HADOOP-13122 Customize User-Agent header sent in HTTP requests by S3A. Chris Nauroth via stevel.

hadoop-common-project/hadoop-common/src/main/resources/core-default.xml

@@ -945,6 +945,21 @@
     upload. No effect if fs.s3a.fast.upload is false.</description>
 </property>
 
+<property>
+  <name>fs.s3a.user.agent.prefix</name>
+  <value></value>
+  <description>
+    Sets a custom value that will be prepended to the User-Agent header sent in
+    HTTP requests to the S3 back-end by S3AFileSystem.  The User-Agent header
+    always includes the Hadoop version number followed by a string generated by
+    the AWS SDK.  An example is "User-Agent: Hadoop 2.8.0, aws-sdk-java/1.10.6".
+    If this optional property is set, then its value is prepended to create a
+    customized User-Agent.  For example, if this configuration property was set
+    to "MyApp", then an example of the resulting User-Agent would be
+    "User-Agent: MyApp, Hadoop 2.8.0, aws-sdk-java/1.10.6".
+  </description>
+</property>
+
 <property>
   <name>fs.s3a.impl</name>
   <value>org.apache.hadoop.fs.s3a.S3AFileSystem</value>

hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/Constants.java

@@ -122,4 +122,6 @@ public class Constants {
   public static final String FS_S3A = "s3a";
 
   public static final int S3A_DEFAULT_PORT = -1;
+
+  public static final String USER_AGENT_PREFIX = "fs.s3a.user.agent.prefix";
 }

hadoop-tools/hadoop-aws/src/main/java/org/apache/hadoop/fs/s3a/S3AFileSystem.java

@@ -69,6 +69,7 @@
 import org.apache.hadoop.fs.permission.FsPermission;
 import org.apache.hadoop.security.ProviderUtils;
 import org.apache.hadoop.util.Progressable;
+import org.apache.hadoop.util.VersionInfo;
 
 import static org.apache.hadoop.fs.s3a.Constants.*;
 
@@ -139,6 +140,8 @@ public void initialize(URI name, Configuration conf) throws IOException {
 
     initProxySupport(conf, awsConf, secureConnections);
 
+    initUserAgent(conf, awsConf);
+
     initAmazonS3Client(conf, credentials, awsConf);
 
     maxKeys = conf.getInt(MAX_PAGING_KEYS, DEFAULT_MAX_PAGING_KEYS);
@@ -231,6 +234,26 @@ void initProxySupport(Configuration conf, ClientConfiguration awsConf,
     }
   }
 
+  /**
+   * Initializes the User-Agent header to send in HTTP requests to the S3
+   * back-end.  We always include the Hadoop version number.  The user also may
+   * set an optional custom prefix to put in front of the Hadoop version number.
+   * The AWS SDK interally appends its own information, which seems to include
+   * the AWS SDK version, OS and JVM version.
+   *
+   * @param conf Hadoop configuration
+   * @param awsConf AWS SDK configuration
+   */
+  private void initUserAgent(Configuration conf, ClientConfiguration awsConf) {
+    String userAgent = "Hadoop " + VersionInfo.getVersion();
+    String userAgentPrefix = conf.getTrimmed(USER_AGENT_PREFIX, "");
+    if (!userAgentPrefix.isEmpty()) {
+      userAgent = userAgentPrefix + ", " + userAgent;
+    }
+    LOG.debug("Using User-Agent: {}", userAgent);
+    awsConf.setUserAgent(userAgent);
+  }
+
   private void initAmazonS3Client(Configuration conf,
       AWSCredentialsProviderChain credentials, ClientConfiguration awsConf)
       throws IllegalArgumentException {

hadoop-tools/hadoop-aws/src/site/markdown/tools/hadoop-aws/index.md

@@ -407,6 +407,21 @@ this capability.
       </description>
     </property>
 
+    <property>
+      <name>fs.s3a.user.agent.prefix</name>
+      <value></value>
+      <description>
+        Sets a custom value that will be prepended to the User-Agent header sent in
+        HTTP requests to the S3 back-end by S3AFileSystem.  The User-Agent header
+        always includes the Hadoop version number followed by a string generated by
+        the AWS SDK.  An example is "User-Agent: Hadoop 2.8.0, aws-sdk-java/1.10.6".
+        If this optional property is set, then its value is prepended to create a
+        customized User-Agent.  For example, if this configuration property was set
+        to "MyApp", then an example of the resulting User-Agent would be
+        "User-Agent: MyApp, Hadoop 2.8.0, aws-sdk-java/1.10.6".
+      </description>
+    </property>
+
     <property>
       <name>fs.s3a.impl</name>
       <value>org.apache.hadoop.fs.s3a.S3AFileSystem</value>

hadoop-tools/hadoop-aws/src/test/java/org/apache/hadoop/fs/s3a/TestS3AConfiguration.java

