diff options
-rwxr-xr-x | byteback-backup | 358 | ||||
-rwxr-xr-x | byteback-snapshot | 468 |
2 files changed, 413 insertions, 413 deletions
diff --git a/byteback-backup b/byteback-backup index ffc4186..430975e 100755 --- a/byteback-backup +++ b/byteback-backup @@ -1,179 +1,179 @@ -#!/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 'trollop' -require 'resolv' - -@sources = ["/"] -@exclude = ["/swap.file", "/var/backups/localhost"] - -def error(message) - STDERR.print "*** #{message}\n" - exit 1 -end - -def verbose(message) - print "#{message}\n" -end - -opts = Trollop::options do - - opt :destination, "Backup destination (i.e. user@host:/path)", - :type => :string - - opt :source, "Source paths", - :type => :strings - - opt :verbose, "Show rsync command and progress" - - opt :retry_number, "Number of retries on error", - :type => :integer, - :default => 3 - - opt :retry_delay, "Wait number of seconds between retries", - :type => :integer, - :default => 1800 - - opt :ssh_key, "SSH key for connection", - :type => :string, - :default => "/etc/byteback/key" -end - -@ssh_key = opts[:ssh_key] -@verbose = opts[:verbose] ? "--verbose" : nil -@sources = opts[:source] if opts[:source] -@destination = opts[:destination] -@retry_number = opts[:retry_number] -@retry_delay = opts[:retry_delay] - -if !@destination && File.exists?("/etc/byteback/destination") - @destination = File.read("/etc/byteback/destination").chomp -end -error("Must suply --destination or put it into /etc/bytebackup/destination") unless @destination - -_dummy, @destination_user, @destination_host, colon, @destination_path = - /^(.*)?(?:@)([^:]+)(:)(.*)?$/.match(@destination).to_a - -error("Must be a remote path") unless colon - -# Validate & normalise source directories -# -error("No sources specified") if @sources.empty? -@sources = @sources.map do |s| - s = s.gsub(/\/+/,"/") - error("Can't read directory #{s}") unless File.readable?(s) - s -end - -# Guess destination for backup -# -if !@destination - guesses = [] - hostname = `hostname -f` - Resolv::DNS.open do |dns| - suffix = hostname.split(".")[2..-1].join(".") - ["byteback." + suffix].each do |name| - [Resolv::DNS::Resource::IN::AAAA, - Resolv::DNS::Resource::IN::A].each do |record_type| - next if !guesses.empty? # only care about first result - guesses += dns.getresources(name, record_type) - end - end - end - - if guesses.empty? - error "Couldn't guess at backup host, please specify --destination" - end - - # ick, do I really have to do this to get a string represnetion of - # the IP address? - # - guess = guesses.first.inspect - match = / (.*)>$/.match(guess)[1] - error "Result #{guesses} is not an IP" if !match - @destination = "byteback@#{match[1]}:#{HOSTNAME}/current/" - - verbose "Guessed destination=#{@destination} from #{guess}" -end - -# Test ssh connection is good before we start -# -error("Could not read ssh key #{@ssh_key}") unless File.readable?(@ssh_key) - -def ssh(*args) - ["ssh", - "-o", "BatchMode=yes", - "-x", "-a", - "-i", @ssh_key, - "-l", @destination_user - ] + - args -end - -error("Could not connect to #{@destination}") unless - system(*ssh("byteback-receive", "--ping", @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 = [ - "rsync", - "--archive", - "--numeric-ids", - "--delete", - "--inplace", - "--rsync-path", - "rsync --fake-super", - "--rsh", - ssh.join(" "), - "--delete", - "--one-file-system", - "--relative" - ] - - args << "--verbose" if @verbose - args += @exclude.map { |x| ["--exclude", x] }.flatten - args += sources - args << @destination - - print args.map { |a| / /.match(a) ? "\"#{a}\"" : a }.join(" ")+"\n" if @verbose - system(*args) - - return $?.exitstatus -end - -RSYNC_EXIT_STATUSES_TO_RETRY_ON = [10,11,20,21,22,23,24,30] - -# Run the file copy, retrying if necessary -# -loop do - status = rsync(*@sources) - - if status === 0 - break - elsif RSYNC_EXIT_STATUSES_TO_RETRY_ON.include?(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 - system(*ssh("sudo", "byteback-snapshot", "--snapshot", @verbose)) +#!/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 'trollop'
