Split syslog file based on month field

syslog-splitter.pl

#!/usr/bin/perl

my $m_old = "";
my $y = 0;

my $fd;
my $fn = "";

my %mon = (
	Jan	=>	'01',
	Feb	=>	'02',
	Mar	=>	'03',
	Apr	=>	'04',
	May	=>	'05',
	Jun	=>	'06',
	Jul	=>	'07',
	Aug	=>	'08',
	Sep	=>	'09',
	Oct	=>	'10',
	Nov	=>	'11',
	Dec	=>	'12',
);

while (<>) {
	next unless (/^(...) /);
	my $m = $1;
	if ($m ne $m_old) {
		if ($m_old ne "") {
			print STDERR "closing $m_old ..";
			close($fd);
			print STDERR " ok\n";
		}
		if ($m eq "Jan") {
			$y++;
		}
		$fn = "./nagios_${y}-${mon{$m}}";
		print STDERR "creating new $fn ..";
		die "already exists" if (-e $fn);
		open($fd, ">", $fn) || die "Error: $.";
		print STDERR " $y ok\n";
		$m_old = $m;
	}
	print $fd $_;
}

Time to split 13GB and 85 million lines into 77 files on Linux 2.6 with 2 core 2.13GHz Xeon and 1GB memory:

real 19m55.749s
user 3m41.751s
sys 0m45.012s