1
0
mirror of https://github.com/quay/quay.git synced 2025-04-19 21:42:17 +03:00
quay/workers/blobuploadcleanupworker/blobuploadcleanupworker.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- Bencode is not compatible with Python 3.x and is no longer
  maintained.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

77 lines
2.7 KiB
Python

import logging
import logging.config
from datetime import timedelta, datetime
from app import app, storage
from data.database import UseThenDisconnect
from workers.blobuploadcleanupworker.models_pre_oci import pre_oci_model as model
from workers.worker import Worker
from util.log import logfile_path
from util.locking import GlobalLock, LockNotAcquiredException
logger = logging.getLogger(__name__)
DELETION_DATE_THRESHOLD = timedelta(days=2)
BLOBUPLOAD_CLEANUP_FREQUENCY = app.config.get("BLOBUPLOAD_CLEANUP_FREQUENCY", 60 * 60)
LOCK_TTL = 60 * 20 # 20 minutes
class BlobUploadCleanupWorker(Worker):
def __init__(self):
super(BlobUploadCleanupWorker, self).__init__()
self.add_operation(self._try_cleanup_uploads, BLOBUPLOAD_CLEANUP_FREQUENCY)
def _try_cleanup_uploads(self):
"""
Performs garbage collection on the blobupload table.
"""
try:
with GlobalLock("BLOB_CLEANUP", lock_ttl=LOCK_TTL):
self._cleanup_uploads()
except LockNotAcquiredException:
logger.debug("Could not acquire global lock for blob upload cleanup worker")
return
def _cleanup_uploads(self):
"""
Performs cleanup on the blobupload table.
"""
logger.debug("Performing blob upload cleanup")
while True:
# Find all blob uploads older than the threshold (typically a week) and delete them.
with UseThenDisconnect(app.config):
stale_upload = model.get_stale_blob_upload(DELETION_DATE_THRESHOLD)
if stale_upload is None:
logger.debug("No additional stale blob uploads found")
return
# Remove the stale upload from storage.
logger.debug("Removing stale blob upload %s", stale_upload.uuid)
assert stale_upload.created <= (datetime.utcnow() - DELETION_DATE_THRESHOLD)
try:
storage.cancel_chunked_upload(
[stale_upload.location_name], stale_upload.uuid, stale_upload.storage_metadata
)
except Exception as ex:
logger.debug(
"Got error when trying to cancel chunked upload %s: %s",
stale_upload.uuid,
str(ex),
)
# Delete the stale upload's row.
with UseThenDisconnect(app.config):
model.delete_blob_upload(stale_upload)
logger.debug("Removed stale blob upload %s", stale_upload.uuid)
if __name__ == "__main__":
logging.config.fileConfig(logfile_path(debug=False), disable_existing_loggers=False)
worker = BlobUploadCleanupWorker()
worker.start()