Update the logic that probes for the borgmatic runtime directory to support more platforms and use cases (#934).
All checks were successful
build / test (push) Successful in 5m45s
build / docs (push) Successful in 1m40s

Reviewed-on: #937
This commit is contained in:
Dan Helfman 2024-11-17 19:57:09 +00:00
commit 76cfeda290
28 changed files with 1147 additions and 601 deletions

4
NEWS
View File

@ -1,5 +1,9 @@
1.9.2.dev0
* #932: Fix missing build backend setting in pyproject.toml to allow Fedora builds.
* #934: Update the logic that probes for the borgmatic streaming database dump, bootstrap
metadata, and check state directories to support more platforms and use cases.
* #934: Add the "RuntimeDirectory" and "StateDirectory" options to the sample systemd service
file to support the new runtime and state directory logic.
1.9.1
* #928: Fix the user runtime directory location on macOS (and possibly Cygwin).

View File

@ -403,16 +403,22 @@ BORG_DIRECTORY_FILE_TYPE = 'd'
def collect_spot_check_archive_paths(
repository, archive, config, local_borg_version, global_arguments, local_path, remote_path
repository,
archive,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
borgmatic_runtime_directory,
):
'''
Given a repository configuration dict, the name of the latest archive, a configuration dict, the
local Borg version, global arguments as an argparse.Namespace instance, the local Borg path, and
the remote Borg path, collect the paths from the given archive (but only include files and
symlinks and exclude borgmatic runtime directories).
local Borg version, global arguments as an argparse.Namespace instance, the local Borg path, the
remote Borg path, and the borgmatic runtime directory, collect the paths from the given archive
(but only include files and symlinks and exclude borgmatic runtime directories).
'''
borgmatic_source_directory = borgmatic.config.paths.get_borgmatic_source_directory(config)
borgmatic_runtime_directory = borgmatic.config.paths.get_borgmatic_runtime_directory(config)
return tuple(
path
@ -445,7 +451,7 @@ def compare_spot_check_hashes(
global_arguments,
local_path,
remote_path,
log_label,
log_prefix,
source_paths,
):
'''
@ -469,7 +475,7 @@ def compare_spot_check_hashes(
if os.path.exists(os.path.join(working_directory or '', source_path))
}
logger.debug(
f'{log_label}: Sampling {sample_count} source paths (~{spot_check_config["data_sample_percentage"]}%) for spot check'
f'{log_prefix}: Sampling {sample_count} source paths (~{spot_check_config["data_sample_percentage"]}%) for spot check'
)
source_sample_paths_iterator = iter(source_sample_paths)
@ -546,18 +552,19 @@ def spot_check(
global_arguments,
local_path,
remote_path,
borgmatic_runtime_directory,
):
'''
Given a repository dict, a loaded configuration dict, the local Borg version, global arguments
as an argparse.Namespace instance, the local Borg path, and the remote Borg path, perform a spot
check for the latest archive in the given repository.
as an argparse.Namespace instance, the local Borg path, the remote Borg path, and the borgmatic
runtime directory, perform a spot check for the latest archive in the given repository.
A spot check compares file counts and also the hashes for a random sampling of source files on
disk to those stored in the latest archive. If any differences are beyond configured tolerances,
then the check fails.
'''
log_label = f'{repository.get("label", repository["path"])}'
logger.debug(f'{log_label}: Running spot check')
log_prefix = f'{repository.get("label", repository["path"])}'
logger.debug(f'{log_prefix}: Running spot check')
try:
spot_check_config = next(
@ -579,7 +586,7 @@ def spot_check(
local_path,
remote_path,
)
logger.debug(f'{log_label}: {len(source_paths)} total source paths for spot check')
logger.debug(f'{log_prefix}: {len(source_paths)} total source paths for spot check')
archive = borgmatic.borg.repo_list.resolve_archive_name(
repository['path'],
@ -590,7 +597,7 @@ def spot_check(
local_path,
remote_path,
)
logger.debug(f'{log_label}: Using archive {archive} for spot check')
logger.debug(f'{log_prefix}: Using archive {archive} for spot check')
archive_paths = collect_spot_check_archive_paths(
repository,
@ -600,8 +607,9 @@ def spot_check(
global_arguments,
local_path,
remote_path,
borgmatic_runtime_directory,
)
logger.debug(f'{log_label}: {len(archive_paths)} total archive paths for spot check')
logger.debug(f'{log_prefix}: {len(archive_paths)} total archive paths for spot check')
# Calculate the percentage delta between the source paths count and the archive paths count, and
# compare that delta to the configured count tolerance percentage.
@ -609,10 +617,10 @@ def spot_check(
if count_delta_percentage > spot_check_config['count_tolerance_percentage']:
logger.debug(
f'{log_label}: Paths in source paths but not latest archive: {", ".join(set(source_paths) - set(archive_paths)) or "none"}'
f'{log_prefix}: Paths in source paths but not latest archive: {", ".join(set(source_paths) - set(archive_paths)) or "none"}'
)
logger.debug(
f'{log_label}: Paths in latest archive but not source paths: {", ".join(set(archive_paths) - set(source_paths)) or "none"}'
f'{log_prefix}: Paths in latest archive but not source paths: {", ".join(set(archive_paths) - set(source_paths)) or "none"}'
)
raise ValueError(
f'Spot check failed: {count_delta_percentage:.2f}% file count delta between source paths and latest archive (tolerance is {spot_check_config["count_tolerance_percentage"]}%)'
@ -626,25 +634,25 @@ def spot_check(
global_arguments,
local_path,
remote_path,
log_label,
log_prefix,
source_paths,
)
# Error if the percentage of failing hashes exceeds the configured tolerance percentage.
logger.debug(f'{log_label}: {len(failing_paths)} non-matching spot check hashes')
logger.debug(f'{log_prefix}: {len(failing_paths)} non-matching spot check hashes')
data_tolerance_percentage = spot_check_config['data_tolerance_percentage']
failing_percentage = (len(failing_paths) / len(source_paths)) * 100
if failing_percentage > data_tolerance_percentage:
logger.debug(
f'{log_label}: Source paths with data not matching the latest archive: {", ".join(failing_paths)}'
f'{log_prefix}: Source paths with data not matching the latest archive: {", ".join(failing_paths)}'
)
raise ValueError(
f'Spot check failed: {failing_percentage:.2f}% of source paths with data not matching the latest archive (tolerance is {data_tolerance_percentage}%)'
)
logger.info(
f'{log_label}: Spot check passed with a {count_delta_percentage:.2f}% file count delta and a {failing_percentage:.2f}% file data delta'
f'{log_prefix}: Spot check passed with a {count_delta_percentage:.2f}% file count delta and a {failing_percentage:.2f}% file data delta'
)
@ -678,7 +686,9 @@ def run_check(
**hook_context,
)
logger.info(f'{repository.get("label", repository["path"])}: Running consistency checks')
log_prefix = repository.get('label', repository['path'])
logger.info(f'{log_prefix}: Running consistency checks')
repository_id = borgmatic.borg.check.get_repository_id(
repository['path'],
config,
@ -730,14 +740,18 @@ def run_check(
write_check_time(make_check_time_path(config, repository_id, 'extract'))
if 'spot' in checks:
spot_check(
repository,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
)
with borgmatic.config.paths.Runtime_directory(
config, log_prefix
) as borgmatic_runtime_directory:
spot_check(
repository,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
borgmatic_runtime_directory,
)
write_check_time(make_check_time_path(config, repository_id, 'spot'))
borgmatic.hooks.command.execute_hook(

