Greetings fellow monks,

I am a strong advocate of perl, so I was very disappointed today when I ran some disk benchmarks and found that perl disk IO seems to be very slow.

I'm writing a gds parser. gds is a binary file format that defines a microchip layout. I wrote a very simple perl script for benchmark testing that just opens the file and reads it in using read commands, without actually doing anything with the data. The code is included below.

This script processes 10 megs of data per second. An equivalent C program that does the exact same thing processes 50 megs of data per second. Why is perl's IO so slow, and is there anything I can do to improve it? Is there an IO module with a more efficient implementation?

Thanks,
TROGDOR

open (FILE, "$path")
   or die "ERROR: Could not open $path.\n";

while (1) {
   $eof = read (FILE, $header, 4);

   ($size, $code, $ftype) = unpack ("nCC", $header) ;
   if ($size == 0) {
      print "Size is zero.  Exiting.\n";
      last;
   }

   $size = $size - 4;
   if ($size > 0) {
      $eof = read (FILE, $data, $size);
   }
}
close FILE;
[download]

---

---

• Are you posting in the right place? Check out Where do I post X? to know for sure.
• Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:

  <code> <a> <b> <big> <blockquote> <br /> <dd> <dl> <dt> <em> <font> <h1> <h2> <h3> <h4> <h5> <h6> <hr /> <i> <li> <nbsp> <ol> <p> <small> <strike> <strong> <sub> <sup> <table> <td> <th> <tr> <tt> <u> <ul>

• Snippets of code should be wrapped in <code> tags not <pre> tags. In fact, <pre> tags should generally be avoided. If they must be used, extreme care should be taken to ensure that their contents do not have long lines (<70 chars), in order to prevent horizontal scrolling (and possible janitor intervention).
• Want more info? How to link or How to display code and escape characters are good places to start.