MAPREDUCE-6751. Add debug log message when splitting is not possible due to unsplittable compression. (Peter Vary via rchiang)

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/FileInputFormat.java

@@ -369,6 +369,13 @@ public abstract class FileInputFormat<K, V> implements InputFormat<K, V> {
                 splitHosts[0], splitHosts[1]));
           }
         } else {
+          if (LOG.isDebugEnabled()) {
+            // Log only if the file is big enough to be splitted
+            if (length > Math.min(file.getBlockSize(), minSize)) {
+              LOG.debug("File is not splittable so no parallelization "
+                  + "is possible: " + file.getPath());
+            }
+          }
           String[][] splitHosts = getSplitHostsAndCachedHosts(blkLocations,0,length,clusterMap);
           splits.add(makeSplit(path, 0, length, splitHosts[0], splitHosts[1]));
         }

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/input/CombineFileInputFormat.java

@@ -600,6 +600,10 @@ public abstract class CombineFileInputFormat<K, V>
         if (!isSplitable) {
           // if the file is not splitable, just create the one block with
           // full file length
+          if (LOG.isDebugEnabled()) {
+            LOG.debug("File is not splittable so no parallelization "
+                + "is possible: " + stat.getPath());
+          }
           blocks = new OneBlockInfo[1];
           fileSize = stat.getLen();
           blocks[0] = new OneBlockInfo(stat.getPath(), 0, fileSize,

hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapreduce/lib/input/FileInputFormat.java

@@ -422,6 +422,13 @@ public abstract class FileInputFormat<K, V> extends InputFormat<K, V> {
                        blkLocations[blkIndex].getCachedHosts()));
           }
         } else { // not splitable
+          if (LOG.isDebugEnabled()) {
+            // Log only if the file is big enough to be splitted
+            if (length > Math.min(file.getBlockSize(), minSize)) {
+              LOG.debug("File is not splittable so no parallelization "
+                  + "is possible: " + file.getPath());
+            }
+          }
           splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts(),
                       blkLocations[0].getCachedHosts()));
         }