1
0
mirror of https://github.com/quay/quay.git synced 2026-01-26 06:21:37 +03:00
Files
quay/tools/deleteinvalidlayers.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- Bencode is not compatible with Python 3.x and is no longer
  maintained.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

103 lines
2.9 KiB
Python

from data.database import (
ImageStorage,
Image,
ImageStoragePlacement,
ImageStorageLocation,
RepositoryTag,
)
from data import model
from app import storage as storage_system
from tqdm import tqdm
def find_broken_storages():
broken_storages = set()
print("Checking storages...")
placement_count = ImageStoragePlacement.select().count()
placements = (
ImageStoragePlacement.select()
.join(ImageStorage)
.switch(ImageStoragePlacement)
.join(ImageStorageLocation)
)
for placement in tqdm(placements, total=placement_count):
path = model.storage.get_layer_path(placement.storage)
if not storage_system.exists([placement.location.name], path):
broken_storages.add(placement.storage.id)
return list(broken_storages)
def delete_broken_layers():
result = input('Please make sure your registry is not running and enter "GO" to continue: ')
if result != "GO":
print("Declined to run")
return
broken_storages = find_broken_storages()
if not broken_storages:
print("No broken layers found")
return
# Find all the images referencing the broken layers.
print("Finding broken images...")
IMAGE_BATCH_SIZE = 100
all_images = []
for i in tqdm(list(range(0, len(broken_storages) / IMAGE_BATCH_SIZE))):
start = i * IMAGE_BATCH_SIZE
end = (i + 1) * IMAGE_BATCH_SIZE
images = (
Image.select().join(ImageStorage).where(Image.storage << broken_storages[start:end])
)
all_images.extend(images)
if not all_images:
print("No broken layers found")
return
# Find all the tags containing the images.
print("Finding associated tags for %s images..." % len(all_images))
all_tags = {}
for image in tqdm(all_images):
query = model.tag.get_matching_tags(
image.docker_image_id, image.storage.uuid, RepositoryTag
)
for tag in query:
all_tags[tag.id] = tag
# Ask to delete them.
print("")
print("The following tags were found to reference invalid images:")
for tag in list(all_tags.values()):
print("%s/%s: %s" % (tag.repository.namespace_user.username, tag.repository.name, tag.name))
if not all_tags:
print("(Tags in time machine)")
print("")
result = input(
'Enter "DELETENOW" to delete these tags and ALL associated images (THIS IS PERMANENT): '
)
if result != "DELETENOW":
print("Declined to delete")
return
print("")
print("Marking tags to be GCed...")
for tag in tqdm(list(all_tags.values())):
tag.lifetime_end_ts = 0
tag.save()
print("GCing all repositories...")
for tag in tqdm(list(all_tags.values())):
model.repository.garbage_collect_repo(tag.repository)
print("All done! You may now restart your registry.")
delete_broken_layers()