path: root/byteback-backup

#!/usr/bin/ruby
#
# Back up this system to a byteback-enabled server (just some command line
# tools and SSH setup).  We aim to make sure this backups are easy, complete
# and safe for most types of hosting customer.
#
# See 'man byteback' for more information.

require 'getoptlong'
require 'resolv'

def remove_lockfile!
  begin
    File.unlink(@lockfile)
  rescue Errno::ENOENT
  end
end

def error(message)
  STDERR.print "*** #{message}\n"
  exit 1
end

def verbose(message)
  print "#{message}\n"
end

def help
  puts <<EOF
#{$0}: Back up this system to a byteback-enabled server

Options:
   --destination, -d <s>:   Backup destination (i.e. user@host:/path)
       --source, -s  <s>:   Source paths (default: /)
       --exclude, -x <s>:   Exclude paths (defaults: /swap.file, /var/backups/localhost, /var/cache/apt/archives, /var/lib/php5, /tmp, /var/tmp)
           --verbose, -v:   Show rsync command and progress
  --retry-number, -r <n>:   Number of retries on error (default: 3)
   --retry-delay, -e <n>:   Wait number of seconds between retries (default: 1800)
       --ssh-key, -k <s>:   SSH key for connection (default: /etc/byteback/key)
              --help, -h:   Show this message

Additional excludes can be specified using /etc/byteback/rsync_filter, which is
an rsync filter file.  See the rsync man page for information on how this
works.

EOF
  remove_lockfile!
  exit 0
end

opts = GetoptLong.new(
  [ '--help',       '-h', GetoptLong::NO_ARGUMENT ],
  [ '--verbose',    '-v', GetoptLong::NO_ARGUMENT ],
  [ '--source',     '-s', GetoptLong::REQUIRED_ARGUMENT ],
  [ '--destination',   '-d', GetoptLong::REQUIRED_ARGUMENT ],
  [ '--retry-number',  '-r', GetoptLong::REQUIRED_ARGUMENT ],
  [ '--retry-delay',   '-e', GetoptLong::REQUIRED_ARGUMENT ],
  [ '--ssh-key'       ,'-k', GetoptLong::REQUIRED_ARGUMENT ]
)

@ssh_key = nil
@destination = nil
@retry_number = 3
@retry_delay = 1800
@sources = nil
@excludes = nil
@lockfile = "/var/run/byteback/byteback.lock"


# Read the default destination
if File.exists?("/etc/byteback/destination")
  @destination = File.read("/etc/byteback/destination").chomp
end

# Set the default SSH key
if File.exists?("/etc/byteback/key")
  @ssh_key = "/etc/byteback/key"
end

begin
  opts.each do |opt,arg|
    case opt
    when '--help'
      help = true
    when '--verbose'
      $VERBOSE = true
    when "--source"
      @sources ||= []
      @sources << arg
    when "--exclude"
      @excludes ||= []
      @excludes << arg
    when "--destination"
      @destination = arg
    when "--retry-number"
      @retry_number = arg.to_i
    when "--retry-delay"
      @retry_delay = arg.to_i
    when "--ssh-key"
      @ssh_key = arg
    end
  end
rescue => err
  # any errors, show the help
  warn err.to_s
  help = true
end

# Check the lockfile first
if File.directory?(File.dirname(@lockfile))
  if File.exists? @lockfile
    # check the lockfile is sane
    exist_pid = File.read(@lockfile).to_i
    if exist_pid > 1 and exist_pid < (File.read("/proc/sys/kernel/pid_max").to_i)
      begin
        Process.getpgid(exist_pid)
        # if no exception, process is running, abort
        error("Process is running (#{exist_pid} from #{@lockfile})! Exiting now.")
      rescue Errno::ESRCH
        # no process running with that pid, pidfile is stale
        remove_lockfile!
      end
    else
      # lockfile isn't sane, remove it and continue
      remove_lockfile!
    end
  end
else
  Dir.mkdir(File.dirname(@lockfile))
  # lockfile didn't exist so just carry on
end

# Own the pidfile ourselves
File.open(@lockfile, "w") do |lockfile|
  lockfile.puts Process::pid
end

#
# Check our destination
#
if @destination =~ /^(?:(.+)@)?([^@:]+):(.+)?$/
  @destination_user, @destination_host, @destination_path = [$1, $2, $3]
else
  error("Destination must be a remote path, e.g. ssh@host.com:/store/backups")
end

#
# Validate & normalise source directories
#
@sources = ["/"] if @sources.nil?

error("No sources specified") if @sources.empty?

