1
0
mirror of https://github.com/quay/quay.git synced 2026-01-27 18:42:52 +03:00
Files
quay/workers/storagereplication.py
Kurtis Mullins 38be6d05d0 Python 3 (#153)
* Convert all Python2 to Python3 syntax.

* Removes oauth2lib dependency

* Replace mockredis with fakeredis

* byte/str conversions

* Removes nonexisting __nonzero__ in Python3

* Python3 Dockerfile and related

* [PROJQUAY-98] Replace resumablehashlib with rehash

* PROJQUAY-123 - replace gpgme with python3-gpg

* [PROJQUAY-135] Fix unhashable class error

* Update external dependencies for Python 3

- Move github.com/app-registry/appr to github.com/quay/appr
- github.com/coderanger/supervisor-stdout
- github.com/DevTable/container-cloud-config
- Update to latest mockldap with changes applied from coreos/mockldap
- Update dependencies in requirements.txt and requirements-dev.txt

* Default FLOAT_REPR function to str in json encoder and removes keyword assignment

True, False, and str were not keywords in Python2...

* [PROJQUAY-165] Replace package `bencode` with `bencode.py`

- Bencode is not compatible with Python 3.x and is no longer
  maintained. Bencode.py appears to be a drop-in replacement/fork
  that is compatible with Python 3.

* Make sure monkey.patch is called before anything else (

* Removes anunidecode dependency and replaces it with text_unidecode

* Base64 encode/decode pickle dumps/loads when storing value in DB

Base64 encodes/decodes the serialized values when storing them in the
DB. Also make sure to return a Python3 string instead of a Bytes when
coercing for db, otherwise, Postgres' TEXT field will convert it into
a hex representation when storing the value.

* Implement __hash__ on Digest class

In Python 3, if a class defines __eq__() but not __hash__(), its
instances will not be usable as items in hashable collections (e.g sets).

* Remove basestring check

* Fix expected message in credentials tests

* Fix usage of Cryptography.Fernet for Python3 (#219)

- Specifically, this addresses the issue where Byte<->String
  conversions weren't being applied correctly.

* Fix utils

- tar+stream layer format utils
- filelike util

* Fix storage tests

* Fix endpoint tests

* Fix workers tests

* Fix docker's empty layer bytes

* Fix registry tests

* Appr

* Enable CI for Python 3.6

* Skip buildman tests

Skip buildman tests while it's being rewritten to allow ci to pass.

* Install swig for CI

* Update expected exception type in redis validation test

* Fix gpg signing calls

Fix gpg calls for updated gpg wrapper, and add signing tests.

* Convert / to // for Python3 integer division

* WIP: Update buildman to use asyncio instead of trollius.

This dependency is considered deprecated/abandoned and was only
used as an implementation/backport of asyncio on Python 2.x
This is a work in progress, and is included in the PR just to get the
rest of the tests passing. The builder is actually being rewritten.

* Target Python 3.8

* Removes unused files

- Removes unused files that were added accidentally while rebasing
- Small fixes/cleanup
- TODO tasks comments

* Add TODO to verify rehash backward compat with resumablehashlib

* Revert "[PROJQUAY-135] Fix unhashable class error" and implements __hash__ instead.

This reverts commit 735e38e3c1d072bf50ea864bc7e119a55d3a8976.
Instead, defines __hash__ for encryped fields class, using the parent
field's implementation.

* Remove some unused files ad imports

Co-authored-by: Kenny Lee Sin Cheong <kenny.lee@redhat.com>
Co-authored-by: Tom McKay <thomasmckay@redhat.com>
2020-06-05 16:50:13 -04:00

