Skip to content

HADOOP-19548: [ABFS][Backport to 3.4] Fix Logging in FSDataInputStream to Mention Correct Buffersize #7660

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 30, 2025
Merged

HADOOP-19548: [ABFS][Backport to 3.4] Fix Logging in FSDataInputStream to Mention Correct Buffersize #7660

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
2 changes: 1 addition & 1 deletion hadoop-tools/hadoop-azure/dev-support/testrun-scripts/configsupport.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,7 +115,7 @@ promptNamespaceType() {
printf "* In the left-hand menu, select 'Overview' section and look for 'Properties'. \n"
printf "* Under 'Blob service', check if 'Hierarchical namespace' is enabled or disabled. \n"
echo "$contactTeamMsg"
select namespaceType in "HNS" "NonHNS"
select namespaceType in "HNS" "NonHNS (FNS)"
do
case $namespaceType in
HNS)
Expand Down
23 changes: 5 additions & 18 deletions ...p-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/AzureBlobFileSystem.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@

package org.apache.hadoop.fs.azurebfs;

import javax.annotation.Nullable;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.IOException;
Expand All @@ -42,6 +41,7 @@
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;
import java.util.concurrent.Future;
import javax.annotation.Nullable;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
Expand Down Expand Up @@ -118,22 +118,7 @@
import static org.apache.hadoop.fs.CommonConfigurationKeys.IOSTATISTICS_LOGGING_LEVEL;
import static org.apache.hadoop.fs.CommonConfigurationKeys.IOSTATISTICS_LOGGING_LEVEL_DEFAULT;
import static org.apache.hadoop.fs.Options.OpenFileOptions.FS_OPTION_OPENFILE_STANDARD_OPTIONS;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_APPEND;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_CREATE;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_CREATE_NON_RECURSIVE;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_DELETE;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_EXIST;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_GET_DELEGATION_TOKEN;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_GET_FILE_STATUS;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_LIST_STATUS;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_MKDIRS;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_OPEN;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.CALL_RENAME;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.DIRECTORIES_CREATED;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.DIRECTORIES_DELETED;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.ERROR_IGNORED;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.FILES_CREATED;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.FILES_DELETED;
import static org.apache.hadoop.fs.azurebfs.AbfsStatistic.*;
Copy link
Contributor

@mukund-thakur mukund-thakur Apr 30, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks like this got changed here https://github.com/apache/hadoop/pull/7523/files#diff-58f7a2a7f1c0b0f71e935687a17dedff0b9456c5aafddd69aff58df56f463973R121 and new we are reverting back

Copy link
Contributor

@mukund-thakur mukund-thakur Apr 30, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should avoid changing imports like this unless it is mandatory. Thanks

import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.CPK_IN_NON_HNS_ACCOUNT_ERROR_MESSAGE;
import static org.apache.hadoop.fs.azurebfs.constants.AbfsServiceType.DFS;
import static org.apache.hadoop.fs.azurebfs.constants.ConfigurationKeys.DATA_BLOCKS_BUFFER;
Expand Down Expand Up @@ -365,8 +350,10 @@ public void registerListener(Listener listener1) {

@Override
public FSDataInputStream open(final Path path, final int bufferSize) throws IOException {
LOG.debug("AzureBlobFileSystem.open path: {} bufferSize: {}", path, bufferSize);
// bufferSize is unused.
LOG.debug(
"AzureBlobFileSystem.open path: {} bufferSize as configured in 'fs.azure.read.request.size': {}",
path, abfsStore.getAbfsConfiguration().getReadBufferSize());
return open(path, Optional.empty());
}

Expand Down
29 changes: 29 additions & 0 deletions ...s/hadoop-azure/src/test/java/org/apache/hadoop/fs/azurebfs/ITestFileSystemProperties.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,14 +20,18 @@

import java.util.Hashtable;

import org.assertj.core.api.Assertions;
import org.junit.Test;

import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.azurebfs.services.AbfsInputStream;
import org.apache.hadoop.fs.azurebfs.utils.TracingContext;

import static org.apache.hadoop.fs.azurebfs.constants.FileSystemConfigurations.ONE_MB;

/**
* Test FileSystemProperties.
*/
Expand Down Expand Up @@ -135,4 +139,29 @@ public void testSetFileSystemProperties() throws Exception {

assertEquals(properties, fetchedProperties);
}

@Test
//Test to verify buffersize remains the same as set in the configuration, irrespective of the parameter passed to FSDataInputStream
public void testBufferSizeSet() throws Exception {
final AzureBlobFileSystem fs = getFileSystem();
AbfsConfiguration abfsConfig = fs.getAbfsStore().getAbfsConfiguration();
int bufferSizeConfig = 6 * ONE_MB;
int bufferSizeArg = 10 * ONE_MB;

Path testPath = path(TEST_PATH);
fs.create(testPath);

abfsConfig.setReadBufferSize(bufferSizeConfig);
FSDataInputStream inputStream = fs.open(testPath, bufferSizeArg);
AbfsInputStream abfsInputStream
= (AbfsInputStream) inputStream.getWrappedStream();
int actualBufferSize = abfsInputStream.getBufferSize();

Assertions.assertThat(actualBufferSize)
.describedAs("Buffer size should be set to the value in the configuration")
.isEqualTo(bufferSizeConfig);
Assertions.assertThat(actualBufferSize)
.describedAs("Buffer size should not be set to the value passed as argument")
.isNotEqualTo(bufferSizeArg);
}
}