MAPREDUCE-3988. mapreduce.job.local.dir doesn't point to a single directory on a node. (Eric Payne via bobby)

git-svn-id: https://svn.apache.org/repos/asf/hadoop/common/trunk@1309086 13f79535-47bb-0310-9956-ffa450edef68

hadoop-mapreduce-project/CHANGES.txt

@@ -231,6 +231,9 @@ Release 0.23.3 - UNRELEASED
 
     MAPREDUCE-4062. AM Launcher thread can hang forever (tgraves via bobby)
 
+    MAPREDUCE-3988. mapreduce.job.local.dir doesn't point to a single directory
+    on a node. (Eric Payne via bobby)
+
 Release 0.23.2 - UNRELEASED
 
   INCOMPATIBLE CHANGES

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapred/YarnChild.java

@@ -54,6 +54,7 @@ import org.apache.hadoop.security.Credentials;
 import org.apache.hadoop.security.UserGroupInformation;
 import org.apache.hadoop.security.token.Token;
 import org.apache.hadoop.security.token.TokenIdentifier;
+import org.apache.hadoop.util.DiskChecker.DiskErrorException;
 import org.apache.hadoop.util.StringUtils;
 import org.apache.hadoop.yarn.api.ApplicationConstants;
 import org.apache.log4j.LogManager;
@@ -236,11 +237,33 @@ class YarnChild {
     job.setStrings(MRConfig.LOCAL_DIR, localSysDirs);
     LOG.info(MRConfig.LOCAL_DIR + " for child: " + job.get(MRConfig.LOCAL_DIR));
     LocalDirAllocator lDirAlloc = new LocalDirAllocator(MRConfig.LOCAL_DIR);
-    Path workDir = lDirAlloc.getLocalPathForWrite("work", job);
+    Path workDir = null;
-    FileSystem lfs = FileSystem.getLocal(job).getRaw();
+    // First, try to find the JOB_LOCAL_DIR on this host.
-    if (!lfs.mkdirs(workDir)) {
+    try {
-        throw new IOException("Mkdirs failed to create "
+      workDir = lDirAlloc.getLocalPathToRead("work", job);
-            + workDir.toString());
+    } catch (DiskErrorException e) {
+      // DiskErrorException means dir not found. If not found, it will
+      // be created below.
+    }
+    if (workDir == null) {
+      // JOB_LOCAL_DIR doesn't exist on this host -- Create it.
+      workDir = lDirAlloc.getLocalPathForWrite("work", job);
+      FileSystem lfs = FileSystem.getLocal(job).getRaw();
+      boolean madeDir = false;
+      try {
+        madeDir = lfs.mkdirs(workDir);
+      } catch (FileAlreadyExistsException e) {
+        // Since all tasks will be running in their own JVM, the race condition
+        // exists where multiple tasks could be trying to create this directory
+        // at the same time. If this task loses the race, it's okay because
+        // the directory already exists.
+        madeDir = true;
+        workDir = lDirAlloc.getLocalPathToRead("work", job);
+      }
+      if (!madeDir) {
+          throw new IOException("Mkdirs failed to create "
+              + workDir.toString());
+      }
     }
     job.set(MRJobConfig.JOB_LOCAL_DIR,workDir.toString());
   }

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-jobclient/src/test/java/org/apache/hadoop/mapred/TestMiniMRChildTask.java

@@ -41,6 +41,7 @@ import org.apache.hadoop.fs.FileSystem;
 import org.apache.hadoop.fs.Path;
 import org.apache.hadoop.mapred.lib.IdentityReducer;
 import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.MRJobConfig;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.hdfs.MiniDFSCluster;
 import org.apache.hadoop.mapreduce.v2.MiniMRYarnCluster;
@@ -228,6 +229,10 @@ public class TestMiniMRChildTask {
       // check if X=$(tt's X var):/tmp for an old env variable inherited from 
       // the tt
       checkEnv("PATH",  path + ":/tmp", "noappend");
+
+      String jobLocalDir = job.get(MRJobConfig.JOB_LOCAL_DIR);
+      assertNotNull(MRJobConfig.JOB_LOCAL_DIR + " is null",
+                    jobLocalDir);
     }
 
     public void map(WritableComparable key, Writable value,