441
##########
flink-filesystems/flink-s3-fs-hadoop/src/main/java/org/apache/flink/fs/s3hadoop/HadoopS3AccessHelper.java:
##########
@@ -18,111 +18,181 @@
package org.apache.flink.fs.s3hadoop;
+import org.apache.flink.fs.s3.common.adapter.v2.AwsSdkV2Adapters;
+import org.apache.flink.fs.s3.common.model.FlinkCompleteMultipartUploadResult;
+import org.apache.flink.fs.s3.common.model.FlinkObjectMetadata;
+import org.apache.flink.fs.s3.common.model.FlinkPartETag;
+import org.apache.flink.fs.s3.common.model.FlinkPutObjectResult;
+import org.apache.flink.fs.s3.common.model.FlinkUploadPartResult;
import org.apache.flink.fs.s3.common.writer.S3AccessHelper;
-import org.apache.flink.util.MathUtils;
-
-import com.amazonaws.SdkBaseException;
-import com.amazonaws.services.s3.model.CompleteMultipartUploadResult;
-import com.amazonaws.services.s3.model.ObjectMetadata;
-import com.amazonaws.services.s3.model.PartETag;
-import com.amazonaws.services.s3.model.PutObjectRequest;
-import com.amazonaws.services.s3.model.PutObjectResult;
-import com.amazonaws.services.s3.model.UploadPartRequest;
-import com.amazonaws.services.s3.model.UploadPartResult;
+
import org.apache.hadoop.conf.Configuration;
-import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.s3a.S3AFileSystem;
import org.apache.hadoop.fs.s3a.S3AUtils;
import org.apache.hadoop.fs.s3a.WriteOperationHelper;
-import org.apache.hadoop.fs.s3a.statistics.S3AStatisticsContext;
-import org.apache.hadoop.fs.store.audit.AuditSpan;
-import org.apache.hadoop.fs.store.audit.AuditSpanSource;
+import org.apache.hadoop.fs.s3a.impl.PutObjectOptions;
+import software.amazon.awssdk.core.exception.SdkException;
+import software.amazon.awssdk.core.sync.RequestBody;
+import software.amazon.awssdk.services.s3.S3Client;
+import
software.amazon.awssdk.services.s3.model.CompleteMultipartUploadResponse;
+import software.amazon.awssdk.services.s3.model.CompletedPart;
+import software.amazon.awssdk.services.s3.model.CreateMultipartUploadRequest;
+import software.amazon.awssdk.services.s3.model.CreateMultipartUploadResponse;
+import software.amazon.awssdk.services.s3.model.DeleteObjectRequest;
+import software.amazon.awssdk.services.s3.model.GetObjectRequest;
+import software.amazon.awssdk.services.s3.model.HeadObjectRequest;
+import software.amazon.awssdk.services.s3.model.HeadObjectResponse;
+import software.amazon.awssdk.services.s3.model.PutObjectRequest;
+import software.amazon.awssdk.services.s3.model.PutObjectResponse;
+import software.amazon.awssdk.services.s3.model.UploadPartRequest;
+import software.amazon.awssdk.services.s3.model.UploadPartResponse;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
+import java.io.InputStream;
import java.io.OutputStream;
+import java.nio.file.Paths;
import java.util.List;
import java.util.concurrent.atomic.AtomicInteger;
+import java.util.stream.Collectors;
import static org.apache.flink.util.Preconditions.checkNotNull;
-/** An implementation of the {@link S3AccessHelper} for the Hadoop S3A
filesystem. */
+/**
+ * An implementation of the {@link S3AccessHelper} for the Hadoop S3A
filesystem.
+ *
+ * <p>This implementation uses the AWS SDK v2 S3Client from Hadoop's
S3AFileSystem to perform
+ * low-level S3 operations required for Flink's recoverable writers. The
S3Client is accessed via
+ * {@link org.apache.hadoop.fs.s3a.S3AInternals#getAmazonS3Client(String)},
which is the recommended
+ * approach for operations not available through the standard FileSystem API.
+ */
public class HadoopS3AccessHelper implements S3AccessHelper {
private final S3AFileSystem s3a;
- private final InternalWriteOperationHelper s3accessHelper;
+ private final S3Client s3Client;
+
+ private final String bucket;
+
+ private final WriteOperationHelper writeHelper;
+
+ private final PutObjectOptions putOptions;
public HadoopS3AccessHelper(S3AFileSystem s3a, Configuration conf) {
- checkNotNull(s3a);
- this.s3accessHelper =
- new InternalWriteOperationHelper(
- s3a,
- checkNotNull(conf),
- s3a.createStoreContext().getInstrumentation(),
- s3a.getAuditSpanSource(),
- s3a.getActiveAuditSpan());
- this.s3a = s3a;
+ this.s3a = checkNotNull(s3a);
+ // Use the S3AInternals API to get the S3Client for low-level
operations
+ // This bypasses some S3A operations (like auditing) but is necessary
for
+ // multipart upload operations that aren't exposed through the
FileSystem API
+ this.s3Client =
Review Comment:
let me look into this
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