View File

@ -38,37 +38,44 @@ def get_config_paths(archive_name, bootstrap_arguments, global_arguments, local_
borgmatic_source_directory = borgmatic.config.paths.get_borgmatic_source_directory(
{'borgmatic_source_directory': bootstrap_arguments.borgmatic_source_directory}
)
borgmatic_runtime_directory = borgmatic.config.paths.get_borgmatic_runtime_directory(
{'user_runtime_directory': bootstrap_arguments.user_runtime_directory}
)
config = make_bootstrap_config(bootstrap_arguments)
# Probe for the manifest file in multiple locations, as the default location has moved to the
# borgmatic runtime directory (which get stored as just "/borgmatic" with Borg 1.4+). But we
# still want to support reading the manifest from previously created archives as well.
for base_directory in ('borgmatic', borgmatic_runtime_directory, borgmatic_source_directory):
borgmatic_manifest_path = os.path.join(base_directory, 'bootstrap', 'manifest.json')
with borgmatic.config.paths.Runtime_directory(
{'user_runtime_directory': bootstrap_arguments.user_runtime_directory},
bootstrap_arguments.repository,
) as borgmatic_runtime_directory:
for base_directory in (
'borgmatic',
borgmatic.config.paths.make_runtime_directory_glob(borgmatic_runtime_directory),
borgmatic_source_directory,
):
borgmatic_manifest_path = 'sh:' + os.path.join(
base_directory, 'bootstrap', 'manifest.json'
)
extract_process = borgmatic.borg.extract.extract_archive(
global_arguments.dry_run,
bootstrap_arguments.repository,
archive_name,
[borgmatic_manifest_path],
config,
local_borg_version,
global_arguments,
local_path=bootstrap_arguments.local_path,
remote_path=bootstrap_arguments.remote_path,
extract_to_stdout=True,
)
manifest_json = extract_process.stdout.read()
extract_process = borgmatic.borg.extract.extract_archive(
global_arguments.dry_run,
bootstrap_arguments.repository,
archive_name,
[borgmatic_manifest_path],
config,
local_borg_version,
global_arguments,
local_path=bootstrap_arguments.local_path,
remote_path=bootstrap_arguments.remote_path,
extract_to_stdout=True,
)
manifest_json = extract_process.stdout.read()
if manifest_json:
break
else:
raise ValueError(
'Cannot read configuration paths from archive due to missing bootstrap manifest'
)
if manifest_json:
break
else:
raise ValueError(
'Cannot read configuration paths from archive due to missing bootstrap manifest'
)
try:
manifest_data = json.loads(manifest_json)