+require 'resolv'
+
+@sources = ["/"]
+@exclude = ["/swap.file", "/var/backups/localhost"]
+
+def error(message)
+ STDERR.print "*** #{message}\n"
+ exit 1
+end
+
+def verbose(message)
+ print "#{message}\n"
+end
+
+opts = Trollop::options do
+
+ opt :destination, "Backup destination (i.e. user@host:/path)",
+ :type => :string
+
+ opt :source, "Source paths",
+ :type => :strings
+
+ opt :verbose, "Show rsync command and progress"
+
+ opt :retry_number, "Number of retries on error",
+ :type => :integer,
+ :default => 3
+
+ opt :retry_delay, "Wait number of seconds between retries",
+ :type => :integer,
+ :default => 1800
+
+ opt :ssh_key, "SSH key for connection",
+ :type => :string,
+ :default => "/etc/byteback/key"
+end
+
+@ssh_key = opts[:ssh_key]
+@verbose = opts[:verbose] ? "--verbose" : nil
+@sources = opts[:source] if opts[:source]
+@destination = opts[:destination]
+@retry_number = opts[:retry_number]
+@retry_delay = opts[:retry_delay]
+
+if !@destination && File.exists?("/etc/byteback/destination")
+ @destination = File.read("/etc/byteback/destination").chomp
+end
+error("Must suply --destination or put it into /etc/bytebackup/destination") unless @destination
+
+_dummy, @destination_user, @destination_host, colon, @destination_path =
+ /^(.*)?(?:@)([^:]+)(:)(.*)?$/.match(@destination).to_a
+
+error("Must be a remote path") unless colon
+
+# Validate & normalise source directories
+#
+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
+
+# Guess destination for backup
+#
+if !@destination
+ guesses = []
+ hostname = `hostname -f`
+ Resolv::DNS.open do |dns|
+ suffix = hostname.split(".")[2..-1].join(".")
+ ["byteback." + suffix].each do |name|
+ [Resolv::DNS::Resource::IN::AAAA,
+ Resolv::DNS::Resource::IN::A].each do |record_type|
+ next if !guesses.empty? # only care about first result
+ guesses += dns.getresources(name, record_type)
+ end
+ end
+ end
+
+ if guesses.empty?
+ error "Couldn't guess at backup host, please specify --destination"
+ end
+
+ # ick, do I really have to do this to get a string represnetion of
+ # the IP address?
+ #
+ guess = guesses.first.inspect
+ match = / (.*)>$/.match(guess)[1]
+ error "Result #{guesses} is not an IP" if !match
+ @destination = "byteback@#{match[1]}:#{HOSTNAME}/current/"
+
+ verbose "Guessed destination=#{@destination} from #{guess}"
+end
+
+# Test ssh connection is good before we start
+#
+error("Could not read ssh key #{@ssh_key}") unless File.readable?(@ssh_key)
+
+def ssh(*args)
+ ["ssh",
+ "-o", "BatchMode=yes",
+ "-x", "-a",
+ "-i", @ssh_key,
+ "-l", @destination_user
+ ] +
+ args
+end
+
+error("Could not connect to #{@destination}") unless
+ system(*ssh("byteback-receive", "--ping", @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 = [
+ "rsync",
+ "--archive",
+ "--numeric-ids",
+ "--delete",
+ "--inplace",
+ "--rsync-path",
+ "rsync --fake-super",
+ "--rsh",
+ ssh.join(" "),
+ "--delete",
+ "--one-file-system",
+ "--relative"
+ ]
+
+ args << "--verbose" if @verbose
+ args += @exclude.map { |x| ["--exclude", x] }.flatten
+ args += sources
+ args << @destination
+
+ print args.map { |a| / /.match(a) ? "\"#{a}\"" : a }.join(" ")+"\n" if @verbose
+ system(*args)
+
+ return $?.exitstatus
+end
+
+RSYNC_EXIT_STATUSES_TO_RETRY_ON = [10,11,20,21,22,23,24,30]
+
+# Run the file copy, retrying if necessary
+#
+loop do
+ status = rsync(*@sources)
+
+ if status === 0
+ break
+ elsif RSYNC_EXIT_STATUSES_TO_RETRY_ON.include?(status)
+ if @retry_number > 0
+ @retry_number -= 1
+ sleep @retry_delay
+ redo
+ else
+ error("Maximum number of rsync retries reached")
+ end
+ else
