HADOOP-19548: [ABFS] Fix Logging in FSDataInputStream to Mention Correct Buffersize

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

@@ -18,6 +18,7 @@
 
 package org.apache.hadoop.fs.azurebfs;
 
+import javax.annotation.Nullable;
 import java.io.File;
 import java.io.FileNotFoundException;
 import java.io.IOException;
@@ -41,7 +42,6 @@
 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;
@@ -118,7 +118,22 @@
 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.*;
+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.constants.AbfsHttpConstants.CPK_IN_NON_HNS_ACCOUNT_ERROR_MESSAGE;
 import static org.apache.hadoop.fs.azurebfs.constants.ConfigurationKeys.DATA_BLOCKS_BUFFER;
 import static org.apache.hadoop.fs.azurebfs.constants.ConfigurationKeys.FS_AZURE_ACCOUNT_IS_HNS_ENABLED;
@@ -347,8 +362,10 @@ 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());
   }
 

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

@@ -135,4 +135,23 @@ 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 = 5 * 1024 * 1024;
+    int bufferSizeArg = 10 * 1024 * 1024;
+
+    Path testPath = path(TEST_PATH);
+    fs.create(testPath);
+
+    abfsConfig.setReadBufferSize(bufferSizeConfig);
+    fs.open(testPath, bufferSizeArg);
+    int actualBufferSize = abfsConfig.getReadBufferSize();
+
+    assertEquals(bufferSizeConfig, actualBufferSize);
+    assertNotEquals(bufferSizeArg, actualBufferSize);
+  }
 }