View File

@ -14,15 +14,15 @@ import borgmatic.hooks.dump
logger = logging.getLogger(__name__)
def create_borgmatic_manifest(config, config_paths, dry_run):
def create_borgmatic_manifest(config, config_paths, borgmatic_runtime_directory, dry_run):
'''
Create a borgmatic manifest file to store the paths to the configuration files used to create
the archive.
Given a configuration dict, a sequence of config file paths, the borgmatic runtime directory,
and whether this is a dry run, create a borgmatic manifest file to store the paths to the
configuration files used to create the archive.
'''
if dry_run:
return
borgmatic_runtime_directory = borgmatic.config.paths.get_borgmatic_runtime_directory(config)
borgmatic_manifest_path = os.path.join(
borgmatic_runtime_directory, 'bootstrap', 'manifest.json'
)
@ -71,54 +71,68 @@ def run_create(
global_arguments.dry_run,
**hook_context,
)
logger.info(f'{repository.get("label", repository["path"])}: Creating archive{dry_run_label}')
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
global_arguments.dry_run,
)
active_dumps = borgmatic.hooks.dispatch.call_hooks(
'dump_data_sources',
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
global_arguments.dry_run,
)
if config.get('store_config_files', True):
create_borgmatic_manifest(
log_prefix = repository.get('label', repository['path'])
logger.info(f'{log_prefix}: Creating archive{dry_run_label}')
with borgmatic.config.paths.Runtime_directory(
config, log_prefix
) as borgmatic_runtime_directory:
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
config_paths,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
borgmatic_runtime_directory,
global_arguments.dry_run,
)
stream_processes = [process for processes in active_dumps.values() for process in processes]
active_dumps = borgmatic.hooks.dispatch.call_hooks(
'dump_data_sources',
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
borgmatic_runtime_directory,
global_arguments.dry_run,
)
stream_processes = [process for processes in active_dumps.values() for process in processes]
json_output = borgmatic.borg.create.create_archive(
global_arguments.dry_run,
repository['path'],
config,
config_paths,
local_borg_version,
global_arguments,
local_path=local_path,
remote_path=remote_path,
progress=create_arguments.progress,
stats=create_arguments.stats,
json=create_arguments.json,
list_files=create_arguments.list_files,
stream_processes=stream_processes,
)
if json_output:
yield borgmatic.actions.json.parse_json(json_output, repository.get('label'))
if config.get('store_config_files', True):
create_borgmatic_manifest(
config,
config_paths,
borgmatic_runtime_directory,
global_arguments.dry_run,
)
json_output = borgmatic.borg.create.create_archive(
global_arguments.dry_run,
repository['path'],
config,
config_paths,
local_borg_version,
global_arguments,
borgmatic_runtime_directory,
local_path=local_path,
remote_path=remote_path,
progress=create_arguments.progress,
stats=create_arguments.stats,
json=create_arguments.json,
list_files=create_arguments.list_files,
stream_processes=stream_processes,
)
if json_output:
yield borgmatic.actions.json.parse_json(json_output, repository.get('label'))
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
config_filename,
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
borgmatic_runtime_directory,
global_arguments.dry_run,
)
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
config_filename,
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
global_arguments.dry_run,
)
borgmatic.hooks.command.execute_hook(
config.get('after_backup'),
config.get('umask'),