+ error("Fatal rsync error occurred (#{status})")
+ end
+end
+
+# Mark the backup as done on the other end
+#
+error("Backup could not be marked complete") unless
+ system(*ssh("sudo", "byteback-snapshot", "--snapshot", @verbose))
diff --git a/byteback-snapshot b/byteback-snapshot index daf368b..4e1be92 100755 --- a/byteback-snapshot +++ b/byteback-snapshot @@ -1,234 +1,234 @@ -#!/usr/bin/ruby -# -# Program to create a snapshot and/or rotate a directory of backup snapshots -# using btrfs subvolume commands. - -require 'trollop' -require 'time' - -def error(message) - STDERR.print "*** #{message}\n" - exit 1 -end - -def verbose(message) - print "#{Time.now}: #{message}\n" if @verbose -end - -# Icky way to find out free disc space on our mount -# -class DiskFree - def initialize(mount) - @mount = mount - end - - def total - all[2] - end - - def used - all[3] - end - - def available - all[4] - end - - def fraction_used - disk_device, disk_fs, disk_total, disk_used, disk_available, *rest = all - disk_used.to_f / disk_available - end - - protected - - def all - disk_device, disk_fs, disk_total, disk_used, disk_available, *rest = - df. - split("\n")[1]. - split(/\s+/). - map { |i| /^[0-9]+$/.match(i) ? i.to_i : i } - end - - def df - `/bin/df -T -P -B1 #{@mount}` - end -end - -# Represent a directory full of backups where "current" is a subvolume -# which is snapshotted to frozen backup directories called e.g. -# "yyyy-mm-ddThh:mm". -# -class BackupDirectory - attr_reader :dir - - def initialize(dir) - @dir = Dir.new(dir) - current - end - - # Return total amount of free space in backup directory (bytes) - # - def free - df = DiskFree.new(@dir.path) - df.total - df.used - end - - # Return an array of Times representing the current list of - # snapshots. - # - def snapshot_times - @dir.entries.map do |entry| - begin - Time.parse(entry) - rescue ArgumentError => error - nil - end - end. - compact. - sort - end - - # What order to remove snapshots in to regain disk space? - # - # Order backups by their closeness to defined backup times, which are - # listed in a set order (i.e. today's backup is more important than yesterday's). - # - BACKUP_IMPORTANCE = [0, 1, 2, 3, 7, 14, 21, 28, 56, 112] - def snapshot_times_by_importance - now = Time.now - snapshot_times_unsorted = snapshot_times - snapshot_times_sorted = [] - while !snapshot_times_unsorted.empty? - BACKUP_IMPORTANCE.each do |days| - target_time = now + (days*86400) - closest = snapshot_times_unsorted.inject(nil) do |best, time| - if best.nil? || (time-target_time).abs < (best-target_time).abs - time - else - best - end - end - break unless closest - snapshot_times_sorted << snapshot_times_unsorted.delete(closest) - end - end - snapshot_times_sorted - end - - # Returns the size of the given snapshot (runs du, may be slow) - # - # Would much prefer to take advantage of this feature: - # http://dustymabe.com/2013/09/22/btrfs-how-big-are-my-snapshots/ - # but it's not currently in Debian/wheezy. - # - def snapshot_size(time=snapshot_times.latest) - `du -s -b #{snapshot_path(time)}`.to_i - end - - def average_snapshot_size(number=10) - snapshot_times.sort[0..number].inject(0) { |time, total| snapshot_size(time) } / number - end - - # Create a new snapshot of 'current' - # - def new_snapshot! - system_no_error("btrfs subvolume snapshot -r #{current.path} #{snapshot_path}") - end - - def delete_snapshot!