#!/usr/bin/perl
# Website Differential Backup
# Keeps several websites and their databases backed up
# by Ed Salisbury (ed@edsalisbury.net)
# http://www.edsalisbury.net
# (c)2009 Ed Salisbury, Some Rights Reserved
#
# Config File Format
# DIR /path/to/dir
# DB dbname
#
# Limitations:
# * Cannot do differential backups of databases
#
#
# License:
# Except where otherwise noted, this work is licensed under Creative Commons
#   Attribution ShareAlike 3.0.
#
# You are free:
#   * to Share - to copy, distribute and transmit the work
#   * to Remix - to adapt the work
#
# Under the following conditions:
#   * Attribution. You must attribute the work in the manner specified by the
#     author or licensor (but not in any way that suggests that they endorse
#     you or your use of the work).
#   * Share Alike. If you alter, transform, or build upon this work, you may
#     distribute the resulting work only under the same, similar or a
#     compatible license.
#   * For any reuse or distribution, you must make clear to others the license
#     terms of this work. The best way to do this is with a link to the
#     license's web page (http://creativecommons.org/licenses/by-sa/3.0/)
#   * Any of the above conditions can be waived if you get permission from the
#   * Nothing in this license impairs or restricts the author's moral rights.

use strict;
use warnings;

# Place to store backups
my $BACKUP_DIR = "/backup";
# Configuration file to read what to backup
my $BACKUP_CONF = "/usr/local/etc/backup.conf";
# Database user/pass
my $DB_USER = 'root';
my $DB_PASS = '**DBPASSWD**';

# Turn off output buffering
$|++;

# Tools
my $TAR = '/bin/tar';
my $GZIP = '/bin/gzip';
my $LS = '/bin/ls';
my $HEAD = '/usr/bin/head';
my $MKDIR = '/bin/mkdir';
my $RM = '/bin/rm';
my $MYSQLDUMP = '/usr/local/mysql/bin/mysqldump';

my @months = qw( Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec );
my @days = qw( Sun Mon Tue Wed Thu Fri Sat );
my @dirs;
my @dbs;

# Get current date
my ($sec, $min, $hour, $mday, $mon, $year, $wday, $yday, $isdst) = localtime time;
my $datestamp = sprintf("%04d%02d%02d", $year+1900, $mon+1, $mday);
my $day = $days[$wday];

# Read config file
unless (open(CFG, $BACKUP_CONF))
{
    print "Error: Cannot open $BACKUP_CONF\n";
    exit(1);
}
while (<CFG>)
{
    chomp;
    if (/^DIR\s+(.*)$/i)
    {
        push (@dirs, $1);
    }
    elsif (/^DB\s+(.*)$/i)
    {
        push (@dbs, $1);
    }
}
close (CFG);

# Do Directory Backups
foreach my $dir (@dirs)
{
    print "Backing up $dir... ";

    # Add backslashes for spaces
    $dir =~ s/ /\\ /g;

    my $backup_src = $dir;

    # Convert slashes to underscores
    $dir =~ s/\//_/g;
    # Remove leading slash
    $dir = substr($dir,1);

    unless (-d "$BACKUP_DIR/$dir")
    {
        system("$MKDIR -p $BACKUP_DIR/$dir");
    }

    # Get datestamp of last full backup
    my $last_full = `$LS -t $BACKUP_DIR/$dir/${dir}_full* 2>&1 | $HEAD -1`;
    chomp($last_full);
    if ($last_full =~ /No such file or directory/)
    {
        $last_full = '';
    }
    my ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,$atime,$mtime,$ctime,
        $blksize,$blocks) = stat($last_full);

    if ($mday == 1)
    {
        # Monthly Full Backup
        system("$TAR -cf $BACKUP_DIR/$dir/${dir}_full_monthly_$datestamp.tar $backup_src > /dev/null 2>&1");
        system("$GZIP -f $BACKUP_DIR/$dir/${dir}_full_monthly_$datestamp.tar");
        system("$RM $BACKUP_DIR/$dir/${dir}_full_weekly_*");
    }
    elsif ($wday == 0 || !$last_full)
    {
        # Weekly Full Backup
        system("$TAR -cf $BACKUP_DIR/$dir/${dir}_full_weekly_$datestamp.tar $backup_src  > /dev/null 2>&1");
        system("$GZIP -f $BACKUP_DIR/$dir/${dir}_full_weekly_$datestamp.tar");
    }

