The problem is in the @ready = $sel->can_read(0.0001); The thing is that this returns a socket only whenever there is a new socket or whenever a socket is closed. Otherwise it waits those 0.0001 seconds. Which may seem small but for 10*1024 (that's how many characters my test script tried to read) this means 1.024s wasted. And is it really necessary to check for new sockets 10000 times a second?;-)

This script

use strict;
use warnings;
use IO::Socket;
use Time::HiRes qw(gettimeofday tv_interval);

my $sock = IO::Socket::INET->new(PeerAddr => 'localhost',
                                 PeerPort => '19',
                                 Proto    => 'tcp');

my $start_time = [gettimeofday];

my $buff;
for (1..10) {
    read $sock, $buff, 1024;
}

print "Taken " . tv_interval($start_time) . "seconds\n";
$sock->close();
[download]

took approximately 10s to read those 10*1024 characters with your code, no matter if I ran just one or eight of them. With this change:

use constant NEW_SOCK_EVERY => 1000;
...
    my $server_sock = new IO::Socket::INET(
        Listen => 1,LocalPort => 19,Reuse=> 1
    );
    my $sel = new IO::Select( $server_sock  );
    my $i = NEW_SOCK_EVERY;
    while($server_sock) {
        if (++$i>=NEW_SOCK_EVERY) {
            $i=0;
            foreach my $socket ($sel->can_read(0.0001)) {
                if($socket == $server_sock ) {
                    new_socket($socket);
                }else{
                    if(defined ($socket)) {
                        close_socket($socket);
                    }
                }
            }
        }
        foreach my $wsocket ($sel->can_write(0.0001)) {
            gen_chars($wsocket);
        }
    }
...
[download]

the time went down to about 2s. I think it's enough to test for new clients 10 times a second, don't you? ;-)

Another option that seems to work (though I can't find it mentioned in the IO::Select's docs) is to specify a negative timeout for the can_read(). That seems to bring the time down to 1.1-1.3 seconds. And it's a much smaller change to your code :-)

---

---

Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!

Titles consisting of a single word are discouraged, and in most cases are disallowed outright.

Read Where should I post X? if you're not absolutely sure you're posting in the right place.

Please read these before you post! —

• How do I compose an effective node title?
• How do I post a question effectively?
• Markup in the Monastery

Posts may use any of the Perl Monks Approved HTML tags:

a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr

You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)

	For:		Use:
	&		&
	<		&lt;
	>		&gt;
	[		&#91;
	]		&#93;

Link using PerlMonks shortcuts! What shortcuts can I use for linking?

See Writeup Formatting Tips and other pages linked from there for more info.