Update: The disparity is coming from strftime.

Update: One must use threads on the Mac and non-threads on Linux for best performance. This is mind-boggling to me. Replacing the strftime line with $A = $Y completes in a couple seconds for threads or non-threads on the Mac and Linux.

The same 500 MB input file is used by both OS.

Mac OS X       Serial:  18.185s
Mac OS X     Parallel:   6.687s  threads
Mac OS X     Parallel:  42.526s  non-threads

CentOS 7 VM    Serial:  10.832s
CentOS 7 VM  Parallel:  23.849s  threads
CentOS 7 VM  Parallel:   2.993s  non-threads
[download]

#!/usr/bin/perl
use strict;
use warnings;

use threads;       # Comment out threads for child processes

use POSIX qw(strftime);
use MCE::Loop;
use MCE::Candy;

my $mutex :shared = 0;

my $infile  = $ARGV[0];
my $outfile = $ARGV[1];

open(DATAOUT, ">", $outfile);

## Workers process chunks in parallel until completed.
## Output order is preserved via MCE::Candy::out_iter_fh

MCE::Loop::init {
   chunk_size => "2m", max_workers => 4, use_slurpio => 1,
   gather => MCE::Candy::out_iter_fh(\*DATAOUT)
};

mce_loop_f {
   my ($mce, $chunkRef, $chunkID) = @_;
   my ($output, @Fields, $X, $Y, $A, $B, $C, $D, @G) = ("");

   open my $CHUNKIN, "<", $chunkRef;
   while( my $line = <$CHUNKIN> )
   {
      chomp $line;
      @Fields = split(',', $line, 9);
      $X = $Fields[8];
      $Y = substr $X, 0, 10;
      @G = gmtime $Y;
      $A = strftime "%M,%Y,%m,%d,%H,%j,%W,%u,%A", @G;
      $B = substr($A, 0, index($A, ','));
      $C = int($B/5);
      $D = int($B/15);
      $output .= $line.",$Y,$A,$C,$D\n";
   }
   close $CHUNKIN;

   MCE->gather($chunkID, $output);

} $infile;

close(DATAOUT);
[download]