429 lines
15 KiB
Python
Executable File
429 lines
15 KiB
Python
Executable File
#!/usr/bin/env python
|
|
# -*- coding: utf8 -*-
|
|
from __future__ import print_function
|
|
import os
|
|
import sys
|
|
import re
|
|
import traceback
|
|
import subprocess
|
|
import pprint
|
|
# import cStringIO
|
|
import time
|
|
|
|
class Log:
|
|
def __init__(self):
|
|
self.titles=[]
|
|
pass
|
|
|
|
def titled_str(self, txt, titles):
|
|
"""magic to make our log messages ident and more clear"""
|
|
str=""
|
|
count=0
|
|
for title in titles:
|
|
if len(self.titles)>count and self.titles[count]==title:
|
|
str=str+ ( " " * len(title))
|
|
else:
|
|
str=str+title
|
|
str=str+": "
|
|
count=count+1
|
|
|
|
str=str+txt
|
|
self.titles=titles
|
|
return(str)
|
|
|
|
def error(self, txt, titles=[]):
|
|
print(txt, file=sys.stderr)
|
|
|
|
def verbose(self, txt, titles=[]):
|
|
if args.verbose:
|
|
print(self.titled_str(txt, titles))
|
|
|
|
def debug(self, txt, titles=[]):
|
|
if args.debug:
|
|
print(txt)
|
|
|
|
|
|
log=Log()
|
|
|
|
#fatal abort execution, exit code 255
|
|
def abort(txt):
|
|
log.error(txt)
|
|
sys.exit(255)
|
|
|
|
|
|
class cached_property(object):
|
|
""" A property that is only computed once per instance and then replaces
|
|
itself with an ordinary attribute. Deleting the attribute resets the
|
|
property.
|
|
|
|
Source: https://github.com/bottlepy/bottle/commit/fa7733e075da0d790d809aa3d2f53071897e6f76
|
|
"""
|
|
|
|
def __init__(self, func):
|
|
self.__doc__ = getattr(func, '__doc__')
|
|
self.func = func
|
|
|
|
|
|
def __get__(self, obj, cls):
|
|
if obj is None:
|
|
return self
|
|
|
|
propname=self.func.__name__
|
|
|
|
#store directly in dict so its cached from now on
|
|
# value = obj.__dict__[propname] = self.func(obj)
|
|
if not hasattr(obj, '_cached_properties'):
|
|
obj._cached_properties={}
|
|
|
|
if not propname in obj._cached_properties:
|
|
obj._cached_properties[propname]=self.func(obj)
|
|
# value = obj.__dict__[propname] = self.func(obj)
|
|
|
|
return obj._cached_properties[propname]
|
|
|
|
|
|
|
|
|
|
class ExecuteNode:
|
|
"""an endpoint to execute local or remote commands via ssh"""
|
|
|
|
def __init__(self, ssh_to=None, readonly=False):
|
|
"""ssh_to: server you want to ssh to. none means local
|
|
readonly: only execute commands that dont make any changes (usefull for testing-runs)
|
|
"""
|
|
|
|
self.ssh_to=ssh_to
|
|
self.readonly=readonly
|
|
|
|
|
|
def run(self, cmd, input=None, tab_split=False, valid_exitcodes=[ 0 ], readonly=False):
|
|
"""run a command on the node
|
|
|
|
readonly: make this True if the command doesnt make any changes and is safe to execute in testmode
|
|
"""
|
|
|
|
encoded_cmd=[]
|
|
|
|
#use ssh?