(time) - system_no_error("btrfs subvolume delete #{snapshot_path(time)}") - end - - def current - Dir.new("#{dir.path}/current") - end - - def snapshot_path(time=Time.now) - "#{dir.path}/#{time.strftime("%Y-%m-%dT%H:%M")}" - end - - protected - - def system_no_error(*args) - raise RuntimeError.new("Command failed: "+args.join(" ")) unless - system(*args) - end -end - -opts = Trollop::options do - - opt :root, "Backups directory (must be a btrfs subvolume)", - :type => :string - - opt :snapshot, "Take a new snapshot" - - opt :prune, "Prune old backups" - :type => :string - - opt :list, "List backups (by 'age' or 'importance')", - :type => :string - - opt :verbose, "Print diagnostics" - -end - -@root = opts[:root] -@verbose = opts[:verbose] -@do_snapshot = opts[:snapshot] -@do_list = opts[:list] -@do_prune = opts[:prune] - -error("Must specify snapshot, prune or list") unless @do_snapshot || @do_prune || @do_list - -error("--root not readable") unless File.directory?(@root) - -@backups = BackupDirectory.new(@root) - -def get_snapshots_by(method) - if method == 'importance' - @backups.snapshot_times_by_importance.reverse # least important first - elsif method == 'age' - @backups.snapshot_times - else - raise ArgumentError.new("Unknown snapshot sort method #{method}") - end -end - -if @do_snapshot - last_snapshot_time = @backups.snapshots.last - error("Last snapshot was less than six hours ago") unless - !last_snapshot_time || - Time.now - @backups.snapshots.last >= 6*60*60 # FIXME: make configurable - - verbose "Making new snapshot" - @backups.new_snapshot! -end - -if @do_list - list = get_snapshots_by(@do_list) - print "Backups in #{@root} by #{@do_list}:\n" - list.each_with_index do |time, index| - print "#{sprintf('% 3d',index)}: #{time}\n" - end -end - -if @do_prune - verbose "Counting last 10 backups" - target_free_space = 1.5 * @backups.average_snapshot_size(10) - verbose "Want to ensure we have #{target_free_space}" - - if @backups.free >= target_free_space - verbose "(we have #{@backups.free} so no action needed)" - else - list = get_snapshots_by(@do_prune) - - while @backups.free < target_free_space && !list.empty? - to_delete = list.pop - verbose "Deleting #{to_delete}" - @backups.delete_snapshot!(to_delete) - verbose "Leaves us with #{@backups.free}" - end - end -end - -verbose "Finished" +#!/usr/bin/ruby
+#
+# Program to create a snapshot and/or rotate a directory of backup snapshots
+# using btrfs subvolume commands.
+
+require 'trollop'
+require 'time'
+
+def error(message)
+ STDERR.print "*** #{message}\n"
+ exit 1
+end
+
+def verbose(message)
+ print "#{Time.now}: #{message}\n" if @verbose
+end
+
+# Icky way to find out free disc space on our mount
+#
+class DiskFree
+ def initialize(mount)
+ @mount = mount
+ end
+
+ def total
+ all[2]
+ end
+
+ def used
+ all[3]
+ end
+
+ def available
+ all[4]
+ end
+
+ def fraction_used
+ disk_device, disk_fs, disk_total, disk_used, disk_available, *rest = all
+ disk_used.to_f / disk_available
+ end
+
+ protected
+
+ def all
+ disk_device, disk_fs, disk_total, disk_used, disk_available, *rest =
+ df.
+ split("\n")[1].
+ split(/\s+/).
+ map { |i| /^[0-9]+$/.match(i) ? i.to_i : i }
+ end
+
+ def df
+ `/bin/df -T -P -B1 #{@mount}`
+ end
+end
+
+# Represent a directory full of backups where "current" is a subvolume
+# which is snapshotted to frozen backup directories called e.g.
+# "yyyy-mm-ddThh:mm".
+#
+class BackupDirectory
+ attr_reader :dir
+
+ def initialize(dir)
+ @dir = Dir.new(dir)
+ current
+ end
+
+ # Return total amount of free space in backup directory (bytes)
+ #
+ def free
+ df = DiskFree.new(@dir.path)
+ df.total - df.used
+ end
+
+ # Return an array of Times representing the current list of
+ # snapshots.
+ #
+ def snapshot_times
+ @dir.entries.map do |entry|
+ begin
+ Time.parse(entry)
+ rescue ArgumentError => error
+ nil
+ end
+ end.
+ compact.
+ sort
+ end
+
+ # What order to remove snapshots in to regain disk space?
+ #
+ # Order backups by their closeness to defined backup times, which are
+ # listed in a set order (i.e. today's backup is more important than yesterday's).
+ #
+ BACKUP_IMPORTANCE = [0, 1, 2, 3, 7, 14, 21, 28, 56, 112]
+ def snapshot_times_by_importance
+ now = Time.now
+ snapshot_times_unsorted = snapshot_times
+ snapshot_times_sorted = []
+ while !snapshot_times_unsorted.empty?