@@ -18,11 +18,13 @@
 
 package org.apache.hadoop.fs.s3a;
 
+import com.amazonaws.ClientConfiguration;
 import com.amazonaws.services.s3.AmazonS3Client;
 import com.amazonaws.services.s3.S3ClientOptions;
 import com.amazonaws.services.s3.model.AmazonS3Exception;
 
 import org.apache.commons.lang.StringUtils;
+import org.apache.commons.lang.reflect.FieldUtils;
 import com.amazonaws.AmazonClientException;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
@@ -46,6 +48,7 @@
 import org.apache.hadoop.security.ProviderUtils;
 import org.apache.hadoop.security.alias.CredentialProvider;
 import org.apache.hadoop.security.alias.CredentialProviderFactory;
+import org.apache.hadoop.util.VersionInfo;
 import org.apache.http.HttpStatus;
 import org.junit.rules.TemporaryFolder;
 
@@ -370,10 +373,13 @@ public void shouldBeAbleToSwitchOnS3PathStyleAccessViaConfigProperty() throws Ex
 
     try {
       fs = S3ATestUtils.createTestFileSystem(conf);
-      final Object object = getClientOptionsField(fs.getAmazonS3Client(), "clientOptions");
-      assertNotNull(object);
-      assertTrue("Unexpected type found for clientOptions!", object instanceof S3ClientOptions);
-      assertTrue("Expected to find path style access to be switched on!", ((S3ClientOptions) object).isPathStyleAccess());
+      assertNotNull(fs);
+      AmazonS3Client s3 = fs.getAmazonS3Client();
+      assertNotNull(s3);
+      S3ClientOptions clientOptions = getField(s3, S3ClientOptions.class,
+          "clientOptions");
+      assertTrue("Expected to find path style access to be switched on!",
+          clientOptions.isPathStyleAccess());
       byte[] file = ContractTestUtils.toAsciiByteArray("test file");
       ContractTestUtils.writeAndRead(fs, new Path("/path/style/access/testFile"), file, file.length, conf.getInt(Constants.FS_S3A_BLOCK_SIZE, file.length), false, true);
     } catch (final AmazonS3Exception e) {
@@ -385,14 +391,53 @@ public void shouldBeAbleToSwitchOnS3PathStyleAccessViaConfigProperty() throws Ex
     }
   }
 
-  private Object getClientOptionsField(AmazonS3Client s3client, String field)
-      throws NoSuchFieldException, IllegalAccessException {
-    final Field clientOptionsProps = s3client.getClass().getDeclaredField(field);
-    assertNotNull(clientOptionsProps);
-    if (!clientOptionsProps.isAccessible()) {
-      clientOptionsProps.setAccessible(true);
+  @Test
+  public void testDefaultUserAgent() throws Exception {
+    conf = new Configuration();
+    fs = S3ATestUtils.createTestFileSystem(conf);
+    assertNotNull(fs);
+    AmazonS3Client s3 = fs.getAmazonS3Client();
+    assertNotNull(s3);
+    ClientConfiguration awsConf = getField(s3, ClientConfiguration.class,
+        "clientConfiguration");
+    assertEquals("Hadoop " + VersionInfo.getVersion(), awsConf.getUserAgent());
   }
-    final Object object = clientOptionsProps.get(s3client);
-    return object;
+
+  @Test
+  public void testCustomUserAgent() throws Exception {
+    conf = new Configuration();
+    conf.set(Constants.USER_AGENT_PREFIX, "MyApp");
+    fs = S3ATestUtils.createTestFileSystem(conf);
+    assertNotNull(fs);
+    AmazonS3Client s3 = fs.getAmazonS3Client();
+    assertNotNull(s3);
+    ClientConfiguration awsConf = getField(s3, ClientConfiguration.class,
+        "clientConfiguration");
+    assertEquals("MyApp, Hadoop " + VersionInfo.getVersion(),
+        awsConf.getUserAgent());
+  }
+
+  /**
+   * Reads and returns a field from an object using reflection.  If the field
+   * cannot be found, is null, or is not the expected type, then this method
+   * fails the test.
+   *
+   * @param target object to read
+   * @param fieldType type of field to read, which will also be the return type
+   * @param fieldName name of field to read
+   * @return field that was read
+   * @throws IllegalAccessException if access not allowed
+   */
+  private static <T> T getField(Object target, Class<T> fieldType,
+      String fieldName) throws IllegalAccessException {
+    Object obj = FieldUtils.readField(target, fieldName, true);
+    assertNotNull(String.format(
+        "Could not read field named %s in object with class %s.", fieldName,
+        target.getClass().getName()), obj);
+    assertTrue(String.format(
+        "Unexpected type found for field named %s, expected %s, actual %s.",
+        fieldName, fieldType.getName(), obj.getClass().getName()),
+        fieldType.isAssignableFrom(obj.getClass()));
+    return fieldType.cast(obj);
   }
 }