This is an automated email from the ASF dual-hosted git repository.
stevel pushed a commit to branch feature-HADOOP-18073-s3a-sdk-upgrade
in repository https://gitbox.apache.org/repos/asf/hadoop.git
The following commit(s) were added to
refs/heads/feature-HADOOP-18073-s3a-sdk-upgrade by this push:
new 238ba6dc6f6 HADOOP-18853. Upgrade AWS SDK version to 2.20.28 (#5960)
238ba6dc6f6 is described below
commit 238ba6dc6f60033fda4d63273b56f7d0cd597e81
Author: ahmarsuhail <ahmar.suh...@gmail.com>
AuthorDate: Wed Aug 23 12:02:32 2023 +0100
HADOOP-18853. Upgrade AWS SDK version to 2.20.28 (#5960)
Upgrades the AWS sdk v2 version to 2.20.28
This
* adds multipart COPY/rename in the java async client
* removes the aws-crt JAR dependency
Contributed by Ahmar Suhail
---
LICENSE-binary | 3 +--
hadoop-project/pom.xml | 12 +++--------
hadoop-tools/hadoop-aws/pom.xml | 4 ----
.../hadoop/fs/s3a/DefaultS3ClientFactory.java | 11 +++++++++-
.../org/apache/hadoop/fs/s3a/S3AFileSystem.java | 1 +
.../org/apache/hadoop/fs/s3a/S3ClientFactory.java | 24 ++++++++++++++++++++++
6 files changed, 39 insertions(+), 16 deletions(-)
diff --git a/LICENSE-binary b/LICENSE-binary
index 851d839cdbd..0c8199da1be 100644
--- a/LICENSE-binary
+++ b/LICENSE-binary
@@ -363,8 +363,7 @@ org.objenesis:objenesis:2.6
org.xerial.snappy:snappy-java:1.1.10.1
org.yaml:snakeyaml:2.0
org.wildfly.openssl:wildfly-openssl:1.1.3.Final
-software.amazon.awssdk:bundle:jar:2.19.12
-software.amazon.awssdk.crt:aws-crt:0.21.0
+software.amazon.awssdk:bundle:jar:2.20.128
--------------------------------------------------------------------------------
diff --git a/hadoop-project/pom.xml b/hadoop-project/pom.xml
index 809084cb3f7..47fa59cc671 100644
--- a/hadoop-project/pom.xml
+++ b/hadoop-project/pom.xml
@@ -184,9 +184,8 @@
<surefire.fork.timeout>900</surefire.fork.timeout>
<aws-java-sdk.version>1.12.367</aws-java-sdk.version>
<hsqldb.version>2.7.1</hsqldb.version>
- <aws-java-sdk-v2.version>2.19.12</aws-java-sdk-v2.version>
- <aws.evenstream.version>1.0.1</aws.evenstream.version>
- <awscrt.version>0.21.0</awscrt.version>
+ <aws-java-sdk-v2.version>2.20.128</aws-java-sdk-v2.version>
+ <aws.eventstream.version>1.0.1</aws.eventstream.version>
<frontend-maven-plugin.version>1.11.2</frontend-maven-plugin.version>
<jasmine-maven-plugin.version>2.1</jasmine-maven-plugin.version>
<phantomjs-maven-plugin.version>0.7</phantomjs-maven-plugin.version>
@@ -1154,12 +1153,7 @@
<dependency>
<groupId>software.amazon.eventstream</groupId>
<artifactId>eventstream</artifactId>
- <version>${aws.evenstream.version}</version>
- </dependency>
- <dependency>
- <groupId>software.amazon.awssdk.crt</groupId>
- <artifactId>aws-crt</artifactId>
- <version>${awscrt.version}</version>
+ <version>${aws.eventstream.version}</version>
</dependency>
<dependency>
<groupId>org.apache.mina</groupId>
diff --git a/hadoop-tools/hadoop-aws/pom.xml b/hadoop-tools/hadoop-aws/pom.xml
index 3591ab4ea5a..66154e2840e 100644
--- a/hadoop-tools/hadoop-aws/pom.xml
+++ b/hadoop-tools/hadoop-aws/pom.xml
@@ -518,10 +518,6 @@
<artifactId>bundle</artifactId>
<scope>compile</scope>
</dependency>
- <dependency>
- <groupId>software.amazon.awssdk.crt</groupId>
- <artifactId>aws-crt</artifactId>
- </dependency>
<dependency>
<groupId>software.amazon.eventstream</groupId>
<artifactId>eventstream</artifactId>
diff --git
a/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/DefaultS3ClientFactory.java
b/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/DefaultS3ClientFactory.java
index 1b2c129a642..98c72d27662 100644
---
a/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/DefaultS3ClientFactory.java
