Skip to content

Batch requests for docker image size #170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jovandeginste wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Batch requests for docker image size #170

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 31 additions & 9 deletions artifactory_cleanup/rules/docker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,8 @@
from artifactory_cleanup.rules.base import ArtifactsList
from artifactory_cleanup.rules.utils import to_masks

import os

ctx_mgr_block, ctx_mgr_test = get_context_managers()


Expand All @@ -20,6 +22,7 @@ class RuleForDocker(Rule):

MANIFEST_FILENAME = "manifest.json"
FAT_MANIFEST_FILENAME = "list.manifest.json"
BATCH_SIZE = int(os.getenv("ARTIFACTORY_CLEANUP_DOCKER_RULE_BATCH_SIZE", 40))

def get_docker_images_list(self, docker_repo):
url = f"/api/docker/{docker_repo}/v2/_catalog"
Expand Down Expand Up @@ -60,21 +63,40 @@ def _collect_docker_size(self, artifacts):
if sizes_collected:
return

docker_repos = list(set(x["repo"] for x in artifacts))
if docker_repos:
images_sizes = defaultdict(int)
print("Fetching docker image sizes...")
for i in range(0, len(artifacts), self.BATCH_SIZE):

slice = artifacts[i : i + self.BATCH_SIZE]
Comment thread
jovandeginste marked this conversation as resolved.
paths = {
"$or": [
{
"$and": [
{
"repo": artifact["repo"],
"path": f"{artifact['path']}/{artifact['name']}",
}
]
}
for artifact in slice
]
}

aql = ArtifactoryPath(self.session.base_url, session=self.session)
args = ["items.find", {"$or": [{"repo": repo} for repo in docker_repos]}]
artifacts_list = aql.aql(*args)
args = [
"items.find",
paths,
]

images_sizes = defaultdict(int)
artifacts_list = aql.aql(*args)
for docker_layer in artifacts_list:
image_key = (docker_layer["repo"], docker_layer["path"])
images_sizes[image_key] += docker_layer["size"]

for artifact in artifacts:
image = f"{artifact['path']}/{artifact['name']}"
image_key = (artifact["repo"], image)
artifact["size"] = images_sizes.get(image_key, 0)
for artifact in artifacts:
image = f"{artifact['path']}/{artifact['name']}"
image_key = (artifact["repo"], image)
artifact["size"] = images_sizes.get(image_key, 0)

def aql_add_filter(self, filters):
filters.append({'$or': [{'name': {'$match': self.MANIFEST_FILENAME}}, {'name': {'$match': self.FAT_MANIFEST_FILENAME}}]})
Expand Down