HADOOP-14518. Customize User-Agent header sent in HTTP/HTTPS requests by WASB. Contributed by Georgi Chalakov.

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

@@ -499,7 +499,15 @@
     name to use for the service when the client wishes to make an RPC call.
   </description>
 </property>
-
+  <property>
+    <name>fs.azure.user.agent.prefix</name>
+    <value>unknown</value>
+    <description>
+      WASB passes User-Agent header to the Azure back-end. The default value
+      contains WASB version, Java Runtime version, Azure Client library version,
+      and the value of the configuration option fs.azure.user.agent.prefix.
+    </description>
+  </property>
 
 <property>
     <name>hadoop.security.uid.cache.secs</name>

hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/conf/TestCommonConfigurationFields.java

@@ -116,6 +116,7 @@ public class TestCommonConfigurationFields extends TestConfigurationFieldsBase {
     xmlPropsToSkipCompare.add("fs.azure.secure.mode");
     xmlPropsToSkipCompare.add("fs.azure.authorization");
     xmlPropsToSkipCompare.add("fs.azure.authorization.caching.enable");
+    xmlPropsToSkipCompare.add("fs.azure.user.agent.prefix");
 
     // Deprecated properties.  These should eventually be removed from the
     // class.

hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azure/AzureNativeFileSystemStore.java

@@ -57,6 +57,7 @@ import org.apache.hadoop.fs.azure.metrics.ResponseReceivedMetricUpdater;
 import org.apache.hadoop.fs.permission.FsPermission;
 import org.apache.hadoop.fs.permission.PermissionStatus;
 import org.apache.hadoop.io.IOUtils;
+import org.apache.hadoop.util.VersionInfo;
 import org.eclipse.jetty.util.ajax.JSON;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
@@ -71,6 +72,10 @@ import com.microsoft.azure.storage.StorageCredentialsAccountAndKey;
 import com.microsoft.azure.storage.StorageCredentialsSharedAccessSignature;
 import com.microsoft.azure.storage.StorageErrorCode;
 import com.microsoft.azure.storage.StorageException;
+import com.microsoft.azure.storage.Constants;
+import com.microsoft.azure.storage.StorageEvent;
+import com.microsoft.azure.storage.core.BaseRequest;
+import com.microsoft.azure.storage.SendingRequestEvent;
 import com.microsoft.azure.storage.blob.BlobListingDetails;
 import com.microsoft.azure.storage.blob.BlobProperties;
 import com.microsoft.azure.storage.blob.BlobRequestOptions;
@@ -102,6 +107,12 @@ public class AzureNativeFileSystemStore implements NativeFileSystemStore {
   static final String DEFAULT_STORAGE_EMULATOR_ACCOUNT_NAME = "storageemulator";
   static final String STORAGE_EMULATOR_ACCOUNT_NAME_PROPERTY_NAME = "fs.azure.storage.emulator.account.name";
 
+  /**
+   * Configuration for User-Agent field.
+   */
+  static final String USER_AGENT_ID_KEY = "fs.azure.user.agent.prefix";
+  static final String USER_AGENT_ID_DEFAULT = "unknown";
+
   public static final Logger LOG = LoggerFactory.getLogger(AzureNativeFileSystemStore.class);
 
   private StorageInterface storageInteractionLayer;
@@ -306,6 +317,9 @@ public class AzureNativeFileSystemStore implements NativeFileSystemStore {
   private boolean useSecureMode = false;
   private boolean useLocalSasKeyMode = false;
 
+  // User-Agent
+  private String userAgentId;
+
   private String delegationToken;
 
   /** The error message template when container is not accessible. */
@@ -504,6 +518,9 @@ public class AzureNativeFileSystemStore implements NativeFileSystemStore {
     pageBlobDirs = getDirectorySet(KEY_PAGE_BLOB_DIRECTORIES);
     LOG.debug("Page blob directories:  {}", setToString(pageBlobDirs));
 
+    // User-agent
+    userAgentId = conf.get(USER_AGENT_ID_KEY, USER_AGENT_ID_DEFAULT);
+
     // Extract directories that should have atomic rename applied.
     atomicRenameDirs = getDirectorySet(KEY_ATOMIC_RENAME_DIRECTORIES);
     String hbaseRoot;
@@ -1910,6 +1927,17 @@ public class AzureNativeFileSystemStore implements NativeFileSystemStore {
 
     OperationContext operationContext = new OperationContext();
 