|
|
if self.ssh_to != None:
|
|
encoded_cmd.extend(["ssh", self.ssh_to])
|
|
|
|
#make sure the command gets all the data in utf8 format:
|
|
#(this is neccesary if LC_ALL=en_US.utf8 is not set in the environment)
|
|
for arg in cmd:
|
|
#add single quotes for remote commands to support spaces and other wierd stuff (remote commands are executed in a shell)
|
|
encoded_cmd.append( ("'"+arg+"'").encode('utf-8'))
|
|
|
|
else:
|
|
for arg in cmd:
|
|
encoded_cmd.append(arg.encode('utf-8'))
|
|
|
|
#debug and test stuff
|
|
debug_txt="# "+" ".join(encoded_cmd)
|
|
|
|
if self.readonly and not readonly:
|
|
log.debug("[NOT EXECUTING (readonly mode)] "+debug_txt)
|
|
else:
|
|
log.debug(debug_txt)
|
|
|
|
if input:
|
|
log.debug("INPUT:\n"+input.rstrip())
|
|
stdin=subprocess.PIPE
|
|
else:
|
|
stdin=None
|
|
|
|
if self.readonly and not readonly:
|
|
return
|
|
|
|
#execute and parse/return results
|
|
p=subprocess.Popen(encoded_cmd, env=os.environ, stdout=subprocess.PIPE, stdin=stdin)
|
|
output=p.communicate(input=input)[0]
|
|
if p.returncode not in valid_exitcodes:
|
|
raise(subprocess.CalledProcessError(p.returncode, encoded_cmd))
|
|
|
|
lines=output.splitlines()
|
|
if not tab_split:
|
|
return(lines)
|
|
else:
|
|
ret=[]
|
|
for line in lines:
|
|
ret.append(line.split("\t"))
|
|
return(ret)
|
|
|
|
def __repr__(self):
|
|
return(self.ssh_to)
|
|
|
|
|
|
|
|
class ZfsDataset():
|
|
"""a zfs dataset (filesystem/volume/snapshot/clone)"""
|
|
|
|
def __init__(self, zfs_node, name):
|
|
"""name: full path of the zfs dataset"""
|
|
self.zfs_node=zfs_node
|
|
self.name=name
|
|
|
|
def __repr__(self):
|
|
return("{}: {}".format(self.zfs_node, self.name))
|
|
|
|
def __str__(self):
|
|
return(self.name)
|
|
|
|
def verbose(self,txt):
|
|
self.zfs_node.verbose(txt,[self.name])
|
|
|
|
def debug(self,txt):
|
|
self.zfs_node.debug(txt,[self.name])
|
|
|
|
|
|
def invalidate(self):
|
|
"""clear cache"""
|
|
#TODO: nicer
|
|
self._cached_properties={}
|
|
|
|
|
|
@property
|
|
def filesystem_name(self):
|
|
"""filesystem part of the name"""
|
|
(filesystem, snapshot_name)=self.name.split("@")
|
|
return(filesystem)
|
|
|
|
@property
|
|
def snapshot_name(self):
|
|
"""snapshot part of the name"""
|
|
(filesystem, snapshot_name)=self.name.split("@")
|
|
return(snapshot_name)
|
|
|
|
@cached_property
|
|
def properties(self):
|
|
"""all zfs properties"""
|
|
|
|
cmd=[
|
|
"zfs", "get", "all", "-H", "-o", "property,value", self.name
|
|
]
|
|
|
|
return(dict(self.zfs_node.run(tab_split=True, cmd=cmd, readonly=True, valid_exitcodes=[ 0 ])))
|
|
|
|
def is_changed(self):
|
|
"""dataset is changed since ANY latest snapshot ?"""
|
|
|
|
if self.properties['written']=="0B" or self.properties.written['written']=="0":
|
|
return(False)
|
|
else:
|
|
return(True)
|
|
|
|
def is_ours(self):
|
|
"""return true if this snapshot is created by this backup_nanme"""
|
|
if re.match("^"+self.zfs_node.backup_name+"-[0-9]*$", self.snapshot_name):
|
|
return(True)
|
|
else:
|
|
return(False)
|
|
|
|
def from_names(self, names):
|
|
"""convert a list of names to a list ZfsDatasets for this zfs_node"""
|
|
ret=[]
|
|
for name in names:
|
|
ret.append(ZfsDataset(self.zfs_node, name))
|
|
|
|
return(ret)
|
|
|
|
@cached_property
|
|
def snapshots(self):
|
|
"""get all snaphots of this dataset"""
|
|
|
|
cmd=[
|
|
"zfs", "list", "-d", "1", "-r", "-t" ,"snapshot", "-H", "-o", "name", self.name
|
|
]
|
|
|
|
names=self.zfs_node.run(cmd=cmd, readonly=True)
|
|
return(self.from_names(names))
|
|
|
|
@cached_property
|
|
def our_snapshots(self):
|
|
"""get list of snapshots creates by us of this dataset"""
|
|
ret=[]
|
|
for snapshot in self.snapshots:
|
|
if snapshot.is_ours():
|
|
ret.append(snapshot)
|
|
|
|
return(ret)
|
|
|
|
@cached_property
|
|
def is_changed_ours(self):
|
|
"""dataset is changed since OUR latest snapshot?"""
