[
https://issues.apache.org/jira/browse/HADOOP-19450?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17927737#comment-17927737
]
ASF GitHub Bot commented on HADOOP-19450:
-----------------------------------------
anmolanmol1234 commented on code in PR #7364:
URL: https://github.com/apache/hadoop/pull/7364#discussion_r1958112915
##########
hadoop-tools/hadoop-azure/src/test/java/org/apache/hadoop/fs/azurebfs/ITestAzureBlobFileSystemMkDir.java:
##########
@@ -167,4 +185,139 @@ public void testMkdirWithExistingFilename() throws
Exception {
intercept(FileAlreadyExistsException.class, () -> fs.mkdirs(new
Path("/testFilePath")));
intercept(FileAlreadyExistsException.class, () -> fs.mkdirs(new
Path("/testFilePath/newDir")));
}
+
+ /**
+ * Tests the idempotency of creating a path with retries by simulating
+ * a conflict response (HTTP 409) from the Azure Blob File System client.
+ * The method ensures that the path creation operation retries correctly
+ * with the proper transaction ID headers, verifying idempotency during
+ * failure recovery.
+ *
+ * @throws Exception if any error occurs during the operation.
+ */
+ @Test
+ public void createPathRetryIdempotency() throws Exception {
+ Configuration configuration = new Configuration(getRawConfiguration());
+ configuration.set(FS_AZURE_ENABLE_CLIENT_TRANSACTION_ID, "true");
+ try (AzureBlobFileSystem fs = getFileSystem(configuration)) {
+ assumeRecoveryThroughClientTransactionID(fs, true);
+ AzureBlobFileSystemStore store = Mockito.spy(fs.getAbfsStore());
+ AbfsClientHandler clientHandler = Mockito.spy(store.getClientHandler());
+ AbfsDfsClient abfsClient = (AbfsDfsClient) Mockito.spy(
+ clientHandler.getClient());
+ fs.getAbfsStore().setClient(abfsClient);
+ fs.getAbfsStore().setClientHandler(clientHandler);
+ Mockito.doReturn(abfsClient).when(clientHandler).getIngressClient();
+ final Path nonOverwriteFile = new Path(
+ "/NonOverwriteTest_FileName_" + UUID.randomUUID());
+ final List<AbfsHttpHeader> headers = new ArrayList<>();
+ TestAbfsClient.mockAbfsOperationCreation(abfsClient,
+ new MockIntercept<AbfsRestOperation>() {
+ private int count = 0;
+
+ @Override
+ public void answer(final AbfsRestOperation mockedObj,
+ final InvocationOnMock answer)
+ throws AbfsRestOperationException {
+ if (count == 0) {
+ count = 1;
+ AbfsHttpOperation op = Mockito.mock(AbfsHttpOperation.class);
+ Mockito.doReturn("PUT").when(op).getMethod();
+ Mockito.doReturn("").when(op).getStorageErrorMessage();
+ Mockito.doReturn(true).when(mockedObj).hasResult();
+ Mockito.doReturn(op).when(mockedObj).getResult();
+ Mockito.doReturn(HTTP_CONFLICT).when(op).getStatusCode();
+ headers.addAll(mockedObj.getRequestHeaders());
+ throw new AbfsRestOperationException(HTTP_CONFLICT,
+ AzureServiceErrorCode.PATH_CONFLICT.getErrorCode(), "",
+ null, op);
+ }
+ }
+ });
+ AbfsRestOperation getPathRestOp = Mockito.mock(AbfsRestOperation.class);
+ AbfsHttpOperation op = Mockito.mock(AbfsHttpOperation.class);
+ Mockito.doAnswer(answer -> {
+ String requiredHeader = null;
+ for (AbfsHttpHeader httpHeader : headers) {
+ if (X_MS_CLIENT_TRANSACTION_ID.equalsIgnoreCase(
+ httpHeader.getName())) {
+ requiredHeader = httpHeader.getValue();
+ break;
+ }
+ }
+ return requiredHeader;
+ }).when(op).getResponseHeader(X_MS_CLIENT_TRANSACTION_ID);
+ Mockito.doReturn(true).when(getPathRestOp).hasResult();
+ Mockito.doReturn(op).when(getPathRestOp).getResult();
+ Mockito.doReturn(getPathRestOp).when(abfsClient).getPathStatus(
+ Mockito.nullable(String.class), Mockito.nullable(Boolean.class),
+ Mockito.nullable(TracingContext.class),
+ Mockito.nullable(ContextEncryptionAdapter.class));
+ fs.create(nonOverwriteFile, false);
+ }
+ }
+
+ /**
+ * Test to verify that the client transaction ID is included in the response
header
+ * during the creation of a new file in Azure Blob Storage.