View File

@ -108,6 +108,7 @@ def restore_single_data_source(
hook_name,
data_source,
connection_params,
borgmatic_runtime_directory,
):
'''
Given (among other things) an archive name, a data source hook name, the hostname, port,
@ -123,9 +124,9 @@ def restore_single_data_source(
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
borgmatic_runtime_directory,
data_source['name'],
)[hook_name]
borgmatic_runtime_directory = borgmatic.config.paths.get_borgmatic_runtime_directory(config)
destination_path = (
tempfile.mkdtemp(dir=borgmatic_runtime_directory)
@ -135,7 +136,7 @@ def restore_single_data_source(
try:
# Kick off a single data source extract. If using a directory format, extract to a temporary
# directory. Otheriwes extract the single dump file to stdout.
# directory. Otherwise extract the single dump file to stdout.
extract_process = borgmatic.borg.extract.extract_archive(
dry_run=global_arguments.dry_run,
repository=repository['path'],
@ -170,6 +171,7 @@ def restore_single_data_source(
dry_run=global_arguments.dry_run,
extract_process=extract_process,
connection_params=connection_params,
borgmatic_runtime_directory=borgmatic_runtime_directory,
)
@ -181,17 +183,17 @@ def collect_archive_data_source_names(
global_arguments,
local_path,
remote_path,
borgmatic_runtime_directory,
):
'''
Given a local or remote repository path, a resolved archive name, a configuration dict, the
local Borg version, global_arguments an argparse.Namespace, and local and remote Borg paths,
query the archive for the names of data sources it contains as dumps and return them as a dict
from hook name to a sequence of data source names.
local Borg version, global_arguments an argparse.Namespace, local and remote Borg paths, and the
borgmatic runtime directory, query the archive for the names of data sources it contains as
dumps and return them as a dict from hook name to a sequence of data source names.
'''
borgmatic_source_directory = str(
pathlib.Path(borgmatic.config.paths.get_borgmatic_source_directory(config))
)
borgmatic_runtime_directory = borgmatic.config.paths.get_borgmatic_runtime_directory(config)
# Probe for the data source dumps in multiple locations, as the default location has moved to
# the borgmatic runtime directory (which get stored as just "/borgmatic" with Borg 1.4+). But we
@ -207,7 +209,7 @@ def collect_archive_data_source_names(
+ borgmatic.hooks.dump.make_data_source_dump_path(base_directory, '*_databases/*/*')
for base_directory in (
'borgmatic',
borgmatic_runtime_directory.lstrip('/'),
borgmatic.config.paths.make_runtime_directory_glob(borgmatic_runtime_directory),
borgmatic_source_directory.lstrip('/'),
)
],
@ -342,109 +344,116 @@ def run_restore(
):
return
logger.info(
f'{repository.get("label", repository["path"])}: Restoring data sources from archive {restore_arguments.archive}'
)
log_prefix = repository.get('label', repository['path'])
logger.info(f'{log_prefix}: Restoring data sources from archive {restore_arguments.archive}')
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
global_arguments.dry_run,
)
with borgmatic.config.paths.Runtime_directory(
config, log_prefix
) as borgmatic_runtime_directory:
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
borgmatic_runtime_directory,
global_arguments.dry_run,
)
archive_name = borgmatic.borg.repo_list.resolve_archive_name(
repository['path'],
restore_arguments.archive,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
)
archive_data_source_names = collect_archive_data_source_names(
repository['path'],
archive_name,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
)
restore_names = find_data_sources_to_restore(
restore_arguments.data_sources, archive_data_source_names
)
found_names = set()
remaining_restore_names = {}
connection_params = {
'hostname': restore_arguments.hostname,
'port': restore_arguments.port,
'username': restore_arguments.username,
'password': restore_arguments.password,
'restore_path': restore_arguments.restore_path,
}
archive_name = borgmatic.borg.repo_list.resolve_archive_name(
repository['path'],
restore_arguments.archive,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
)
archive_data_source_names = collect_archive_data_source_names(
repository['path'],
archive_name,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
borgmatic_runtime_directory,
)
restore_names = find_data_sources_to_restore(
restore_arguments.data_sources, archive_data_source_names
)
found_names = set()
remaining_restore_names = {}
connection_params = {
'hostname': restore_arguments.hostname,
'port': restore_arguments.port,
'username': restore_arguments.username,
'password': restore_arguments.password,
'restore_path': restore_arguments.restore_path,
}
for hook_name, data_source_names in restore_names.items():
for data_source_name in data_source_names:
found_hook_name, found_data_source = get_configured_data_source(
config, archive_data_source_names, hook_name, data_source_name
)
if not found_data_source:
remaining_restore_names.setdefault(found_hook_name or hook_name, []).append(
data_source_name
for hook_name, data_source_names in restore_names.items():
for data_source_name in data_source_names:
found_hook_name, found_data_source = get_configured_data_source(
config, archive_data_source_names, hook_name, data_source_name
)
continue
found_names.add(data_source_name)
restore_single_data_source(
repository,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
archive_name,
found_hook_name or hook_name,
dict(found_data_source, **{'schemas': restore_arguments.schemas}),
connection_params,
)
if not found_data_source:
remaining_restore_names.setdefault(found_hook_name or hook_name, []).append(
data_source_name
)
continue
# For any data sources that weren't found via exact matches in the configuration, try to
# fallback to "all" entries.
for hook_name, data_source_names in remaining_restore_names.items():
for data_source_name in data_source_names:
found_hook_name, found_data_source = get_configured_data_source(
config, archive_data_source_names, hook_name, data_source_name, 'all'
)
found_names.add(data_source_name)
restore_single_data_source(
repository,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
archive_name,
found_hook_name or hook_name,
dict(found_data_source, **{'schemas': restore_arguments.schemas}),
connection_params,
borgmatic_runtime_directory,
)
if not found_data_source:
continue
# For any data sources that weren't found via exact matches in the configuration, try to
# fallback to "all" entries.
for hook_name, data_source_names in remaining_restore_names.items():
for data_source_name in data_source_names:
found_hook_name, found_data_source = get_configured_data_source(
config, archive_data_source_names, hook_name, data_source_name, 'all'
)
found_names.add(data_source_name)
data_source = copy.copy(found_data_source)
data_source['name'] = data_source_name
if not found_data_source:
continue
restore_single_data_source(
repository,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
archive_name,
found_hook_name or hook_name,
dict(data_source, **{'schemas': restore_arguments.schemas}),
connection_params,
)
found_names.add(data_source_name)
data_source = copy.copy(found_data_source)
data_source['name'] = data_source_name
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
global_arguments.dry_run,
)
restore_single_data_source(
repository,
config,
local_borg_version,
global_arguments,
local_path,
remote_path,
archive_name,
found_hook_name or hook_name,
dict(data_source, **{'schemas': restore_arguments.schemas}),
connection_params,
borgmatic_runtime_directory,
)
borgmatic.hooks.dispatch.call_hooks_even_if_unconfigured(
'remove_data_source_dumps',
config,
repository['path'],
borgmatic.hooks.dump.DATA_SOURCE_HOOK_NAMES,
borgmatic_runtime_directory,
global_arguments.dry_run,
)
ensure_data_sources_found(restore_names, remaining_restore_names, found_names)

View File

@ -504,6 +504,7 @@ def create_archive(
config_paths,
local_borg_version,
global_arguments,
borgmatic_runtime_directory,
local_path='borg',
remote_path=None,
progress=False,
@ -524,9 +525,7 @@ def create_archive(
working_directory = borgmatic.config.paths.get_working_directory(config)
borgmatic_runtime_directories = expand_directories(
collect_borgmatic_runtime_directories(
borgmatic.config.paths.get_borgmatic_runtime_directory(config)
),
collect_borgmatic_runtime_directories(borgmatic_runtime_directory),
working_directory=working_directory,
)