@sources = @sources.map do |s|
  s = s.gsub(/\/+/,"/")
  error("Can't read directory #{s}") unless File.readable?(s)
  s
end

#
# Validate and normalise excludes
#
if @excludes.nil?
  @excludes = %w(
     /swap.file
     /tmp
     /var/backups/localhost
     /var/cache/apt/archives
     /var/lib/php5
     /var/tmp
  ).select do |x|
    File.exists?(x)
  end
end


#
# Always add these filesystems
#
@excludes += %w(/dev /proc /run /sys)

@excludes = @excludes.map do |e|
  e.gsub(/\/+/,"/")
end

error("Must suply --destination or put it into /etc/bytebackup/destination") unless @destination

#
# Test ssh connection is good before we start
#
error("Could not read ssh key #{@ssh_key}") unless File.readable?(@ssh_key)

def ssh(*ssh_args)
  args = ["ssh",
    "-o", "BatchMode=yes",
    "-x", "-a",
    "-i", @ssh_key,
    "-l", @destination_user,
    @destination_host
  ] +
  ssh_args.
  map { |a| a ? a : "" }

  print args.map { |a| / /.match(a) ? "\"#{a}\"" : a }.join(" ")+"\n" if $VERBOSE

  system(*args)
end

error("Could not connect to #{@destination}") unless
  ssh("byteback-receive", "--ping", ($VERBOSE ? "--verbose" : "" ))

#
# Call rsync to copy certain sources, returns exit status (see man rsync)
#
def rsync(*sources)
  # Default options include --inplace because we only care about consistency
  # at the end of the job, and rsync will do more work for big files without
  # it.
  #
  args = %w(rsync --archive --numeric-ids --delete-delay --inplace --relative)
  args += [ "--rsync-path", "rsync --fake-super"]
  args += [ "--rsh", "ssh -o BatchMode=yes -x -a -i #{@ssh_key} -l #{@destination_user}"]
  args << "--verbose" if $VERBOSE
  args += @excludes.map { |x| ["--exclude", x] }.flatten

  #
  # Add in the rsync excludes and sources files, if present.
  #
  if File.exists?("/etc/byteback/excludes")
      args += ["--exclude-from", "/etc/byteback/excludes"]
  end

  #
  # Add in an rsync_filter if required.
  #
  if File.exists?("/etc/byteback/rsync_filter")
      args += ["--filter", "merge /etc/byteback/rsync_filter"]
  end

  args += sources
  args << @destination

  print args.map { |a| / /.match(a) ? "\"#{a}\"" : a }.join(" ")+"\n" if $VERBOSE

  system(*args)

  return $?.exitstatus
end

#
# We treat exit statuses 0 and 24 as success; 0 is "Success"; 24 is "Partial
# transfer due to vanished source files", which we treat as success otherwise
# on some hosts the backup process never finishes.
#
RSYNC_EXIT_STATUSES_TO_ACCEPT   = [0, 24]
RSYNC_EXIT_STATUSES_TO_RETRY_ON = [10,11,20,21,22,23,30]

# Run the file copy, retrying if necessary
#
loop do
  status = rsync(*@sources)

  if RSYNC_EXIT_STATUSES_TO_ACCEPT.any?{|s| s === status} 
    break
  elsif RSYNC_EXIT_STATUSES_TO_RETRY_ON.any?{|s| s === status}
    if @retry_number > 0
      @retry_number -= 1
      sleep @retry_delay
      redo
    else
      error("Maximum number of rsync retries reached")
    end
  else
    error("Fatal rsync error occurred (#{status})")
  end
end

# Mark the backup as done on the other end
#
error("Backup could not be marked complete") unless
  ssh("sudo", "byteback-snapshot", "--snapshot", ($VERBOSE ? "--verbose" : ""))

remove_lockfile!