diff --git a/hadoop-common-project/hadoop-common/CHANGES.txt b/hadoop-common-project/hadoop-common/CHANGES.txt index 18c73c0a7e..132e4c00aa 100644 --- a/hadoop-common-project/hadoop-common/CHANGES.txt +++ b/hadoop-common-project/hadoop-common/CHANGES.txt @@ -661,6 +661,10 @@ Release 2.8.0 - UNRELEASED HADOOP-11958. MetricsSystemImpl fails to show backtrace when an error occurs (Jason Lowe via jeagles) + + HADOOP-12009 Clarify FileSystem.listStatus() sorting order & fix + FileSystemContractBaseTest:testListStatus. (J.Andreina via stevel) + OPTIMIZATIONS HADOOP-11785. Reduce the number of listStatus operation in distcp diff --git a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java index 01d4b27460..3f9e3bd381 100644 --- a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java +++ b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileSystem.java @@ -1498,7 +1498,9 @@ public boolean accept(Path file) { /** * List the statuses of the files/directories in the given path if the path is * a directory. - * + *

+ * Does not guarantee to return the List of files/directories status in a + * sorted order. * @param f given path * @return the statuses of the files/directories in the given patch * @throws FileNotFoundException when the path does not exist; @@ -1540,6 +1542,9 @@ public RemoteIterator listCorruptFileBlocks(Path path) /** * Filter files/directories in the given path using the user-supplied path * filter. + *

+ * Does not guarantee to return the List of files/directories status in a + * sorted order. * * @param f * a path name @@ -1560,6 +1565,9 @@ public FileStatus[] listStatus(Path f, PathFilter filter) /** * Filter files/directories in the given list of paths using default * path filter. + *

+ * Does not guarantee to return the List of files/directories status in a + * sorted order. * * @param files * a list of paths @@ -1576,6 +1584,9 @@ public FileStatus[] listStatus(Path[] files) /** * Filter files/directories in the given list of paths using user-supplied * path filter. + *

+ * Does not guarantee to return the List of files/directories status in a + * sorted order. * * @param files * a list of paths @@ -1736,6 +1747,8 @@ public LocatedFileStatus next() throws IOException { * while consuming the entries. Each file system implementation should * override this method and provide a more efficient implementation, if * possible. + * Does not guarantee to return the iterator that traverses statuses + * of the files in a sorted order. * * @param p target path * @return remote iterator @@ -1763,6 +1776,8 @@ public FileStatus next() throws IOException { /** * List the statuses and block locations of the files in the given path. + * Does not guarantee to return the iterator that traverses statuses + * of the files in a sorted order. * * If the path is a directory, * if recursive is false, returns files in the directory; diff --git a/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md b/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md index 84e375508c..f323374c94 100644 --- a/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md +++ b/hadoop-common-project/hadoop-common/src/site/markdown/filesystem/filesystem.md @@ -183,6 +183,10 @@ to the same path: forall fs in listStatus(Path) : fs == getFileStatus(fs.path) +**Ordering of results**: there is no guarantee of ordering of the listed entries. +While HDFS currently returns an alphanumerically sorted list, neither the Posix `readdir()` +nor Java's `File.listFiles()` API calls define any ordering of returned values. Applications +which require a uniform sort order on the results must perform the sorting themselves. ### Atomicity and Consistency diff --git a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java index 2ca81e9e90..495af00089 100644 --- a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java +++ b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/FileSystemContractBaseTest.java @@ -20,6 +20,7 @@ import java.io.FileNotFoundException; import java.io.IOException; +import java.util.ArrayList; import junit.framework.TestCase; @@ -224,9 +225,13 @@ public void testListStatus() throws Exception { paths = fs.listStatus(path("/test/hadoop")); assertEquals(3, paths.length); - assertEquals(path("/test/hadoop/a"), paths[0].getPath()); - assertEquals(path("/test/hadoop/b"), paths[1].getPath()); - assertEquals(path("/test/hadoop/c"), paths[2].getPath()); + ArrayList list = new ArrayList(); + for (FileStatus fileState : paths) { + list.add(fileState.getPath().toString()); + } + assertTrue(list.contains(path("/test/hadoop/a"))); + assertTrue(list.contains(path("/test/hadoop/b"))); + assertTrue(list.contains(path("/test/hadoop/c"))); paths = fs.listStatus(path("/test/hadoop/a")); assertEquals(0, paths.length);