View File

@ -1,4 +1,8 @@
import logging
import os
import tempfile
logger = logging.getLogger(__name__)
def expand_user_in_path(path):
@ -26,26 +30,91 @@ def get_borgmatic_source_directory(config):
return expand_user_in_path(config.get('borgmatic_source_directory') or '~/.borgmatic')
def get_borgmatic_runtime_directory(config):
'''
Given a configuration dict, get the borgmatic runtime directory used for storing temporary
runtime data like streaming database dumps and bootstrap metadata. Defaults to
$XDG_RUNTIME_DIR/./borgmatic or $TMPDIR/./borgmatic or $TEMP/./borgmatic or
/run/user/$UID/./borgmatic.
TEMPORARY_DIRECTORY_PREFIX = 'borgmatic-'
The "/./" is taking advantage of a Borg feature such that the part of the path before the "/./"
does not get stored in the file path within an archive. That way, the path of the runtime
directory can change without leaving database dumps within an archive inaccessible.
class Runtime_directory:
'''
return expand_user_in_path(
os.path.join(
A Python context manager for creating and cleaning up the borgmatic runtime directory used for
storing temporary runtime data like streaming database dumps and bootstrap metadata.
Example use as a context manager:
with borgmatic.config.paths.Runtime_directory(config) as borgmatic_runtime_directory:
do_something_with(borgmatic_runtime_directory)
For the scope of that "with" statement, the runtime directory is available. Afterwards, it
automatically gets cleaned up as necessary.
'''
def __init__(self, config, log_prefix):
'''
Given a configuration dict and a log prefix, determine the borgmatic runtime directory,
creating a secure, temporary directory within it if necessary. Defaults to
$XDG_RUNTIME_DIR/./borgmatic or $RUNTIME_DIRECTORY/./borgmatic or
$TMPDIR/borgmatic-[random]/./borgmatic or $TEMP/borgmatic-[random]/./borgmatic or
/tmp/borgmatic-[random]/./borgmatic where "[random]" is a randomly generated string intended
to avoid path collisions.
If XDG_RUNTIME_DIR or RUNTIME_DIRECTORY is set and already ends in "/borgmatic", then don't
tack on a second "/borgmatic" path component.
The "/./" is taking advantage of a Borg feature such that the part of the path before the "/./"
does not get stored in the file path within an archive. That way, the path of the runtime
directory can change without leaving database dumps within an archive inaccessible.
'''
runtime_directory = (
config.get('user_runtime_directory')
or os.environ.get('XDG_RUNTIME_DIR')
or os.environ.get('TMPDIR')
or os.environ.get('TEMP')
or f'/run/user/{os.getuid()}',
'.',
'borgmatic',
or os.environ.get('XDG_RUNTIME_DIR') # Set by PAM on Linux.
or os.environ.get('RUNTIME_DIRECTORY') # Set by systemd if configured.
)
if runtime_directory:
self.temporary_directory = None
else:
base_directory = os.environ.get('TMPDIR') or os.environ.get('TEMP') or '/tmp'
os.makedirs(base_directory, mode=0o700, exist_ok=True)
self.temporary_directory = tempfile.TemporaryDirectory(
prefix=TEMPORARY_DIRECTORY_PREFIX,
dir=base_directory,
)
runtime_directory = self.temporary_directory.name
(base_path, final_directory) = os.path.split(runtime_directory.rstrip(os.path.sep))
self.runtime_path = expand_user_in_path(
os.path.join(
base_path if final_directory == 'borgmatic' else runtime_directory, '.', 'borgmatic'
)
)
os.makedirs(self.runtime_path, mode=0o700, exist_ok=True)
logger.debug(f'{log_prefix}: Using runtime directory {os.path.normpath(self.runtime_path)}')
def __enter__(self):
'''
Return the borgmatic runtime path as a string.
'''
return self.runtime_path
def __exit__(self, exception, value, traceback):
'''
Delete any temporary directory that was created as part of initialization.
'''
if self.temporary_directory:
self.temporary_directory.cleanup()
def make_runtime_directory_glob(borgmatic_runtime_directory):
'''
Given a borgmatic runtime directory path, make a glob that would match that path, specifically
replacing any randomly generated temporary subdirectory with "*" since such a directory's name
changes on every borgmatic run.
'''
return os.path.join(
*(
'*' if subdirectory.startswith(TEMPORARY_DIRECTORY_PREFIX) else subdirectory
for subdirectory in os.path.normpath(borgmatic_runtime_directory).split(os.path.sep)
)
)
@ -59,10 +128,9 @@ def get_borgmatic_state_directory(config):
return expand_user_in_path(
os.path.join(
config.get('user_state_directory')
or os.environ.get(
'XDG_STATE_HOME',
'~/.local/state',
),
or os.environ.get('XDG_STATE_HOME')
or os.environ.get('STATE_DIRECTORY') # Set by systemd if configured.
or '~/.local/state',
'borgmatic',
)
)