+    // Set User-Agent
+    operationContext.getSendingRequestEventHandler().addListener(new StorageEvent<SendingRequestEvent>() {
+      @Override
+      public void eventOccurred(SendingRequestEvent eventArg) {
+        HttpURLConnection connection = (HttpURLConnection) eventArg.getConnectionObject();
+        String userAgentInfo = String.format(Utility.LOCALE_US, "WASB/%s (%s) %s",
+                VersionInfo.getVersion(), userAgentId, BaseRequest.getUserAgent());
+        connection.setRequestProperty(Constants.HeaderConstants.USER_AGENT, userAgentInfo);
+      }
+    });
+
     if (selfThrottlingEnabled) {
       SelfThrottlingIntercept.hook(operationContext, selfThrottlingReadFactor,
           selfThrottlingWriteFactor);

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

@@ -192,6 +192,19 @@ The configuration option `fs.azure.page.blob.extension.size` is the page blob
 extension size.  This defines the amount to extend a page blob if it starts to
 get full.  It must be 128MB or greater, specified as an integer number of bytes.
 
+### Custom User-Agent
+WASB passes User-Agent header to the Azure back-end. The default value
+contains WASB version, Java Runtime version, Azure Client library version, and the
+value of the configuration option `fs.azure.user.agent.prefix`. Customized User-Agent
+header enables better troubleshooting and analysis by Azure service.
+
+```xml
+<property>
+    <name>fs.azure.user.agent.prefix</name>
+    <value>Identifier</value>
+</property>
+```
+
 ### Atomic Folder Rename
 
 Azure storage stores files as a flat key/value store without formal support

hadoop-tools/hadoop-azure/src/test/java/org/apache/hadoop/fs/azure/TestWasbUriAndConfiguration.java

@@ -566,4 +566,52 @@ public class TestWasbUriAndConfiguration {
         CredentialProviderFactory.CREDENTIAL_PROVIDER_PATH, null);
     assertEquals(newPath, effectivePath);
   }
+
+  @Test
+  public void testUserAgentConfig() throws Exception {
+    // Set the user agent
+    try {
+      testAccount = AzureBlobStorageTestAccount.createMock();
+      Configuration conf = testAccount.getFileSystem().getConf();
+      String authority = testAccount.getFileSystem().getUri().getAuthority();
+      URI defaultUri = new URI("wasbs", authority, null, null, null);
+      conf.set(FS_DEFAULT_NAME_KEY, defaultUri.toString());
+      conf.set("fs.AbstractFileSystem.wasbs.impl", "org.apache.hadoop.fs.azure.Wasbs");
+
+      conf.set(AzureNativeFileSystemStore.USER_AGENT_ID_KEY, "TestClient");
+
+      FileSystem fs = FileSystem.get(conf);
+      AbstractFileSystem afs = FileContext.getFileContext(conf).getDefaultFileSystem();
+
+      assertTrue(afs instanceof Wasbs);
+      assertEquals(-1, afs.getUri().getPort());
+      assertEquals("wasbs", afs.getUri().getScheme());
+
+    } finally {
+      testAccount.cleanup();
+      FileSystem.closeAll();
+    }
+
+    // Unset the user agent
+    try {
+      testAccount = AzureBlobStorageTestAccount.createMock();
+      Configuration conf = testAccount.getFileSystem().getConf();
+      String authority = testAccount.getFileSystem().getUri().getAuthority();
+      URI defaultUri = new URI("wasbs", authority, null, null, null);
+      conf.set(FS_DEFAULT_NAME_KEY, defaultUri.toString());
+      conf.set("fs.AbstractFileSystem.wasbs.impl", "org.apache.hadoop.fs.azure.Wasbs");
+
+      conf.unset(AzureNativeFileSystemStore.USER_AGENT_ID_KEY);
+
+      FileSystem fs = FileSystem.get(conf);
+      AbstractFileSystem afs = FileContext.getFileContext(conf).getDefaultFileSystem();
+      assertTrue(afs instanceof Wasbs);
+      assertEquals(-1, afs.getUri().getPort());
+      assertEquals("wasbs", afs.getUri().getScheme());
+
+    } finally {
+      testAccount.cleanup();
+      FileSystem.closeAll();
+    }
+  }
 }

hadoop-tools/hadoop-azure/src/test/resources/azure-test.xml

@@ -34,6 +34,11 @@
     <value>true</value>
   </property>
 
+  <property>
+    <name>fs.azure.user.agent.prefix</name>
+    <value>MSFT</value>
+  </property>
+
   <!-- Save the above configuration properties in a separate file named -->
   <!-- azure-auth-keys.xml in the same directory as this file. -->
   <!-- DO NOT ADD azure-auth-keys.xml TO REVISION CONTROL.  The keys to your -->