+++
b/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/DefaultS3ClientFactory.java
@@ -37,6 +37,7 @@ import software.amazon.awssdk.services.s3.S3AsyncClient;
import software.amazon.awssdk.services.s3.S3BaseClientBuilder;
import software.amazon.awssdk.services.s3.S3Client;
import software.amazon.awssdk.services.s3.S3Configuration;
+import software.amazon.awssdk.services.s3.multipart.MultipartConfiguration;
import software.amazon.awssdk.transfer.s3.S3TransferManager;
import org.apache.commons.lang3.StringUtils;
@@ -98,17 +99,25 @@ public class DefaultS3ClientFactory extends Configured
Configuration conf = getConf();
String bucket = uri.getHost();
+
NettyNioAsyncHttpClient.Builder httpClientBuilder = AWSClientConfig
.createAsyncHttpClientBuilder(conf)
.proxyConfiguration(AWSClientConfig.createAsyncProxyConfiguration(conf,
bucket));
+
+ MultipartConfiguration multipartConfiguration =
MultipartConfiguration.builder()
+ .minimumPartSizeInBytes(parameters.getMinimumPartSize())
+ .thresholdInBytes(parameters.getMultiPartThreshold())
+ .build();
+
return configureClientBuilder(S3AsyncClient.builder(), parameters, conf,
bucket)
.httpClientBuilder(httpClientBuilder)
+ .multipartConfiguration(multipartConfiguration)
+ .multipartEnabled(true)
.build();
}
@Override
public S3TransferManager createS3TransferManager(final S3AsyncClient
s3AsyncClient) {
-
return S3TransferManager.builder()
.s3Client(s3AsyncClient)
.build();
diff --git
a/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3AFileSystem.java
b/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3AFileSystem.java
index 305695f2ef5..43f0b9c98cd 100644
---
a/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3AFileSystem.java
+++
b/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3AFileSystem.java
@@ -982,6 +982,7 @@ public class S3AFileSystem extends FileSystem implements
StreamCapabilities,
.withRequesterPays(conf.getBoolean(ALLOW_REQUESTER_PAYS,
DEFAULT_ALLOW_REQUESTER_PAYS))
.withExecutionInterceptors(auditManager.createExecutionInterceptors())
.withMinimumPartSize(partSize)
+ .withMultipartThreshold(multiPartThreshold)
.withTransferManagerExecutor(unboundedThreadPool)
.withRegion(region);
diff --git
a/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3ClientFactory.java
b/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3ClientFactory.java
index fa2c0769d26..d4504cd08d7 100644
---
a/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3ClientFactory.java
+++
b/hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3ClientFactory.java
@@ -151,6 +151,11 @@ public interface S3ClientFactory {
*/
private long minimumPartSize;
+ /**
+ * Threshold for multipart operations.
+ */
+ private long multiPartThreshold;
+
/**
* Executor that the transfer manager will use to execute background tasks.
*/
@@ -337,6 +342,25 @@ public interface S3ClientFactory {
return this;
}
+ /**
+ * Get the threshold for multipart operations.
+ * @return multipart threshold
+ */
+ public long getMultiPartThreshold() {
+ return multiPartThreshold;
+ }
+
+ /**
+ * Set the threshold for multipart operations.
+ * @param value new value
+ * @return the builder
+ */
+ public S3ClientCreationParameters withMultipartThreshold(
+ final long value) {
+ multiPartThreshold = value;
+ return this;
+ }
+
/**
* Get the executor that the transfer manager will use to execute
background tasks.
* @return part size
---------------------------------------------------------------------
To unsubscribe, e-mail: common-commits-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-commits-h...@hadoop.apache.org
