2015-12-26 22:12:36 -08:00
|
|
|
#!/usr/bin/env python3
|
|
|
|
|
|
|
|
import argparse
|
|
|
|
from configparser import ConfigParser
|
|
|
|
from urllib.parse import urlparse
|
|
|
|
from os.path import normpath, join, exists
|
2015-12-28 21:20:06 -08:00
|
|
|
from os import chmod, chown, stat, environ
|
2015-12-26 22:12:36 -08:00
|
|
|
from enum import Enum
|
|
|
|
import subprocess
|
2015-12-29 22:38:04 -08:00
|
|
|
from requests import get,put,head
|
2016-07-02 18:35:35 -07:00
|
|
|
import json
|
2015-12-26 22:12:36 -08:00
|
|
|
|
2016-04-19 23:19:58 -07:00
|
|
|
SSH_KEY_PATH = environ["DATADB_KEYPATH"] if "DATADB_KEYPATH" in environ else '/root/.ssh/datadb.key'
|
2015-12-26 22:12:36 -08:00
|
|
|
RSYNC_DEFAULT_ARGS = ['rsync', '-avzr', '--exclude=.datadb.lock', '--whole-file', '--one-file-system', '--delete', '-e', 'ssh -i {} -p 4874 -o StrictHostKeyChecking=no'.format(SSH_KEY_PATH)]
|
|
|
|
DATADB_HTTP_API = 'http://datadb.services.davepedu.com:4875/cgi-bin/'
|
|
|
|
|
|
|
|
class SyncStatus(Enum):
|
|
|
|
"Data is on local disk"
|
|
|
|
DATA_AVAILABLE = 1
|
|
|
|
"Data is not on local disk"
|
|
|
|
DATA_MISSING = 2
|
|
|
|
|
|
|
|
|
|
|
|
def restore(profile, conf, force=False): #remote_uri, local_dir, identity='/root/.ssh/datadb.key'
|
|
|
|
"""
|
|
|
|
Restore data from datadb
|
|
|
|
"""
|
|
|
|
|
|
|
|
# Sanity check: If the lockfile exists we assume the data is already there, so we wouldn't want to call rsync again
|
|
|
|
# as it would wipe out local changes. This can be overridden with --force
|
|
|
|
assert (status(profile, conf) == SyncStatus.DATA_MISSING) or force, "Data already exists (Use --force?)"
|
|
|
|
|
|
|
|
original_perms = stat(conf["dir"])
|
|
|
|
dest = urlparse(conf["uri"])
|
|
|
|
|
2015-12-29 23:25:23 -08:00
|
|
|
status_code = head(DATADB_HTTP_API+'get_backup', params={'proto':dest.scheme, 'name':profile}).status_code
|
|
|
|
if status_code == 404:
|
2015-12-29 22:38:04 -08:00
|
|
|
print("Connected to datadb, but datasource '{}' doesn't exist. Exiting".format(profile))
|
|
|
|
# TODO: special exit code >1 to indicate this?
|
|
|
|
return
|
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
if dest.scheme == 'rsync':
|
|
|
|
args = RSYNC_DEFAULT_ARGS[:]
|
|
|
|
|
|
|
|
# Request backup server to prepare the backup, the returned dir is what we sync from
|
|
|
|
rsync_path = get(DATADB_HTTP_API+'get_backup', params={'proto':'rsync', 'name':profile}).text.rstrip()
|
|
|
|
|
|
|
|
# Add rsync source path
|
|
|
|
args.append('nexus@{}:{}'.format(dest.netloc, normpath(rsync_path)+'/'))
|
|
|
|
|
|
|
|
# Add local dir
|
|
|
|
args.append(normpath(conf["dir"])+'/')
|
|
|
|
print("Rsync restore call: {}".format(' '.join(args)))
|
|
|
|
|
|
|
|
subprocess.check_call(args)
|
|
|
|
|
|
|
|
elif dest.scheme == 'archive':
|
|
|
|
# http request backup server
|
|
|
|
# download tarball
|
|
|
|
args_curl = ['curl', '-s', '-v', '-XGET', '{}get_backup?proto=archive&name={}'.format(DATADB_HTTP_API, profile)]
|
|
|
|
# unpack
|
|
|
|
args_tar = ['tar', 'zxv', '-C', normpath(conf["dir"])+'/']
|
|
|
|
|
|
|
|
print("Tar restore call: {} | {}".format(' '.join(args_curl), ' '.join(args_tar)))
|
|
|
|
|
|
|
|
dl = subprocess.Popen(args_curl, stdout=subprocess.PIPE)
|
|
|
|
extract = subprocess.Popen(args_tar, stdin=dl.stdout)
|
|
|
|
|
|
|
|
dl.wait()
|
|
|
|
extract.wait()