View File

@ -14,15 +14,11 @@ from borgmatic.hooks import dump
logger = logging.getLogger(__name__)
def make_dump_path(config, base_directory=None): # pragma: no cover
def make_dump_path(base_directory): # pragma: no cover
'''
Given a configuration dict and an optional base directory, make the corresponding dump path. If
a base directory isn't provided, use the borgmatic runtime directory.
Given a base directory, make the corresponding dump path.
'''
return dump.make_data_source_dump_path(
base_directory or borgmatic.config.paths.get_borgmatic_runtime_directory(config),
'mariadb_databases',
)
return dump.make_data_source_dump_path(base_directory, 'mariadb_databases')
SYSTEM_DATABASE_NAMES = ('information_schema', 'mysql', 'performance_schema', 'sys')
@ -126,12 +122,12 @@ def use_streaming(databases, config, log_prefix):
return any(databases)
def dump_data_sources(databases, config, log_prefix, dry_run):
def dump_data_sources(databases, config, log_prefix, borgmatic_runtime_directory, dry_run):
'''
Dump the given MariaDB databases to a named pipe. The databases are supplied as a sequence of
dicts, one dict describing each database as per the configuration schema. Use the given
configuration dict to construct the destination path and the given log prefix in any log
entries.
borgmatic runtime directory to construct the destination path and the given log prefix in any
log entries.
Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
@ -142,7 +138,7 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
logger.info(f'{log_prefix}: Dumping MariaDB databases{dry_run_label}')
for database in databases:
dump_path = make_dump_path(config)
dump_path = make_dump_path(borgmatic_runtime_directory)
extra_environment = {'MYSQL_PWD': database['password']} if 'password' in database else None
dump_database_names = database_names_to_dump(
database, extra_environment, log_prefix, dry_run
@ -185,43 +181,55 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
return [process for process in processes if process]
def remove_data_source_dumps(databases, config, log_prefix, dry_run): # pragma: no cover
def remove_data_source_dumps(
databases, config, log_prefix, borgmatic_runtime_directory, dry_run
): # pragma: no cover
'''
Remove all database dump files for this hook regardless of the given databases. Use the given
configuration dict to construct the destination path and the log prefix in any log entries. If
this is a dry run, then don't actually remove anything.
Remove all database dump files for this hook regardless of the given databases. Use the
borgmatic_runtime_directory to construct the destination path and the log prefix in any log
entries. If this is a dry run, then don't actually remove anything.
'''
dump.remove_data_source_dumps(make_dump_path(config), 'MariaDB', log_prefix, dry_run)
dump.remove_data_source_dumps(
make_dump_path(borgmatic_runtime_directory), 'MariaDB', log_prefix, dry_run
)
def make_data_source_dump_patterns(databases, config, log_prefix, name=None): # pragma: no cover
def make_data_source_dump_patterns(
databases, config, log_prefix, borgmatic_runtime_directory, name=None
): # pragma: no cover
'''
Given a sequence of configurations dicts, a configuration dict, a prefix to log with, and a
database name to match, return the corresponding glob patterns to match the database dump in an
archive.
Given a sequence of configurations dicts, a configuration dict, a prefix to log with, the
borgmatic runtime directory, and a database name to match, return the corresponding glob
patterns to match the database dump in an archive.
'''
borgmatic_source_directory = borgmatic.config.paths.get_borgmatic_source_directory(config)
return (
dump.make_data_source_dump_filename(make_dump_path('borgmatic'), name, hostname='*'),
dump.make_data_source_dump_filename(
make_dump_path(config, 'borgmatic'), name, hostname='*'
make_dump_path(borgmatic_runtime_directory), name, hostname='*'
),
dump.make_data_source_dump_filename(make_dump_path(config), name, hostname='*'),
dump.make_data_source_dump_filename(
make_dump_path(config, borgmatic_source_directory), name, hostname='*'
make_dump_path(borgmatic_source_directory), name, hostname='*'
),
)
def restore_data_source_dump(
hook_config, config, log_prefix, data_source, dry_run, extract_process, connection_params
hook_config,
config,
log_prefix,
data_source,
dry_run,
extract_process,
connection_params,
borgmatic_runtime_directory,
):
'''
Restore a database from the given extract stream. The database is supplied as a data source
configuration dict, but the given hook configuration is ignored. The given configuration dict is
used to construct the destination path, and the given log prefix is used for any log entries. If
this is a dry run, then don't actually restore anything. Trigger the given active extract
process (an instance of subprocess.Popen) to produce output to consume.
configuration dict, but the given hook configuration is ignored. The given log prefix is used
for any log entries. If this is a dry run, then don't actually restore anything. Trigger the
given active extract process (an instance of subprocess.Popen) to produce output to consume.
'''
dry_run_label = ' (dry run; not actually restoring anything)' if dry_run else ''
hostname = connection_params['hostname'] or data_source.get(

