ストレージ管理を自動化する

export GL_TOKEN=xxx
export GL_GROUP_ID=56595735

pip3 install python-gitlab
python3 get_all_projects_top_level_namespace_storage_analysis_cleanup_example.py

Project Developer Evangelism and Technical Marketing at GitLab  / playground / Artifact generator group / Gen Job Artifacts 4 statistics: {
    "commit_count": 2,
    "storage_size": 90241770,
    "repository_size": 3521,
    "wiki_size": 0,
    "lfs_objects_size": 0,
    "job_artifacts_size": 90238249,
    "pipeline_artifacts_size": 0,
    "packages_size": 0,
    "snippets_size": 0,
    "uploads_size": 0
}

[
    {
        "file_type": "archive",
        "size": 1049089,
        "filename": "artifacts.zip",
        "file_format": "zip"
    },
    {
        "file_type": "metadata",
        "size": 157,
        "filename": "metadata.gz",
        "file_format": "gzip"
    },
    {
        "file_type": "trace",
        "size": 3146,
        "filename": "job.log",
        "file_format": null
    }
]

[
    {
        "file_type": "archive",
        "size": 1049089,
        "filename": "artifacts.zip",
        "file_format": "zip"
    },
    {
        "file_type": "metadata",
        "size": 157,
        "filename": "metadata.gz",
        "file_format": "gzip"
    },
    {
        "file_type": "trace",
        "size": 3146,
        "filename": "job.log",
        "file_format": null
    }
]

   ci_job_artifacts = []

    for project in projects:
        project_obj = gl.projects.get(project.id)

        jobs = project.jobs.list(pagination="keyset", order_by="id", per_page=100, iterator=True)

        for job in jobs:
            artifacts = job.attributes['artifacts']
            #print("DEBUG: ID {i}: {a}".format(i=job.id, a=json.dumps(artifacts, indent=4)))
            if not artifacts:
                continue

            for a in artifacts:
                data = {
                    "project_id": project_obj.id,
                    "project_web_url": project_obj.name,
                    "project_path_with_namespace": project_obj.path_with_namespace,
                    "job_id": job.id,
                    "artifact_filename": a['filename'],
                    "artifact_file_type": a['file_type'],
                    "artifact_size": a['size']
                }

                ci_job_artifacts.append(data)

    print("\nDone collecting data.")

    if len(ci_job_artifacts) > 0:
        print("| Project | Job | Artifact name | Artifact type | Artifact size |\n|---------|-----|---------------|---------------|---------------|") # Start markdown friendly table
        for artifact in ci_job_artifacts:
            print('| [{project_name}]({project_web_url}) | {job_name} | {artifact_name} | {artifact_type} | {artifact_size} |'.format(project_name=artifact['project_path_with_namespace'], project_web_url=artifact['project_web_url'], job_name=artifact['job_id'], artifact_name=artifact['artifact_filename'], artifact_type=artifact['artifact_file_type'], artifact_size=render_size_mb(artifact['artifact_size'])))
    else:
        print("No artifacts found.")

$ python3 get_all_projects_top_level_namespace_storage_analysis_cleanup_example.py

| Project | Job | Artifact name | Artifact type | Artifact size |
|---------|-----|---------------|---------------|---------------|
| [gitlab-da/playground/artifact-gen-group/gen-job-artifacts-4](Gen Job Artifacts 4) | 4828297946 | artifacts.zip | archive | 50.0154 |
| [gitlab-da/playground/artifact-gen-group/gen-job-artifacts-4](Gen Job Artifacts 4) | 4828297946 | metadata.gz | metadata | 0.0001 |
| [gitlab-da/playground/artifact-gen-group/gen-job-artifacts-4](Gen Job Artifacts 4) | 4828297946 | job.log | trace | 0.0030 |
| [gitlab-da/playground/artifact-gen-group/gen-job-artifacts-4](Gen Job Artifacts 4) | 4828297945 | artifacts.zip | archive | 20.0063 |
| [gitlab-da/playground/artifact-gen-group/gen-job-artifacts-4](Gen Job Artifacts 4) | 4828297945 | metadata.gz | metadata | 0.0001 |
| [gitlab-da/playground/artifact-gen-group/gen-job-artifacts-4](Gen Job Artifacts 4) | 4828297945 | job.log | trace | 0.0030 |