|
|
|
|
# TODO: convert to pure python?
|
|
|
|
|
|
|
|
assert dl.returncode == 0, "Could not download archive"
|
|
|
|
assert extract.returncode == 0, "Could not extract archive"
|
|
|
|
|
|
|
|
# Restore original permissions on data dir
|
|
|
|
# TODO store these in conf file
|
|
|
|
chmod(conf["dir"], original_perms.st_mode)
|
|
|
|
chown(conf["dir"], original_perms.st_uid, original_perms.st_gid)
|
|
|
|
# TODO apply other permissions
|
|
|
|
|
|
|
|
|
|
|
|
def backup(profile, conf, force=False):
|
|
|
|
"""
|
|
|
|
Backup data to datadb
|
|
|
|
"""
|
|
|
|
|
|
|
|
# Sanity check: If the lockfile doesn't exist we assume the data is missing, so we wouldn't want to call rsync
|
|
|
|
# again as it would wipe out the backup.
|
|
|
|
assert (status(profile, conf) == SyncStatus.DATA_AVAILABLE) or force, "Data is missing (Use --force?)"
|
|
|
|
|
|
|
|
dest = urlparse(conf["uri"])
|
|
|
|
|
|
|
|
if dest.scheme == 'rsync':
|
|
|
|
args = RSYNC_DEFAULT_ARGS[:]
|
|
|
|
|
2016-04-19 23:19:58 -07:00
|
|
|
# Excluded paths
|
|
|
|
for exclude_path in conf["exclude"].split(","):
|
|
|
|
if not exclude_path == "":
|
|
|
|
args.append("--exclude")
|
|
|
|
args.append(exclude_path)
|
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
# Add local dir
|
|
|
|
args.append(normpath(conf["dir"])+'/')
|
|
|
|
|
|
|
|
# Hit backupdb via http to retreive absolute path of rsync destination of remote server
|
2016-07-02 18:35:35 -07:00
|
|
|
rsync_path, token = get(DATADB_HTTP_API+'new_backup', params={'proto':'rsync', 'name':profile, 'keep':conf["keep"]}).json()
|
2015-12-26 22:12:36 -08:00
|
|
|
|
|
|
|
# Add rsync source path
|
|
|
|
args.append(normpath('nexus@{}:{}'.format(dest.netloc, rsync_path))+'/')
|
|
|
|
|
|
|
|
#print("Rsync backup call: {}".format(' '.join(args)))
|
|
|
|
|
2016-03-21 22:58:22 -07:00
|
|
|
try:
|
|
|
|
subprocess.check_call(args)
|
|
|
|
except subprocess.CalledProcessError as cpe:
|
|
|
|
if cpe.returncode not in [0,24]: # ignore partial transfer due to vanishing files on our end
|
|
|
|
raise
|
2016-07-02 18:35:35 -07:00
|
|
|
# confirm completion
|
|
|
|
put(DATADB_HTTP_API+'new_backup', params={'proto':'rsync', 'name':profile, 'token': token, 'keep':conf["keep"]})
|
2015-12-26 22:12:36 -08:00
|
|
|
|
|
|
|
elif dest.scheme == 'archive':
|
|
|
|
# CD to local source dir
|
|
|
|
# create tarball
|
|
|
|
# http PUT file to backup server
|
2016-04-19 23:19:58 -07:00
|
|
|
args_tar = ['tar', '--exclude=.datadb.lock']
|
|
|
|
|
|
|
|
# Excluded paths
|
|
|
|
for exclude_path in conf["exclude"].split(","):
|
|
|
|
if not exclude_path == "":
|
|
|
|
args_tar.append("--exclude")
|
|
|
|
args_tar.append(exclude_path)
|
|
|
|
|
|
|
|
args_tar += ['-zcv', './']
|
2015-12-26 22:12:36 -08:00
|
|
|
args_curl = ['curl', '-v', '-XPUT', '--data-binary', '@-', '{}new_backup?proto=archive&name={}&keep={}'.format(DATADB_HTTP_API, profile, conf["keep"])]
|
|
|
|
|
|
|
|
print("Tar backup call: {} | {}".format(' '.join(args_tar), ' '.join(args_curl)))
|
|
|
|
|
|
|
|
compress = subprocess.Popen(args_tar, stdout=subprocess.PIPE, cwd=normpath(conf["dir"])+'/')
|
|
|
|
upload = subprocess.Popen(args_curl, stdin=compress.stdout)
|
|
|
|
|
|
|
|
compress.wait()
|
|
|
|
upload.wait()