|
|
|
|
if not self.our_snapshots:
|
|
return(True)
|
|
|
|
latest_snapshot=self.snapshots[-1]
|
|
|
|
cmd=[ "zfs", "get","-H" ,"-ovalue", "written@"+str(latest_snapshot), self.name ]
|
|
output=self.zfs_node.run(readonly=True, tab_split=False, cmd=cmd, valid_exitcodes=[ 0 ])
|
|
if output[0]=="0B" or output[0]=="0":
|
|
return(False)
|
|
|
|
return(True)
|
|
|
|
@cached_property
|
|
def recursive_datasets(self, types="filesystem,volume"):
|
|
"""get all datasets recursively under us"""
|
|
|
|
names=self.zfs_node.run(tab_split=False, readonly=True, valid_exitcodes=[ 0 ], cmd=[
|
|
"zfs", "list", "-r", "-t", types, "-o", "name", "-H", self.name
|
|
])
|
|
|
|
return(self.from_names(names[1:]))
|
|
|
|
|
|
class ZfsNode(ExecuteNode):
|
|
"""a node that contains zfs datasets. implements global lowlevel zfs commands"""
|
|
|
|
def __init__(self, backup_name, ssh_to=None, readonly=False, description=""):
|
|
self.backup_name=backup_name
|
|
if not description:
|
|
self.description=ssh_to
|
|
|
|
ExecuteNode.__init__(self, ssh_to=ssh_to, readonly=readonly)
|
|
|
|
def verbose(self,txt,titles=[]):
|
|
titles.insert(0,self.description)
|
|
log.verbose(txt, titles)
|
|
|
|
def debug(self,txt, titles=[]):
|
|
titles.insert(0,self.description)
|
|
log.debug(txt, titles)
|
|
|
|
def new_snapshotname(self):
|
|
"""determine uniq new snapshotname"""
|
|
return(self.backup_name+"-"+time.strftime("%Y%m%d%H%M%S"))
|
|
|
|
|
|
def consistent_snapshot(self, datasets, snapshot_name, allow_empty=True):
|
|
"""create a consistent (atomic) snapshot of specified datasets.
|
|
|
|
allow_empty: Allow empty snapshots. (compared to our latest snapshot)
|
|
"""
|
|
|
|
cmd=[ "zfs", "snapshot" ]
|
|
|
|
noop=True
|
|
for dataset in datasets:
|
|
if not allow_empty:
|
|
if not dataset.is_changed_ours:
|
|
dataset.verbose("No changes, not snapshotting")
|
|
continue
|
|
|
|
cmd.append(str(dataset)+"@"+snapshot_name)
|
|
dataset.invalidate()
|
|
noop=False
|
|
|
|
if noop:
|
|
self.verbose("No changes, not creating snapshot.")
|
|
else:
|
|
self.verbose("Creating snapshot {}".format(snapshot_name))
|
|
self.run(cmd, readonly=False)
|
|
|
|
|
|
@cached_property
|
|
def selected_datasets(self):
|
|
"""determine filesystems that should be backupped by looking at the special autobackup-property, systemwide
|
|
|
|
returns: list of ZfsDataset
|
|
"""
|
|
#get all source filesystems that have the backup property
|
|
lines=self.run(tab_split=True, readonly=True, cmd=[
|
|
"zfs", "get", "-t", "volume,filesystem", "-o", "name,value,source", "-s", "local,inherited", "-H", "autobackup:"+self.backup_name
|
|
])
|
|
|
|
#determine filesystems that should be actually backupped
|
|
selected_filesystems=[]
|
|
direct_filesystems=[]
|
|
for line in lines:
|
|
(name,value,source)=line
|
|
dataset=ZfsDataset(self, name)
|
|
|
|
if value=="false":
|
|
dataset.verbose("Ignored (disabled)")
|
|
|
|
else:
|
|
if source=="local" and ( value=="true" or value=="child"):
|
|
direct_filesystems.append(name)
|
|
|
|
if source=="local" and value=="true":
|
|
selected_filesystems.append(dataset)
|
|
dataset.verbose("Selected (direct selection)")
|
|
elif source.find("inherited from ")==0 and (value=="true" or value=="child"):
|
|
inherited_from=re.sub("^inherited from ", "", source)
|
|
if inherited_from in direct_filesystems:
|
|
selected_filesystems.append(dataset)
|
|
dataset.verbose("Selected (inherited selection)")
|
|
else:
|
|
dataset.verbose("Ignored (already a backup)")
|
|
else:
|
|
dataset.verbose("Ignored (only childs)")
|
|
|
|
return(selected_filesystems)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
################################################################## ENTRY POINT
|
|
|
|
# parse arguments
|
|
import argparse
|
|
parser = argparse.ArgumentParser(
|
|
description='ZFS autobackup v2.4',
|
|
epilog='When a filesystem fails, zfs_backup will continue and report the number of failures at that end. Also the exit code will indicate the number of failures.')
