Skip to content

HADOOP-19497 [branch-3.4]: [ABFS] Enable rename and create recovery from client transaction id over DFS endpoint #7612

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 15, 2025
Merged

HADOOP-19497 [branch-3.4]: [ABFS] Enable rename and create recovery from client transaction id over DFS endpoint #7612

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 1 addition & 4 deletions ...hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/constants/AbfsHttpConstants.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,13 +199,10 @@ public String toString() {
}

public static ApiVersion getCurrentVersion() {
return DEC_12_2019;
return NOV_04_2024;
}
}

@Deprecated
public static final String DECEMBER_2019_API_VERSION = ApiVersion.DEC_12_2019.toString();

/**
* List of Constants Used by Blob Endpoint Rest APIs.
*/
Expand Down
2 changes: 1 addition & 1 deletion ...azure/src/main/java/org/apache/hadoop/fs/azurebfs/constants/FileSystemConfigurations.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,7 +198,7 @@ public final class FileSystemConfigurations {

public static final int DEFAULT_FS_AZURE_BLOB_DELETE_THREAD = DEFAULT_FS_AZURE_LISTING_ACTION_THREADS;

public static final boolean DEFAULT_FS_AZURE_ENABLE_CLIENT_TRANSACTION_ID = false;
public static final boolean DEFAULT_FS_AZURE_ENABLE_CLIENT_TRANSACTION_ID = true;

private FileSystemConfigurations() {}
}
6 changes: 0 additions & 6 deletions ...p-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsClient.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,6 @@ private AbfsClient(final URL baseUrl,
this.encryptionContextProvider = encryptionContextProvider;
// Version update needed to support x-ms-encryption-context header
// @link https://learn.microsoft.com/en-us/rest/api/storageservices/put-block?tabs=microsoft-entra-id}
xMsVersion = ApiVersion.AUG_03_2023; // will be default once server change deployed
encryptionType = EncryptionType.ENCRYPTION_CONTEXT;
} else if (abfsConfiguration.getEncodedClientProvidedEncryptionKey() != null) {
clientProvidedEncryptionKey =
Expand All @@ -228,11 +227,6 @@ private AbfsClient(final URL baseUrl,
encryptionType = EncryptionType.GLOBAL_KEY;
}

// Version update needed to support x-ms-client-transaction-id header
if (abfsConfiguration.getIsClientTransactionIdEnabled()) {
xMsVersion = ApiVersion.NOV_04_2024;
}

String sslProviderName = null;

if (this.baseUrl.toString().startsWith(HTTPS_SCHEME)) {
Expand Down
445 changes: 301 additions & 144 deletions ...ools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsDfsClient.java
View file
Open in desktop

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion ...p-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsErrors.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ public final class AbfsErrors {
public static final String ERR_CREATE_RECOVERY =
"Error while recovering from create failure.";
public static final String ERR_RENAME_RECOVERY =
"Error while recovering from rename failure.";
"Error while recovering from rename failure for path: ";
public static final String ERR_BLOB_LIST_PARSING = "Parsing of XML List Response Failed in BlobClient.";
public static final String ERR_DFS_LIST_PARSING = "Parsing of Json List Response Failed in DfsClient.";
public static final String INCORRECT_INGRESS_TYPE = "Ingress Type Cannot be DFS for Blob endpoint configured filesystem.";
Expand Down
2 changes: 1 addition & 1 deletion ...oop-azure/src/test/java/org/apache/hadoop/fs/azurebfs/ITestAzureBlobFileSystemCreate.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2289,6 +2289,6 @@ public void answer(final AbfsRestOperation mockedObj,
null, op);
}
}
});
}, 0);
}
}
9 changes: 5 additions & 4 deletions ...oop-azure/src/test/java/org/apache/hadoop/fs/azurebfs/ITestAzureBlobFileSystemRename.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2673,12 +2673,13 @@ public void testFailureInGetPathStatusDuringRenameRecovery() throws Exception {
final String[] clientTransactionId = new String[1];
mockAddClientTransactionIdToHeader(abfsDfsClient, clientTransactionId);
mockRetriedRequest(abfsDfsClient, new ArrayList<>());
boolean[] flag = new boolean[1];
int[] flag = new int[1];
Mockito.doAnswer(getPathStatus -> {
if (!flag[0]) {
flag[0] = true;
if (flag[0] == 1) {
flag[0] += 1;
throw new AbfsRestOperationException(HTTP_CLIENT_TIMEOUT, "", "", new Exception());
}
flag[0] += 1;
return getPathStatus.callRealMethod();
}).when(abfsDfsClient).getPathStatus(
Mockito.nullable(String.class), Mockito.nullable(Boolean.class),
Expand Down Expand Up @@ -2737,6 +2738,6 @@ public void answer(final AbfsRestOperation mockedObj,
SOURCE_PATH_NOT_FOUND.getErrorCode(), EMPTY_STRING, null, op);
}
}
});
}, 1);
}
}
9 changes: 5 additions & 4 deletions ...ols/hadoop-azure/src/test/java/org/apache/hadoop/fs/azurebfs/services/TestAbfsClient.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,11 +152,11 @@ private boolean isThreadRunning(String threadName) {
* @throws Exception if an error occurs while mocking the operation creation
*/
public static void mockAbfsOperationCreation(final AbfsClient abfsClient,
final MockIntercept mockIntercept) throws Exception {
boolean[] flag = new boolean[1];
final MockIntercept mockIntercept, int failedCall) throws Exception {
int[] flag = new int[1];
Mockito.doAnswer(answer -> {
if (!flag[0]) {
flag[0] = true;
if (flag[0] == failedCall) {
flag[0] += 1;
AbfsRestOperation op = Mockito.spy(
new AbfsRestOperation(
answer.getArgument(0),
Expand All @@ -174,6 +174,7 @@ public static void mockAbfsOperationCreation(final AbfsClient abfsClient,
Mockito.doReturn(true).when(op).isARetriedRequest();
return op;
}
flag[0] += 1;
return answer.callRealMethod();
}).when(abfsClient)
.getAbfsRestOperation(any(), any(), any(), any());
Expand Down
23 changes: 17 additions & 6 deletions ...ure/src/test/java/org/apache/hadoop/fs/azurebfs/services/TestAbfsRenameRetryRecovery.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,7 @@
import org.apache.hadoop.fs.azurebfs.contracts.exceptions.AbfsRestOperationException;
import org.apache.hadoop.fs.azurebfs.contracts.exceptions.AzureBlobFileSystemException;
import org.apache.hadoop.fs.azurebfs.contracts.services.AzureServiceErrorCode;
import org.apache.hadoop.fs.azurebfs.security.ContextEncryptionAdapter;
import org.apache.hadoop.fs.azurebfs.utils.TracingContext;
import org.apache.hadoop.fs.statistics.IOStatistics;