+ * <p>
+ * This test ensures that when a new file is created, the Azure Blob
FileSystem client
+ * correctly includes the client transaction ID in the response header for
the created file.
+ * The test uses a configuration where client transaction ID is enabled and
verifies
+ * its presence after the file creation operation.
+ * </p>
+ *
+ * @throws Exception if any error occurs during test execution
+ */
+ @Test
+ public void getClientTransactionIdAfterCreate() throws Exception {
+ try (AzureBlobFileSystem fs = getFileSystem()) {
+ assumeRecoveryThroughClientTransactionID(fs, true);
+ AbfsDfsClient abfsDfsClient = (AbfsDfsClient) fs.getAbfsClient();
+ final Path nonOverwriteFile = new Path(
+ "/NonOverwriteTest_FileName_" + UUID.randomUUID());
+ fs.create(nonOverwriteFile, false);
+
+ final AbfsHttpOperation getPathStatusOp =
+ abfsDfsClient.getPathStatus(nonOverwriteFile.toUri().getPath(),
false,
+ getTestTracingContext(fs, true), null).getResult();
+ Assertions.assertThat(
+ getPathStatusOp.getResponseHeader(X_MS_CLIENT_TRANSACTION_ID))
+ .describedAs("Client transaction ID should be set during create")
+ .isNotNull();
+ }
+ }
+
+ /**
+ * Test to verify that the client transaction ID is included in the response
header
+ * after two consecutive create operations on the same file in Azure Blob
Storage.
+ * <p>
+ * This test ensures that even after performing two create operations (with
overwrite)
+ * on the same file, the Azure Blob FileSystem client includes the client
transaction ID
+ * in the response header for the created file. The test checks for the
presence of
+ * the client transaction ID in the response after the second create call.
+ * </p>
+ *
+ * @throws Exception if any error occurs during test execution
+ */
+ @Test
+ public void testClientTransactionIdAfterTwoCreateCalls() throws Exception {
+ try (AzureBlobFileSystem fs = getFileSystem()) {
+ assumeRecoveryThroughClientTransactionID(fs, true);
+ AbfsDfsClient abfsDfsClient = (AbfsDfsClient) fs.getAbfsClient();
+ Path testPath = path("testfile");
+ AzureBlobFileSystemStore.Permissions permissions
+ = new AzureBlobFileSystemStore.Permissions(false,
+ FsPermission.getDefault(), FsPermission.getUMask(fs.getConf()));
+ fs.create(testPath, false);
+ fs.create(testPath, true);
+ final AbfsHttpOperation getPathStatusOp =
+ abfsDfsClient.getPathStatus(testPath.toUri().getPath(), false,
+ getTestTracingContext(fs, true), null).getResult();
+ Assertions.assertThat(
+ getPathStatusOp.getResponseHeader(X_MS_CLIENT_TRANSACTION_ID))
+ .describedAs("Client transaction ID should be set during create")
+ .isNotNull();
+ }
Review Comment:
We should add a test to assert the set transaction id and the received one
is same
> [ABFS] Rename/Create path idempotency client-level resolution
> -------------------------------------------------------------
>
> Key: HADOOP-19450
> URL: https://issues.apache.org/jira/browse/HADOOP-19450
> Project: Hadoop Common
> Issue Type: Task
> Components: fs/azure
> Affects Versions: 3.5.0
> Reporter: Manish Bhatt
> Assignee: Manish Bhatt
> Priority: Major
> Labels: pull-request-available
>
> CreatePath and RenamePath APIs are idempotent as subsequent retries on same
> resource don’t change the server state. However, when client experiences
> connection break on the CreatePath and the RenamePath APIs, client cannot
> make sense if the request is accepted by the server or not.
> On connection failure, the client retries the request. The server might
> return 404 (sourceNotFound) in case of RenamePath API and 409
> (pathAlreadyExists) in case of CreatePath (overwrite=false) API. Now the
> client doesn’t have a path forward. Reason being, in case of CreatePath,
> client doesn’t know if the path was created on the original request or the
> path was already there for some other request, in case of RenamePath, client
> doesn’t know if the source was removed because of the original-try or it was
> not there on the first place.
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