|
|
|
|
# TODO: convert to pure python?
|
|
|
|
|
|
|
|
assert compress.returncode == 0, "Could not create archive"
|
|
|
|
assert upload.returncode == 0, "Could not upload archive"
|
|
|
|
|
|
|
|
|
|
|
|
def status(profile, conf):
|
|
|
|
"""
|
|
|
|
Check status of local dir - if the lock file is in place, we assume the data is there
|
|
|
|
"""
|
|
|
|
|
|
|
|
lockfile = join(conf["dir"], '.datadb.lock')
|
|
|
|
|
|
|
|
if exists(lockfile):
|
|
|
|
return SyncStatus.DATA_AVAILABLE
|
|
|
|
return SyncStatus.DATA_MISSING
|
|
|
|
|
|
|
|
|
2015-12-27 22:52:34 -08:00
|
|
|
def shell_exec(cmd, workdir='/tmp/'):
|
|
|
|
"""
|
|
|
|
Execute a command in shell, wait for exit.
|
|
|
|
"""
|
|
|
|
print("Calling: {}".format(cmd))
|
|
|
|
subprocess.Popen(cmd, shell=True, cwd=workdir).wait()
|
|
|
|
|
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
def main():
|
|
|
|
"""
|
|
|
|
Excepts a config file at /etc/datadb.ini. Example:
|
|
|
|
|
|
|
|
----------------------------
|
|
|
|
[gyfd]
|
|
|
|
uri=
|
|
|
|
dir=
|
|
|
|
keep=
|
|
|
|
auth=
|
|
|
|
restore_preexec=
|
|
|
|
restore_postexec=
|
|
|
|
export_preexec=
|
|
|
|
export_postexec=
|
2016-04-19 23:19:58 -07:00
|
|
|
exclude=
|
2015-12-26 22:12:36 -08:00
|
|
|
----------------------------
|
|
|
|
|
|
|
|
Each [section] defines one backup task.
|
|
|
|
|
|
|
|
Fields:
|
|
|
|
|
|
|
|
*uri*: Destination/source for this instance's data. Always fits the following format:
|
|
|
|
|
|
|
|
<procotol>://<server>/<backup name>
|
|
|
|
|
|
|
|
Valid protocols:
|
|
|
|
|
|
|
|
rsync - rsync executed over SSH. The local dir will be synced with the remote backup dir using rsync.
|
|
|
|
archive - tar archives transported over HTTP. The local dir will be tarred and PUT to the backup server's remote dir via http.
|
|
|
|
|
|
|
|
*dir*: Local dir for this backup
|
|
|
|
|
|
|
|
*keep*: Currently unused. Number of historical copies to keep on remote server
|
|
|
|
|
|
|
|
*auth*: Currently unused. Username:password string to use while contacting the datadb via HTTP.
|
|
|
|
|
|
|
|
*restore_preexec*: Shell command to exec before pulling/restoring data
|
|
|
|
|
|
|
|
*restore_postexec*: Shell command to exec after pulling/restoring data
|
|
|
|
|
|
|
|
*export_preexec*: Shell command to exec before pushing data
|
|
|
|
|
|
|
|
*export_postexec*: Shell command to exec after pushing data
|
|
|
|
|
2016-04-19 23:19:58 -07:00
|
|
|
*exclude*: if the underlying transport method supports excluding paths, a comma separated list of paths to exclude. Applies to backup operations only.
