bash$ bin/hdfs oiv -i fsimage -o fsimage.txt

   bash$ bin/hdfs oiv -i fsimage -o fsimage.xml -p XML

   bash$ bin/hdfs oiv -i fsimage -o fsimage.txt -p Indented

      numFilesOfEachUser.pig:
   -- This script determines the total number of files each user has in
   -- the namespace. Its output is of the form:
   --   username, totalNumFiles

   -- Load all of the fields from the file
   A = LOAD '$inputFile' USING PigStorage('\t') AS (path:chararray,
                                                    replication:int,
                                                    modTime:chararray,
                                                    accessTime:chararray,
                                                    blockSize:long,
                                                    numBlocks:int,
                                                    fileSize:long,
                                                    NamespaceQuota:int,
                                                    DiskspaceQuota:int,
                                                    perms:chararray,
                                                    username:chararray,
                                                    groupname:chararray);


   -- Grab just the path and username
   B = FOREACH A GENERATE path, username;

   -- Generate the sum of the number of paths for each user
   C = FOREACH (GROUP B BY username) GENERATE group, COUNT(B.path);

   -- Save results
   STORE C INTO '$outputFile';

   bin/pig -x local -param inputFile=../foo -param outputFile=../results ../numFilesOfEachUser.pig

   bart 1
   lisa 16
   homer 28
   marge 2456

      neverAccessed.pig:
   -- This script generates a list of files that were created but never
   -- accessed, based on their AccessTime

   -- Load all of the fields from the file
   A = LOAD '$inputFile' USING PigStorage('\t') AS (path:chararray,
                                                    replication:int,
                                                    modTime:chararray,
                                                    accessTime:chararray,
                                                    blockSize:long,
                                                    numBlocks:int,
                                                    fileSize:long,
                                                    NamespaceQuota:int,
                                                    DiskspaceQuota:int,
                                                    perms:chararray,
                                                    username:chararray,
                                                    groupname:chararray);

   -- Grab just the path and last time the file was accessed
   B = FOREACH A GENERATE path, accessTime;

   -- Drop all the paths that don't have the default assigned last-access time
   C = FILTER B BY accessTime == '1969-12-31 16:00';

   -- Drop the accessTimes, since they're all the same
   D = FOREACH C GENERATE path;

   -- Save results
   STORE D INTO '$outputFile';

   bin/pig -x local -param inputFile=../foo -param outputFile=../results ../neverAccessed.pig

      probableDuplicates.pig:
   -- This script finds probable duplicate files greater than 100 MB by
   -- grouping together files based on their byte size. Files of this size
   -- with exactly the same number of bytes can be considered probable
   -- duplicates, but should be checked further, either by comparing the
   -- contents directly or by another proxy, such as a hash of the contents.
   -- The scripts output is of the type:
   --    fileSize numProbableDuplicates {(probableDup1), (probableDup2)}

   -- Load all of the fields from the file
   A = LOAD '$inputFile' USING PigStorage('\t') AS (path:chararray,
                                                    replication:int,
                                                    modTime:chararray,
                                                    accessTime:chararray,
                                                    blockSize:long,
                                                    numBlocks:int,
                                                    fileSize:long,
                                                    NamespaceQuota:int,
                                                    DiskspaceQuota:int,
                                                    perms:chararray,
                                                    username:chararray,
                                                    groupname:chararray);

   -- Grab the pathname and filesize
   B = FOREACH A generate path, fileSize;

   -- Drop files smaller than 100 MB
   C = FILTER B by fileSize > 100L  * 1024L * 1024L;

   -- Gather all the files of the same byte size
   D = GROUP C by fileSize;

   -- Generate path, num of duplicates, list of duplicates
   E = FOREACH D generate group AS fileSize, COUNT(C) as numDupes, C.path AS files;

   -- Drop all the files where there are only one of them
   F = FILTER E by numDupes > 1L;

   -- Sort by the size of the files
   G = ORDER F by fileSize;

   -- Save results
   STORE G INTO '$outputFile';

   bin/pig -x local -param inputFile=../foo -param outputFile=../results ../probableDuplicates.pig

   1077288632 2 {(/user/tennant/work1/part-00501),(/user/tennant/work1/part-00993)}
   1077288664 4 {(/user/tennant/work0/part-00567),(/user/tennant/work0/part-03980),(/user/tennant/work1/part-00725),(/user/eccelston/output/part-03395)}
   1077288668 3 {(/user/tennant/work0/part-03705),(/user/tennant/work0/part-04242),(/user/tennant/work1/part-03839)}
   1077288698 2 {(/user/tennant/work0/part-00435),(/user/eccelston/output/part-01382)}
   1077288702 2 {(/user/tennant/work0/part-03864),(/user/eccelston/output/part-03234)}