    # Daily Differential Backup
    if ($mtime)
    {
        my $newer = sprintf("%02d-%s", (localtime($mtime))[3], $months[(localtime($mtime))[4]]);
        system("$TAR --newer $newer -cf $BACKUP_DIR/$dir/${dir}_diff_daily_$day.tar $backup_src > /dev/null 2>&1");
    }
    else
    {
        system("$TAR -cf $BACKUP_DIR/$dir/${dir}_diff_daily_$day.tar $backup_src > /dev/null 2>&1");
    }
    system("$GZIP -f $BACKUP_DIR/$dir/${dir}_diff_daily_$day.tar");

    print "done.\n";
}

# Do Database Backups
foreach my $db (@dbs)
{
    my $db_name = $db;
    $db = "db_$db";

    unless (-d "$BACKUP_DIR/$db")
    {
        system("$MKDIR -p $BACKUP_DIR/$db");
    }

    print "Backing up $db_name database... ";

    if ($mday == 1)
    {
        # Monthly Backup
        system("$MYSQLDUMP --user=$DB_USER --password='$DB_PASS' $db_name > $BACKUP_DIR/$db/${db}_monthly_$datestamp.sql");
        system("$GZIP -f $BACKUP_DIR/$db/${db}_monthly_$datestamp.sql");
        system("$RM $BACKUP_DIR/$db/${db}_weekly_*");
    }
    elsif ($wday == 0)
    {
        # Weekly Backup
        system("$MYSQLDUMP --user=$DB_USER --password='$DB_PASS' $db_name > $BACKUP_DIR/$db/${db}_weekly_$datestamp.sql");
        system("$GZIP -f $BACKUP_DIR/$db/${db}_weekly_$datestamp.sql");
    }

    # Daily Backup
    system("$MYSQLDUMP --user=$DB_USER --password='$DB_PASS' $db_name > $BACKUP_DIR/$db/${db}_daily_$day.sql");
    system("$GZIP -f $BACKUP_DIR/$db/${db}_daily_$day.sql");

    print "done.\n";
}

Call the script something like /usr/local/bin/backup, and then create a config file /usr/local/etc/backup.conf, that has the following format:
DIR /www/domain1.com
DIR /www/domain2.com
DB domain1_wp_db
DB domain2_wp_db

(Substituting locations/db names appropriate for your environment of course). If you use a different config file than /usr/local/etc/backup.conf, be sure to change that line in the script. Also, you’ll need to change the mysql root password in the script to be whatever it is for your env (or make it non-root, whichever you want, it just needs to be able to do a mysqldump on the databases)

Next, set up your crontab to run nightly:

sudo crontab -e

Add the following line:

0 1 * * * /usr/local/bin/backup > /dev/null 2>&1

That should be it! Again, make sure to do some test restores to verify that it works ok! Here’s what a typical backup directory looks like after a couple of months running the script:

[ed@halo1:/backup/www_edsalisbury.net]$ ls -l
total 144240
-rw-r--r--  1 root root  5423759 Sep 11 01:00 www_edsalisbury.net_diff_daily_Fri.tar.gz
-rw-r--r--  1 root root  1839115 Sep  7 01:00 www_edsalisbury.net_diff_daily_Mon.tar.gz
-rw-r--r--  1 root root  5787136 Sep 12 01:00 www_edsalisbury.net_diff_daily_Sat.tar.gz
-rw-r--r--  1 root root  7193167 Sep 13 01:00 www_edsalisbury.net_diff_daily_Sun.tar.gz
-rw-r--r--  1 root root  3782727 Sep 10 01:00 www_edsalisbury.net_diff_daily_Thu.tar.gz
-rw-r--r--  1 root root  2455973 Sep  8 01:00 www_edsalisbury.net_diff_daily_Tue.tar.gz
-rw-r--r--  1 root root  3268897 Sep  9 01:00 www_edsalisbury.net_diff_daily_Wed.tar.gz
-rw-r--r--  1 root root 23705401 Aug  1 01:00 www_edsalisbury.net_full_monthly_20090801.tar.gz
-rw-r--r--  1 root root 33975458 Sep  1 01:00 www_edsalisbury.net_full_monthly_20090901.tar.gz
-rw-r--r--  1 root root 31453170 Sep  6 01:00 www_edsalisbury.net_full_weekly_20090906.tar.gz
-rw-r--r--  1 root root 28556424 Sep 13 01:00 www_edsalisbury.net_full_weekly_20090913.tar.gz

Not too bad, size-wise. For all of my sites, the backup directory is about 4 GB, and will stay around that size for quite a while. The differentials get deleted and so do the weekly full backups after the monthly full completes. This makes it so that the directory only really grows when there’s a new full monthly. If you find this script useful or have issues, be sure to post a comment!

