I want to create a custom Apache2 log handler, and the template that is found on the apache site is:

#file:MyApache2/LogPerUser.pm
#---------------------------
package MyApache2::LogPerUser;

use strict;
use warnings;

use Apache2::RequestRec ();
use Apache2::Connection ();

use Fcntl qw(:flock);
use File::Spec::Functions qw(catfile);

use Apache2::Const -compile => qw(OK DECLINED);

sub handler {
  my $r = shift;

  my ($username) = $r->uri =~ m|^/~([^/]+)|;
  return Apache2::Const::DECLINED unless defined $username;

  my $entry = sprintf qq(%s [%s] "%s" %d %d\n),
      $r->connection->remote_ip, scalar(localtime),
      $r->uri, $r->status, $r->bytes_sent;

  my $log_path = catfile Apache2::ServerUtil::server_root,
      "logs", "$username.log";
  open my $fh, ">>$log_path" or die "can't open $log_path: $!";
  flock $fh, LOCK_EX;
  print $fh $entry;
  close $fh;

  return Apache2::Const::OK;
}
1;

What is the performance cost of the flocks? Is this logging process done in parallel, or in serial with the HTTP request? In parallel the performance would not matter as much, but I wouldn't want the user to wait another split second to add something like this.