Expand All @@ -58,7 +59,9 @@
import static org.apache.hadoop.fs.statistics.IOStatisticAssertions.assertThatStatisticCounter;
import static org.apache.hadoop.fs.statistics.IOStatisticAssertions.lookupCounterStatistic;
import static org.apache.hadoop.test.LambdaTestUtils.intercept;
import static org.mockito.ArgumentMatchers.anyBoolean;
import static org.mockito.ArgumentMatchers.anyList;
import static org.mockito.ArgumentMatchers.anyString;
import static org.mockito.Mockito.doReturn;
import static org.mockito.Mockito.mock;
import static org.mockito.Mockito.times;
Expand Down Expand Up @@ -180,6 +183,12 @@ AbfsClient getMockAbfsClient() throws IOException {
.when(spyClient)
.createRenameRestOperation(Mockito.any(URL.class), anyList());

Mockito.doCallRealMethod()
.when(spyClient)
.getPathStatus(anyString(), anyBoolean(),
Mockito.any(TracingContext.class),
Mockito.any(ContextEncryptionAdapter.class));

return spyClient;

}
Expand Down Expand Up @@ -275,9 +284,14 @@ public void testRenameRecoveryEtagMatchFsLevel() throws IOException {
// 4 calls should have happened in total for rename
// 1 -> original rename rest call, 2 -> first retry,
// +2 for getPathStatus calls
int totalConnections = 4;
if (!getConfiguration().getIsClientTransactionIdEnabled()) {
// 1 additional getPathStatus call to get dest etag
totalConnections++;
}
assertThatStatisticCounter(ioStats,
CONNECTIONS_MADE.getStatName())
.isEqualTo(5 + connMadeBeforeRename);
.isEqualTo(totalConnections + connMadeBeforeRename);
// the RENAME_PATH_ATTEMPTS stat should be incremented by 1
// retries happen internally within AbfsRestOperation execute()
// the stat for RENAME_PATH_ATTEMPTS is updated only once before execute() is called
Expand Down Expand Up @@ -350,21 +364,18 @@ public void testRenameRecoveryFailsForDirFsLevel() throws Exception {
if (getConfiguration().getIsClientTransactionIdEnabled()) {
// Recovery based on client transaction id should be successful
assertTrue(renameResult);
// One extra getPathStatus call should have happened
newConnections = 5;
} else {
assertFalse(renameResult);
newConnections = 4;
}

// validating stat counters after rename
// 3 calls should have happened in total for rename
// 4 calls should have happened in total for rename
// 1 -> original rename rest call, 2 -> first retry,
// +1 for getPathStatus calls
// last getPathStatus call should be skipped
assertThatStatisticCounter(ioStats,
CONNECTIONS_MADE.getStatName())
.isEqualTo(newConnections + connMadeBeforeRename);
.isEqualTo(4 + connMadeBeforeRename);

// the RENAME_PATH_ATTEMPTS stat should be incremented by 1
// retries happen internally within AbfsRestOperation execute()
Expand Down