+ BACKUP_IMPORTANCE.each do |days|
+ target_time = now + (days*86400)
+ closest = snapshot_times_unsorted.inject(nil) do |best, time|
+ if best.nil? || (time-target_time).abs < (best-target_time).abs
+ time
+ else
+ best
+ end
+ end
+ break unless closest
+ snapshot_times_sorted << snapshot_times_unsorted.delete(closest)
+ end
+ end
+ snapshot_times_sorted
+ end
+
+ # Returns the size of the given snapshot (runs du, may be slow)
+ #
+ # Would much prefer to take advantage of this feature:
+ # http://dustymabe.com/2013/09/22/btrfs-how-big-are-my-snapshots/
+ # but it's not currently in Debian/wheezy.
+ #
+ def snapshot_size(time=snapshot_times.latest)
+ `du -s -b #{snapshot_path(time)}`.to_i
+ end
+
+ def average_snapshot_size(number=10)
+ snapshot_times.sort[0..number].inject(0) { |time, total| snapshot_size(time) } / number
+ end
+
+ # Create a new snapshot of 'current'
+ #
+ def new_snapshot!
+ system_no_error("btrfs subvolume snapshot -r #{current.path} #{snapshot_path}")
+ end
+
+ def delete_snapshot!(time)
+ system_no_error("btrfs subvolume delete #{snapshot_path(time)}")
+ end
+
+ def current
+ Dir.new("#{dir.path}/current")
+ end
+
+ def snapshot_path(time=Time.now)
+ "#{dir.path}/#{time.strftime("%Y-%m-%dT%H:%M")}"
+ end
+
+ protected
+
+ def system_no_error(*args)
+ raise RuntimeError.new("Command failed: "+args.join(" ")) unless
+ system(*args)
+ end
+end
+
+opts = Trollop::options do
+
+ opt :root, "Backups directory (must be a btrfs subvolume)",
+ :type => :string
+
+ opt :snapshot, "Take a new snapshot"
+
+ opt :prune, "Prune old backups"
+ :type => :string
+
+ opt :list, "List backups (by 'age' or 'importance')",
+ :type => :string
+
+ opt :verbose, "Print diagnostics"
+
+end
+
+@root = opts[:root]
+@verbose = opts[:verbose]
+@do_snapshot = opts[:snapshot]
+@do_list = opts[:list]
+@do_prune = opts[:prune]
+
+error("Must specify snapshot, prune or list") unless @do_snapshot || @do_prune || @do_list
+
+error("--root not readable") unless File.directory?(@root)
+
+@backups = BackupDirectory.new(@root)
+
+def get_snapshots_by(method)
+ if method == 'importance'
+ @backups.snapshot_times_by_importance.reverse # least important first
+ elsif method == 'age'
+ @backups.snapshot_times
+ else
+ raise ArgumentError.new("Unknown snapshot sort method #{method}")
+ end
+end
+
+if @do_snapshot
+ last_snapshot_time = @backups.snapshots.last
+ error("Last snapshot was less than six hours ago") unless
+ !last_snapshot_time ||
+ Time.now - @backups.snapshots.last >= 6*60*60 # FIXME: make configurable
+
+ verbose "Making new snapshot"
+ @backups.new_snapshot!
+end
+
+if @do_list
+ list = get_snapshots_by(@do_list)
+ print "Backups in #{@root} by #{@do_list}:\n"
+ list.each_with_index do |time, index|
+ print "#{sprintf('% 3d',index)}: #{time}\n"
+ end
+end
+
+if @do_prune
+ verbose "Counting last 10 backups"
+ target_free_space = 1.5 * @backups.average_snapshot_size(10)
+ verbose "Want to ensure we have #{target_free_space}"
+
+ if @backups.free >= target_free_space
+ verbose "(we have #{@backups.free} so no action needed)"
+ else
+ list = get_snapshots_by(@do_prune)
+
+ while @backups.free < target_free_space && !list.empty?
+ to_delete = list.pop
+ verbose "Deleting #{to_delete}"
+ @backups.delete_snapshot!(to_delete)
+ verbose "Leaves us with #{@backups.free}"
+ end
+ end
+end
+
+verbose "Finished"
|