   for project in projects:
        project_obj = gl.projects.get(project.id)

        jobs = project.jobs.list(pagination="keyset", order_by="id", per_page=100, iterator=True)

        for job in jobs:
            artifacts = job.attributes['artifacts']
            if not artifacts:
                continue

            # Advanced filtering: Age and Size
            # Example: 90 days, 10 MB threshold (TODO: Make this configurable)
            threshold_age = 90 * 24 * 60 * 60
            threshold_size = 10 * 1024 * 1024

            # job age, need to parse API format: 2023-08-08T22:41:08.270Z
            created_at = datetime.datetime.strptime(job.created_at, '%Y-%m-%dT%H:%M:%S.%fZ')
            now = datetime.datetime.now()
            age = (now - created_at).total_seconds()
            # Shorter: Use a function
            # age = calculate_age(job.created_at)

            for a in artifacts:
                # Analysis collection code removed for readability

                # Advanced filtering: match job artifacts age and size against thresholds
                if (float(age) > float(threshold_age)) or (float(a['size']) > float(threshold_size)):
                    # mark job for deletion (cannot delete inside the loop)
                    jobs_marked_delete_artifacts.append(job)

    print("\nDone collecting data.")

    # Advanced filtering: Delete all job artifacts marked to being deleted.
    for job in jobs_marked_delete_artifacts:
        # delete the artifact
        print("DEBUG", job)
        job.delete_artifacts()

    # Print collection summary (removed for readability)

glab api --method GET projects/$GL_PROJECT_ID/jobs | jq --compact-output '.[]' | jq --compact-output '.id'

4836226184
4836226183
4836226181
4836226180

glab api --method POST projects/$GL_PROJECT_ID/jobs/4836226180/erase | jq --compact-output '.name,.status'
"generate-package: [1]"
"success"

    for job in jobs_marked_delete_artifacts:
        # delete the artifacts and job log
        print("DEBUG", job)
        #job.delete_artifacts()
        job.erase()
        # Sleep for 1 second
        time.sleep(1)

export GL_PROJECT_ID=48349590

glab api --method GET projects/$GL_PROJECT_ID/pipelines | jq --compact-output '.[]' | jq --compact-output '.id,.created_at'
960031926
"2023-08-08T22:09:52.745Z"
959884072
"2023-08-08T18:59:47.581Z"

glab api --method DELETE projects/$GL_PROJECT_ID/pipelines/960031926

glab api --method GET projects/$GL_PROJECT_ID/pipelines | jq --compact-output '.[]' | jq --compact-output '.id,.created_at'
959884072
"2023-08-08T18:59:47.581Z"

    ci_job_artifacts_expiry = {}

    # Loop over projects, fetch .gitlab-ci.yml, run the linter to get the full translated config, and extract the `artifacts:` setting
    # https://python-gitlab.readthedocs.io/en/stable/gl_objects/ci_lint.html
    for project in projects:
            project_obj = gl.projects.get(project.id)
            project_name = project_obj.name
            project_web_url = project_obj.web_url
            try:
                lint_result = project.ci_lint.get()
                if lint_result.merged_yaml is None:
                    continue

                ci_pipeline = yaml.safe_load(lint_result.merged_yaml)
                #print("Project {p} Config\n{c}\n\n".format(p=project_name, c=json.dumps(ci_pipeline, indent=4)))

                for k in ci_pipeline:
                    v = ci_pipeline[k]
                    # This is a job object with `script` attribute
                    if isinstance(v, dict) and 'script' in v:
                        print(".", end="", flush=True) # Get some feedback that it is still looping
                        artifacts = v['artifacts'] if 'artifacts' in v else {}