View File

@ -8,15 +8,11 @@ from borgmatic.hooks import dump
logger = logging.getLogger(__name__)
def make_dump_path(config, base_directory=None): # pragma: no cover
def make_dump_path(base_directory): # pragma: no cover
'''
Given a configuration dict and an optional base directory, make the corresponding dump path. If
a base directory isn't provided, use the borgmatic runtime directory.
Given a base directory, make the corresponding dump path.
'''
return dump.make_data_source_dump_path(
base_directory or borgmatic.config.paths.get_borgmatic_runtime_directory(config),
'mongodb_databases',
)
return dump.make_data_source_dump_path(base_directory, 'mongodb_databases')
def use_streaming(databases, config, log_prefix):
@ -27,11 +23,12 @@ def use_streaming(databases, config, log_prefix):
return any(database.get('format') != 'directory' for database in databases)
def dump_data_sources(databases, config, log_prefix, dry_run):
def dump_data_sources(databases, config, log_prefix, borgmatic_runtime_directory, dry_run):
'''
Dump the given MongoDB databases to a named pipe. The databases are supplied as a sequence of
dicts, one dict describing each database as per the configuration schema. Use the configuration
dict to construct the destination path and the given log prefix in any log entries.
dicts, one dict describing each database as per the configuration schema. Use the borgmatic
runtime directory to construct the destination path (used for the directory format and the given
log prefix in any log entries.
Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
@ -44,7 +41,7 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
for database in databases:
name = database['name']
dump_filename = dump.make_data_source_dump_filename(
make_dump_path(config), name, database.get('hostname')
make_dump_path(borgmatic_runtime_directory), name, database.get('hostname')
)
dump_format = database.get('format', 'archive')
@ -94,36 +91,49 @@ def build_dump_command(database, dump_filename, dump_format):
)
def remove_data_source_dumps(databases, config, log_prefix, dry_run): # pragma: no cover
def remove_data_source_dumps(
databases, config, log_prefix, borgmatic_runtime_directory, dry_run
): # pragma: no cover
'''
Remove all database dump files for this hook regardless of the given databases. Use the log
prefix in any log entries. Use the given configuration dict to construct the destination path.
If this is a dry run, then don't actually remove anything.
Remove all database dump files for this hook regardless of the given databases. Use the
borgmatic_runtime_directory to construct the destination path and the log prefix in any log
entries. If this is a dry run, then don't actually remove anything.
'''
dump.remove_data_source_dumps(make_dump_path(config), 'MongoDB', log_prefix, dry_run)
dump.remove_data_source_dumps(
make_dump_path(borgmatic_runtime_directory), 'MongoDB', log_prefix, dry_run
)
def make_data_source_dump_patterns(databases, config, log_prefix, name=None): # pragma: no cover
def make_data_source_dump_patterns(
databases, config, log_prefix, borgmatic_runtime_directory, name=None
): # pragma: no cover
'''
Given a sequence of database configurations dicts, a configuration dict, a prefix to log with,
and a database name to match, return the corresponding glob patterns to match the database dump
in an archive.
Given a sequence of configurations dicts, a configuration dict, a prefix to log with, the
borgmatic runtime directory, and a database name to match, return the corresponding glob
patterns to match the database dump in an archive.
'''
borgmatic_source_directory = borgmatic.config.paths.get_borgmatic_source_directory(config)
return (
dump.make_data_source_dump_filename(make_dump_path('borgmatic'), name, hostname='*'),
dump.make_data_source_dump_filename(
make_dump_path(config, 'borgmatic'), name, hostname='*'
make_dump_path(borgmatic_runtime_directory), name, hostname='*'
),
dump.make_data_source_dump_filename(make_dump_path(config), name, hostname='*'),
dump.make_data_source_dump_filename(
make_dump_path(config, borgmatic_source_directory), name, hostname='*'
make_dump_path(borgmatic_source_directory), name, hostname='*'
),
)
def restore_data_source_dump(
hook_config, config, log_prefix, data_source, dry_run, extract_process, connection_params
hook_config,
config,
log_prefix,
data_source,
dry_run,
extract_process,
connection_params,
borgmatic_runtime_directory,
):
'''
Restore a database from the given extract stream. The database is supplied as a data source
@ -137,7 +147,9 @@ def restore_data_source_dump(
'''
dry_run_label = ' (dry run; not actually restoring anything)' if dry_run else ''
dump_filename = dump.make_data_source_dump_filename(
make_dump_path(config), data_source['name'], data_source.get('hostname')
make_dump_path(borgmatic_runtime_directory),
data_source['name'],
data_source.get('hostname'),
)
restore_command = build_restore_command(
extract_process, data_source, dump_filename, connection_params

View File

@ -14,15 +14,11 @@ from borgmatic.hooks import dump
logger = logging.getLogger(__name__)
def make_dump_path(config, base_directory=None): # pragma: no cover
def make_dump_path(base_directory): # pragma: no cover
'''
Given a configuration dict and an optional base directory, make the corresponding dump path. If
a base directory isn't provided, use the borgmatic runtime directory.
Given a base directory, make the corresponding dump path.
'''
return dump.make_data_source_dump_path(
base_directory or borgmatic.config.paths.get_borgmatic_runtime_directory(config),
'mysql_databases',
)
return dump.make_data_source_dump_path(base_directory, 'mysql_databases')
SYSTEM_DATABASE_NAMES = ('information_schema', 'mysql', 'performance_schema', 'sys')
@ -125,11 +121,12 @@ def use_streaming(databases, config, log_prefix):
return any(databases)
def dump_data_sources(databases, config, log_prefix, dry_run):
def dump_data_sources(databases, config, log_prefix, borgmatic_runtime_directory, dry_run):
'''
Dump the given MySQL/MariaDB databases to a named pipe. The databases are supplied as a sequence
of dicts, one dict describing each database as per the configuration schema. Use the given
configuration dict to construct the destination path and the given log prefix in any log entries.
borgmatic runtime directory to construct the destination path and the given log prefix in any
log entries.
Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
@ -140,7 +137,7 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
logger.info(f'{log_prefix}: Dumping MySQL databases{dry_run_label}')
for database in databases:
dump_path = make_dump_path(config)
dump_path = make_dump_path(borgmatic_runtime_directory)
extra_environment = {'MYSQL_PWD': database['password']} if 'password' in database else None
dump_database_names = database_names_to_dump(
database, extra_environment, log_prefix, dry_run
@ -183,43 +180,55 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
return [process for process in processes if process]
def remove_data_source_dumps(databases, config, log_prefix, dry_run): # pragma: no cover
def remove_data_source_dumps(
databases, config, log_prefix, borgmatic_runtime_directory, dry_run
): # pragma: no cover
'''
Remove all database dump files for this hook regardless of the given databases. Use the given
configuration dict to construct the destination path and the log prefix in any log entries. If
this is a dry run, then don't actually remove anything.
Remove all database dump files for this hook regardless of the given databases. Use the
borgmatic runtime directory to construct the destination path and the log prefix in any log
entries. If this is a dry run, then don't actually remove anything.
'''
dump.remove_data_source_dumps(make_dump_path(config), 'MySQL', log_prefix, dry_run)
dump.remove_data_source_dumps(
make_dump_path(borgmatic_runtime_directory), 'MySQL', log_prefix, dry_run
)
def make_data_source_dump_patterns(databases, config, log_prefix, name=None): # pragma: no cover
def make_data_source_dump_patterns(
databases, config, log_prefix, borgmatic_runtime_directory, name=None
): # pragma: no cover
'''
Given a sequence of configurations dicts, a configuration dict, a prefix to log with, and a
database name to match, return the corresponding glob patterns to match the database dump in an
archive.
Given a sequence of configurations dicts, a configuration dict, a prefix to log with, the
borgmatic runtime directory, and a database name to match, return the corresponding glob
patterns to match the database dump in an archive.
'''
borgmatic_source_directory = borgmatic.config.paths.get_borgmatic_source_directory(config)
return (
dump.make_data_source_dump_filename(make_dump_path('borgmatic'), name, hostname='*'),
dump.make_data_source_dump_filename(
make_dump_path(config, 'borgmatic'), name, hostname='*'
make_dump_path(borgmatic_runtime_directory), name, hostname='*'
),
dump.make_data_source_dump_filename(make_dump_path(config), name, hostname='*'),
dump.make_data_source_dump_filename(
make_dump_path(config, borgmatic_source_directory), name, hostname='*'
make_dump_path(borgmatic_source_directory), name, hostname='*'
),
)
def restore_data_source_dump(
hook_config, config, log_prefix, data_source, dry_run, extract_process, connection_params
hook_config,
config,
log_prefix,
data_source,
dry_run,
extract_process,
connection_params,
borgmatic_runtime_directory,
):
'''
Restore a database from the given extract stream. The database is supplied as a data source
configuration dict, but the given hook configuration is ignored. The given configuration dict is
used to construct the destination path, and the given log prefix is used for any log entries. If
this is a dry run, then don't actually restore anything. Trigger the given active extract
process (an instance of subprocess.Popen) to produce output to consume.
configuration dict, but the given hook configuration is ignored. The given log prefix is used
for any log entries. If this is a dry run, then don't actually restore anything. Trigger the
given active extract process (an instance of subprocess.Popen) to produce output to consume.
'''
dry_run_label = ' (dry run; not actually restoring anything)' if dry_run else ''
hostname = connection_params['hostname'] or data_source.get(