The next thing is to set up the apache config file to be able to include a separate file just for vhosts. Add this section somewhere in your httpd.conf file:

# Virtual Hosts
NameVirtualHost *
Include etc/httpd-vhosts.conf

Now, create httpd-vhosts.conf in the apache config dir, and create a manual entry to make sure it works:

    ServerName      www.mydomain.com
    ServerAdmin     webmaster@mydomain.com
    ServerAlias     mydomain.com
    DocumentRoot    /www/mydomain.com/docs
    DirectoryIndex  index.html index.php
    AccessFileName  .htaccess
    HostnameLookups Off
    ErrorLog        /www/logs/mydomain.com/error.log
    LogLevel        warn
    CustomLog       /www/logs/mydomain.com/access.log combined

(Be sure to change “mydomain.com” to your domain)

Create /www/<domain.com> and log files, as well as change ownerships properly:

# mkdir /www/logs/<domain.com>
# mkdir /www/<domain.com>
# chmod g+w /www/<domain.com>
# chown nobody:nobody /www/<domain.com>
# chown nobody:nobody /www/logs/<domain.com>

Next, create some sort of test file (like index.html) in the new doc directory.

When you’re ready, restart the webserver (usually just by running apachectl graceful) With any luck, you should be seeing the webpage you created when you go do www.<domain.com>. If not, look at the apache config for errors, and verify that the DNS entries are correct.

Now, as you were expecting, I have a script to be able to automate this. It’s pretty simple, but handy. I call it “add_vhost” and I put it into /usr/local/bin:

#!/usr/bin/perl -w
# AddVhost
# Add Virtual Host Configs for Apache
# by Ed Salisbury (ed@edsalisbury.net)
# http://www.edsalisbury.net
# (c)2009 Ed Salisbury, Some Rights Reserved
#
# License:
# Except where otherwise noted, this work is licensed under Creative Commons
#   Attribution ShareAlike 3.0.
#
# You are free:
#   * to Share -- to copy, distribute and transmit the work
#   * to Remix -- to adapt the work
#
# Under the following conditions:
#   * Attribution. You must attribute the work in the manner specified by the
#     author or licensor (but not in any way that suggests that they endorse
#     you or your use of the work).
#   * Share Alike. If you alter, transform, or build upon this work, you may
#     distribute the resulting work only under the same, similar or a
#     compatible license.
#   * For any reuse or distribution, you must make clear to others the license
#     terms of this work. The best way to do this is with a link to the
#     license's web page (http://creativecommons.org/licenses/by-sa/3.0/)
#   * Any of the above conditions can be waived if you get permission from the
#     copyright holder.
#   * Nothing in this license impairs or restricts the author's moral rights.

use strict;

my $DOCROOT = '/www';
my $LOGDIR = '/www/logs';
my $USER = 'nobody';
my $GROUP = 'nobody';
my $VHOST_CFG = "/usr/local/apache2/etc/httpd-vhosts.conf";

my $domain = $ARGV[0];

if (!$domain)
{
    print "Error: No domain specified!\n";
    exit(1);
}
open (OUT, ">> $VHOST_CFG");
print OUT "\n";
print OUT "<VirtualHost *>\n";
print OUT "\tServerName      www.$domain\n";
print OUT "\tServerAdmin     webmaster\@$domain\n";
print OUT "\tServerAlias     $domain\n";
print OUT "\tDocumentRoot    $DOCROOT/$domain\n";
print OUT "\tDirectoryIndex  index.html index.php\n";
print OUT "\tAccessFileName  .htaccess\n";
print OUT "\tHostnameLookups Off\n";
print OUT "\tErrorLog        $LOGDIR/$domain/error.log\n";
print OUT "\tLogLevel        warn\n";
print OUT "\tCustomLog       $LOGDIR/$domain/access.log combined\n";
print OUT "</VirtualHost>\n";
close (OUT);

system("mkdir $LOGDIR/$domain");
system("mkdir $DOCROOT/$domain");
system("chmod g+w $DOCROOT/$domain");
system("chown $USER:$GROUP $DOCROOT/$domain");
system("chown $USER:$GROUP $LOGDIR/$domain");

Be sure to change the config variables to suit your environment. When you want to add a virtual host, simply run:

% sudo add_vhost domain.com

It will create the config and set everything up for you. All you need to do then is to restart the webserver, and you’re good to go!