199 lines
7.0 KiB
Python

import logging
import time
import features
from app import app, storage as app_storage, image_replication_queue
from data.database import CloseForLongOperation
from data import model
from workers.queueworker import QueueWorker, WorkerUnhealthyException, JobException
from util.log import logfile_path
logger = logging.getLogger(__name__)
POLL_PERIOD_SECONDS = 10
RESERVATION_SECONDS = app.config.get("STORAGE_REPLICATION_PROCESSING_SECONDS", 60 * 20)
class StorageReplicationWorker(QueueWorker):
def process_queue_item(self, job_details):
storage_uuid = job_details["storage_id"]
namespace_id = job_details["namespace_user_id"]
logger.debug(
"Starting replication of image storage %s under namespace %s",
storage_uuid,
namespace_id,
)
try:
namespace = model.user.get_namespace_user_by_user_id(namespace_id)
except model.user.InvalidUsernameException:
logger.exception(
"Exception when looking up namespace %s for replication of image storage %s",
namespace_id,
storage_uuid,
)
return
self.replicate_storage(namespace, storage_uuid, app_storage)
def _backoff_check_exists(self, location, path, storage, backoff_check=True):
for retry in range(0, 4):
if storage.exists([location], path):
return True
if not backoff_check:
return False
seconds = pow(2, retry) * 2
logger.debug(
"Cannot find path `%s` in location %s (try #%s). Sleeping for %s seconds",
path,
location,
retry,
seconds,
)
time.sleep(seconds)
return False
def replicate_storage(self, namespace, storage_uuid, storage, backoff_check=True):
# Lookup the namespace and its associated regions.
if not namespace:
logger.debug("Unknown namespace when trying to replicate storage %s", storage_uuid)
return
locations = model.user.get_region_locations(namespace)
# Lookup the image storage.
try:
partial_storage = model.storage.get_storage_by_uuid(storage_uuid)
except model.InvalidImageException:
logger.debug("Unknown storage: %s", storage_uuid)
return
# Check to see if the image is at all the required locations.
locations_required = locations | set(storage.default_locations)
locations_missing = locations_required - set(partial_storage.locations)
logger.debug(
"For replication of storage %s under namespace %s: %s required; %s missing",
storage_uuid,
namespace.username,
locations_required,
locations_missing,
)
if not locations_missing:
logger.debug(
"No missing locations for storage %s under namespace %s. Required: %s",
storage_uuid,
namespace.username,
locations_required,
)
return
# For any missing storage locations, initiate a copy.
existing_location = list(partial_storage.locations)[0]
path_to_copy = model.storage.get_layer_path(partial_storage)
# Lookup and ensure the existing location exists.
if not self._backoff_check_exists(existing_location, path_to_copy, storage, backoff_check):
logger.warning(
"Cannot find image storage %s in existing location %s; stopping replication",
storage_uuid,
existing_location,
)
raise JobException()
# For each missing location, copy over the storage.
for location in locations_missing:
logger.debug(
"Starting copy of storage %s to location %s from %s",
partial_storage.uuid,
location,
existing_location,
)
# Copy the binary data.
copied = False
try:
with CloseForLongOperation(app.config):
storage.copy_between(path_to_copy, existing_location, location)
copied = True
except IOError:
logger.exception(
"Failed to copy path `%s` of image storage %s to location %s",
path_to_copy,
partial_storage.uuid,
location,
)
raise JobException()
except:
logger.exception(
"Unknown exception when copying path %s of image storage %s to loc %s",
path_to_copy,
partial_storage.uuid,
location,
)
raise WorkerUnhealthyException()
if copied:
# Verify the data was copied to the target storage, to ensure that there are no cases
# where we write the placement without knowing the data is present.
if not self._backoff_check_exists(location, path_to_copy, storage, backoff_check):
logger.warning(
"Failed to find path `%s` in location `%s` after copy",
path_to_copy,
location,
)
raise JobException()
# Create the storage location record for the storage now that the copy has
# completed.
model.storage.add_storage_placement(partial_storage, location)
logger.debug(
"Finished copy of image storage %s to location %s from %s",
partial_storage.uuid,
location,
existing_location,
)
logger.debug(
"Completed replication of image storage %s to locations %s from %s",
partial_storage.uuid,
locations_missing,
existing_location,
)
if __name__ == "__main__":
logging.config.fileConfig(logfile_path(debug=False), disable_existing_loggers=False)
has_local_storage = False
if features.STORAGE_REPLICATION:
for storage_type, _ in list(app.config.get("DISTRIBUTED_STORAGE_CONFIG", {}).values()):
if storage_type == "LocalStorage":
has_local_storage = True
break
if not features.STORAGE_REPLICATION or has_local_storage:
if has_local_storage:
logger.error("Storage replication can't be used with local storage")
else:
logger.debug("Full storage replication disabled; skipping")
while True:
time.sleep(10000)
logger.debug("Starting replication worker")
worker = StorageReplicationWorker(
image_replication_queue,
poll_period_seconds=POLL_PERIOD_SECONDS,
reservation_seconds=RESERVATION_SECONDS,
)
worker.start()