|
|
parser.add_argument('--ssh-source', default=None, help='Source host to get backup from. (user@hostname) Default %(default)s.')
|
|
parser.add_argument('--ssh-target', default=None, help='Target host to push backup to. (user@hostname) Default %(default)s.')
|
|
parser.add_argument('--keep-source', type=int, default=30, help='Number of days to keep old snapshots on source. Default %(default)s.')
|
|
parser.add_argument('--keep-target', type=int, default=30, help='Number of days to keep old snapshots on target. Default %(default)s.')
|
|
parser.add_argument('backup_name', help='Name of the backup (you should set the zfs property "autobackup:backup-name" to true on filesystems you want to backup')
|
|
parser.add_argument('target_path', help='Target ZFS filesystem')
|
|
|
|
parser.add_argument('--no-snapshot', action='store_true', help='dont create new snapshot (usefull for finishing uncompleted backups, or cleanups)')
|
|
parser.add_argument('--no-send', action='store_true', help='dont send snapshots (usefull to only do a cleanup)')
|
|
parser.add_argument('--allow-empty', action='store_true', help='if nothing has changed, still create empty snapshots.')
|
|
parser.add_argument('--ignore-replicated', action='store_true', help='Ignore datasets that seem to be replicated some other way. (No changes since lastest snapshot. Usefull for proxmox HA replication)')
|
|
parser.add_argument('--no-holds', action='store_true', help='Dont lock snapshots on the source. (Usefull to allow proxmox HA replication to switches nodes)')
|
|
parser.add_argument('--ignore-new', action='store_true', help='Ignore filesystem if there are already newer snapshots for it on the target (use with caution)')
|
|
|
|
parser.add_argument('--resume', action='store_true', help='support resuming of interrupted transfers by using the zfs extensible_dataset feature (both zpools should have it enabled) Disadvantage is that you need to use zfs recv -A if another snapshot is created on the target during a receive. Otherwise it will keep failing.')
|
|
parser.add_argument('--strip-path', default=0, type=int, help='number of directory to strip from path (use 1 when cloning zones between 2 SmartOS machines)')
|
|
parser.add_argument('--buffer', default="", help='Use mbuffer with specified size to speedup zfs transfer. (e.g. --buffer 1G) Will also show nice progress output.')
|
|
|
|
|
|
# parser.add_argument('--destroy-stale', action='store_true', help='Destroy stale backups that have no more snapshots. Be sure to verify the output before using this! ')
|
|
parser.add_argument('--properties', default=None, help='Comma seperated list of zfs properties that should be synced to target. (Quotas are always disabled temporarily)')
|
|
parser.add_argument('--rollback', action='store_true', help='Rollback changes on the target before starting a backup. (normally you can prevent changes by setting the readonly property on the target_path to on)')
|
|
parser.add_argument('--ignore-transfer-errors', action='store_true', help='Ignore transfer errors (still checks if received filesystem exists. usefull for acltype errors)')
|
|
|
|
|
|
parser.add_argument('--test', action='store_true', help='dont change anything, just show what would be done (still does all read-only operations)')
|
|
parser.add_argument('--verbose', action='store_true', help='verbose output')
|
|
parser.add_argument('--debug', action='store_true', help='debug output (shows commands that are executed)')
|
|
|
|
#note args is the only global variable we use, since its a global readonly setting anyway
|
|
args = parser.parse_args()
|
|
|
|
|
|
source_node=ZfsNode(args.backup_name, ssh_to=args.ssh_source, readonly=args.test)
|
|
target_node=ZfsNode(args.backup_name, ssh_to=args.ssh_target, readonly=args.test)
|
|
|
|
|
|
source_datasets=source_node.selected_datasets
|
|
|
|
if not source_datasets:
|
|
abort("No source filesystems selected, please do a 'zfs set autobackup:{0}=true' on {1}".format(args.backup_name,args.ssh_source))
|
|
|
|
source_node.consistent_snapshot(source_datasets, source_node.new_snapshotname(), allow_empty=args.allow_empty)
|
|
|
|
# for source_dataset in source_datasets:
|
|
# print(source_dataset)
|
|
# print(source_dataset.recursive_datasets)
|
|
#
|
|
#
|
|
# pprint.pprint(ZfsDataset(node, "rpool").recursive_datasets)
|