#!/usr/bin/perl

use strict;
use warnings;

use File::Find;
use threads;

my $size_threshold = 5 * 1024 * 1024; #point at which to abort directory travers
ing.

my @dirs =  ( "/nas/fs001", "/nas/fs002",  "/nas/fs003",  "/nas/fs003",
              "/nas/fs004", "/nas/fs005", "/nas/fs006", "/nas/fs007",
              "/nas/fs008", "/nas/fs009", "/nas/fs010", "/nas/fs011",
              "/nas/fs012", "/nas/fs013", "/nas/fs014" );
@dirs = ( "/usr/local/apache" );
@dirs = ( "/nas/fs001", "/nas/fs002" );

#"/usr/local/apache";
my $customer_file = "/usr/local/apache/htdocs/dusage/disk_usage.conf";
my $max_depth = 7;

my $debug = 1;

sub dusage
{
  my $dir = pop; # 1 arg only, because that lets me thread.
  my $tsize;
  my %rtree;
  my $datafile = $dir;
  $datafile =~ s,/,,g;
  print "Opening $datafile for output";
  open ( OUTPUT, ">$datafile.csv" ) or die $!;
  find (
     sub {
       if ( -f && ! -l )
       {
         my $filesize = -s $_;
         $tsize += $filesize;

       #chop up the path, populate rtree at each of traverse_depth levels

         my @directory_structure = split ( '/', $File::Find::name );
         pop(@directory_structure); # we'll never want the trailing filename

         for ( my $depth = 0; $depth <= $max_depth; $depth++)
         {
           if ( $#directory_structure < $depth ) { next };
           my $thispath = join ( '/', @directory_structure[0..$depth]);
           $rtree{$thispath} += $filesize;
         }
       }
     }
     , $dir );

    foreach my $key ( keys ( %rtree ) )
    {
      my $indent = ( $key =~ tr,/,, );
      print OUTPUT $indent, ",", $key, ",", $rtree{$key},"\n";
    }

  close (OUTPUT);
}

#main

foreach my $directory ( @dirs )
{
  dusage ( $directory );
}