[hadoop] branch trunk updated: HADOOP-18636 LocalDirAllocator cannot recover from directory tree deletion (#5412)

[st...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

stevel pushed a commit to branch trunk
in repository https://gitbox.apache.org/repos/asf/hadoop.git


The following commit(s) were added to refs/heads/trunk by this push:
     new 11a220c6e71 HADOOP-18636 LocalDirAllocator cannot recover from directory tree deletion (#5412)
11a220c6e71 is described below

commit 11a220c6e712d1b0732e9e514287dea35067b949
Author: Steve Loughran <st...@cloudera.com>
AuthorDate: Wed Feb 22 11:48:12 2023 +0000

    HADOOP-18636 LocalDirAllocator cannot recover from directory tree deletion (#5412)
    
    
    
    Even though DiskChecker.mkdirsWithExistsCheck() will create the directory tree,
    it is only called *after* the enumeration of directories with available
    space has completed.
    
    Directories which don't exist are reported as having 0 space, therefore
    the mkdirs code is never reached.
    
    Adding a simple mkdirs() -without bothering to check the outcome-
    ensures that if a dir has been deleted then it will be reconstructed
    if possible. If it can't it will still have 0 bytes of space
    reported and so be excluded from the allocation.
    
    Contributed by Steve Loughran
---
 .../java/org/apache/hadoop/fs/LocalDirAllocator.java  |  9 ++++++++-
 .../org/apache/hadoop/fs/TestLocalDirAllocator.java   | 19 +++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/LocalDirAllocator.java b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/LocalDirAllocator.java
index 774e015b373..d8ab16f41d3 100644
--- a/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/LocalDirAllocator.java
+++ b/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/LocalDirAllocator.java
@@ -414,7 +414,14 @@ public class LocalDirAllocator {
         
             //build the "roulette wheel"
         for(int i =0; i < ctx.dirDF.length; ++i) {
-          availableOnDisk[i] = ctx.dirDF[i].getAvailable();
+          final DF target = ctx.dirDF[i];
+          // attempt to recreate the dir so that getAvailable() is valid
+          // if it fails, getAvailable() will return 0, so the dir will
+          // be declared unavailable.
+          // return value is logged at debug to keep spotbugs quiet.
+          final boolean b = new File(target.getDirPath()).mkdirs();
+          LOG.debug("mkdirs of {}={}", target, b);
+          availableOnDisk[i] = target.getAvailable();
           totalAvailable += availableOnDisk[i];
         }
 
diff --git a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/TestLocalDirAllocator.java b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/TestLocalDirAllocator.java
index 939881f39df..3693b4f0acd 100644
--- a/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/TestLocalDirAllocator.java
+++ b/hadoop-common-project/hadoop-common/src/test/java/org/apache/hadoop/fs/TestLocalDirAllocator.java
@@ -548,5 +548,24 @@ public class TestLocalDirAllocator {
             "p1/x", Long.MAX_VALUE - 1), "Expect a DiskErrorException.",
         () -> dirAllocator.getLocalPathForWrite("p1/x", Long.MAX_VALUE - 1, conf));
   }
+
+  /**
+   * Test for HADOOP-18636 LocalDirAllocator cannot recover from directory tree deletion.
+   */
+  @Test(timeout = 30000)
+  public void testDirectoryRecovery() throws Throwable {
+    String dir0 = buildBufferDir(ROOT, 0);
+    String subdir = dir0 + "/subdir1/subdir2";
+
+    conf.set(CONTEXT, subdir);
+    // get local path and an ancestor
+    final Path pathForWrite = dirAllocator.getLocalPathForWrite("file", -1, conf);
+    final Path ancestor = pathForWrite.getParent().getParent();
+
+    // delete that ancestor
+    localFs.delete(ancestor, true);
+    // and expect to get a new file back
+    dirAllocator.getLocalPathForWrite("file2", -1, conf);
+  }
 }
 


---------------------------------------------------------------------
To unsubscribe, e-mail: common-commits-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-commits-help@hadoop.apache.org