View File

@ -16,15 +16,11 @@ from borgmatic.hooks import dump
logger = logging.getLogger(__name__)
def make_dump_path(config, base_directory=None): # pragma: no cover
def make_dump_path(base_directory): # pragma: no cover
'''
Given a configuration dict and an optional base directory, make the corresponding dump path. If
a base directory isn't provided, use the borgmatic runtime directory.
Given a base directory, make the corresponding dump path.
'''
return dump.make_data_source_dump_path(
base_directory or borgmatic.config.paths.get_borgmatic_runtime_directory(config),
'postgresql_databases',
)
return dump.make_data_source_dump_path(base_directory, 'postgresql_databases')
def make_extra_environment(database, restore_connection_params=None):
@ -108,12 +104,12 @@ def use_streaming(databases, config, log_prefix):
return any(database.get('format') != 'directory' for database in databases)
def dump_data_sources(databases, config, log_prefix, dry_run):
def dump_data_sources(databases, config, log_prefix, borgmatic_runtime_directory, dry_run):
'''
Dump the given PostgreSQL databases to a named pipe. The databases are supplied as a sequence of
dicts, one dict describing each database as per the configuration schema. Use the given
configuration dict to construct the destination path and the given log prefix in any log
entries.
borgmatic runtime directory to construct the destination path and the given log prefix in any
log entries.
Return a sequence of subprocess.Popen instances for the dump processes ready to spew to a named
pipe. But if this is a dry run, then don't actually dump anything and return an empty sequence.
@ -127,7 +123,7 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
for database in databases:
extra_environment = make_extra_environment(database)
dump_path = make_dump_path(config)
dump_path = make_dump_path(borgmatic_runtime_directory)
dump_database_names = database_names_to_dump(
database, extra_environment, log_prefix, dry_run
)
@ -210,43 +206,57 @@ def dump_data_sources(databases, config, log_prefix, dry_run):
return processes
def remove_data_source_dumps(databases, config, log_prefix, dry_run): # pragma: no cover
def remove_data_source_dumps(
databases, config, log_prefix, borgmatic_runtime_directory, dry_run
): # pragma: no cover
'''
Remove all database dump files for this hook regardless of the given databases. Use the given
configuration dict to construct the destination path and the log prefix in any log entries. If
this is a dry run, then don't actually remove anything.
Remove all database dump files for this hook regardless of the given databases. Use the
borgmatic runtime directory to construct the destination path and the log prefix in any log
entries. If this is a dry run, then don't actually remove anything.
'''
dump.remove_data_source_dumps(make_dump_path(config), 'PostgreSQL', log_prefix, dry_run)
dump.remove_data_source_dumps(
make_dump_path(borgmatic_runtime_directory), 'PostgreSQL', log_prefix, dry_run
)
def make_data_source_dump_patterns(databases, config, log_prefix, name=None): # pragma: no cover
def make_data_source_dump_patterns(
databases, config, log_prefix, borgmatic_runtime_directory, name=None
): # pragma: no cover
'''
Given a sequence of configurations dicts, a configuration dict, a prefix to log with, and a
database name to match, return the corresponding glob patterns to match the database dump in an
archive.
Given a sequence of configurations dicts, a configuration dict, a prefix to log with, the
borgmatic runtime directory, and a database name to match, return the corresponding glob
patterns to match the database dump in an archive.
'''
borgmatic_source_directory = borgmatic.config.paths.get_borgmatic_source_directory(config)
return (
dump.make_data_source_dump_filename(make_dump_path('borgmatic'), name, hostname='*'),
dump.make_data_source_dump_filename(
make_dump_path(config, 'borgmatic'), name, hostname='*'
make_dump_path(borgmatic_runtime_directory), name, hostname='