|
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
"""
|
2015-12-28 21:20:06 -08:00
|
|
|
|
|
|
|
conf_path = environ["DATADB_CONF"] if "DATADB_CONF" in environ else "/etc/datadb.ini"
|
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
# Load profiles
|
|
|
|
config = ConfigParser()
|
2015-12-28 21:20:06 -08:00
|
|
|
config.read(conf_path)
|
2015-12-26 22:12:36 -08:00
|
|
|
|
|
|
|
config = {section:{k:config[section][k] for k in config[section]} for section in config.sections()}
|
|
|
|
|
|
|
|
parser = argparse.ArgumentParser(description="Backupdb Agent depends on config: /etc/datadb.ini")
|
|
|
|
|
2015-12-28 21:20:06 -08:00
|
|
|
parser.add_argument('-f', '--force', default=False, action='store_true', help='force restore operation if destination data already exists')
|
|
|
|
parser.add_argument('-n', '--no-exec', default=False, action='store_true', help='don\'t run pre/post-exec commands')
|
|
|
|
parser.add_argument('-b', '--no-pre-exec', default=False, action='store_true', help='don\'t run pre-exec commands')
|
|
|
|
parser.add_argument('-m', '--no-post-exec', default=False, action='store_true', help='don\'t run post-exec commands')
|
2015-12-26 22:12:36 -08:00
|
|
|
|
|
|
|
parser.add_argument('profile', type=str, choices=config.keys(), help='Profile to restore')
|
|
|
|
|
|
|
|
#parser.add_argument('-i', '--identity',
|
|
|
|
# help='Ssh keyfile to use', type=str, default='/root/.ssh/datadb.key')
|
|
|
|
#parser.add_argument('-r', '--remote',
|
|
|
|
# help='Remote server (rsync://...)', type=str, required=True)
|
|
|
|
#parser.add_argument('-l', '--local_dir',
|
|
|
|
# help='Local path', type=str, required=True)
|
|
|
|
|
|
|
|
subparser_modes = parser.add_subparsers(dest='mode', help='modes (only "rsync")')
|
|
|
|
|
|
|
|
subparser_backup = subparser_modes.add_parser('backup', help='backup to datastore')
|
|
|
|
|
|
|
|
subparser_restore = subparser_modes.add_parser('restore', help='restore from datastore')
|
|
|
|
|
|
|
|
subparser_status = subparser_modes.add_parser('status', help='get info for profile')
|
|
|
|
|
|
|
|
args = parser.parse_args()
|
|
|
|
|
2015-12-28 21:20:06 -08:00
|
|
|
if args.no_exec:
|
|
|
|
args.no_pre_exec = True
|
|
|
|
args.no_post_exec = True
|
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
if args.mode == 'restore':
|
2015-12-28 21:20:06 -08:00
|
|
|
if not args.no_pre_exec and config[args.profile]['restore_preexec']:
|
2015-12-27 22:57:24 -08:00
|
|
|
shell_exec(config[args.profile]['restore_preexec'])
|
2015-12-27 22:52:34 -08:00
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
restore(args.profile, config[args.profile], force=args.force)
|
2015-12-27 22:52:34 -08:00
|
|
|
|
2015-12-28 21:20:06 -08:00
|
|
|
if not args.no_post_exec and config[args.profile]['restore_postexec']:
|
2015-12-27 22:57:24 -08:00
|
|
|
shell_exec(config[args.profile]['restore_postexec'])
|
2015-12-27 22:52:34 -08:00
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
elif args.mode == 'backup':
|
2015-12-28 21:20:06 -08:00
|
|
|
if not args.no_pre_exec and config[args.profile]['export_preexec']:
|
2015-12-27 22:57:24 -08:00
|
|
|
shell_exec(config[args.profile]['export_preexec'])
|
2015-12-27 22:52:34 -08:00
|
|
|
|
2015-12-26 22:12:36 -08:00
|
|
|
backup(args.profile, config[args.profile])
|
2015-12-27 22:52:34 -08:00
|
|
|
|
2015-12-28 21:20:06 -08:00
|
|
|
if not args.no_post_exec and config[args.profile]['export_postexec']:
|
2015-12-27 22:57:24 -08:00
|
|
|
shell_exec(config[args.profile]['export_postexec'])
|
2015-12-26 22:12:36 -08:00
|
|
|
|
|
|
|
elif args.mode == 'status':
|
|
|
|
info = status(args.profile, config[args.profile])
|
|
|
|
print(SyncStatus(info))
|
|
|
|
|
|
|
|
else:
|
|
|
|
parser.print_usage()
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
main()
|