                        print("Project {p} job {j} artifacts {a}".format(p=project_name, j=k, a=json.dumps(artifacts, indent=4)))

                        expire_in = None
                        if 'expire_in' in artifacts:
                            expire_in = artifacts['expire_in']

                        store_key = project_web_url + '_' + k
                        ci_job_artifacts_expiry[store_key] = { 'project_web_url': project_web_url,
                                                        'project_name': project_name,
                                                        'job_name': k,
                                                        'artifacts_expiry': expire_in}

            except Exception as e:
                 print(f"Exception searching artifacts on ci_pipelines: {e}".format(e=e))

    if len(ci_job_artifacts_expiry) > 0:
        print("| Project | Job | Artifact expiry |\n|---------|-----|-----------------|") #Start markdown friendly table
        for k, details in ci_job_artifacts_expiry.items():
            if details['job_name'][0] == '.':
                continue # ignore job templates that start with a '.'
            print(f'| [{ details["project_name"] }]({details["project_web_url"]}) | { details["job_name"] } | { details["artifacts_expiry"] if details["artifacts_expiry"] is not None else "❌ N/A" } |')

export GL_GROUP_ID=56595735

# Install script dependencies
python3 -m pip install 'python-gitlab[yaml]'

python3 get_all_cicd_config_artifacts_expiry.py

| Project | Job | Artifact expiry |
|---------|-----|-----------------|
| [Gen Job Artifacts 4](https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-4) | generator | 30 days |
| [Gen Job Artifacts with expiry and included jobs](https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-expiry-included-jobs) | included-job10 | 10 days |
| [Gen Job Artifacts with expiry and included jobs](https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-expiry-included-jobs) | included-job1 | 1 days |
| [Gen Job Artifacts with expiry and included jobs](https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-expiry-included-jobs) | included-job30 | 30 days |
| [Gen Job Artifacts with expiry and included jobs](https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-expiry-included-jobs) | generator | 30 days |
| [Gen Job Artifacts 2](https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-2) | generator | ❌ N/A |
| [Gen Job Artifacts 1](https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-1) | generator | ❌ N/A |

# https://gitlab.com/gitlab-da/playground/artifact-gen-group/gen-job-artifacts-expiry-included-jobs
export GL_PROJECT_ID=48349263

glab api --method GET projects/$GL_PROJECT_ID/search --field "scope=blobs" --field "search=expire_in filename:*.yml"

default:
    artifacts:
        expire_in: 1 week

        repositories = project.repositories.list(iterator=True, size=True)
        if len(repositories) > 0:
            repository = repositories.pop()
            tags = repository.tags.list()

            # Cleanup: Keep only the latest tag
            repository.tags.delete_in_bulk(keep_n=1)
            # Cleanup: Delete all tags older than 1 month
            repository.tags.delete_in_bulk(older_than="1m")
            # Cleanup: Delete all tags matching the regex `v.*`, and keep the latest 2 tags
            repository.tags.delete_in_bulk(name_regex_delete="v.+", keep_n=2)

export GL_PROJECT_ID=48057080

echo '{"container_expiration_policy_attributes":{"cadence":"1month","enabled":true,"keep_n":1,"older_than":"14d","name_regex":".*","name_regex_keep":".*-main"}}' | glab api --method PUT --header 'Content-Type: application/json;charset=UTF-8' projects/$GL_PROJECT_ID --input -

...

  "container_expiration_policy": {
    "cadence": "1month",
    "enabled": true,
    "keep_n": 1,
    "older_than": "14d",
    "name_regex": ".*",
    "name_regex_keep": ".*-main",
    "next_run_at": "2023-09-08T21:16:25.354Z"
  },

# https://gitlab.com/gitlab-da/playground/container-package-gen-group/generic-package-generator
export GL_PROJECT_ID=48377643

glab api --method GET projects/$GL_PROJECT_ID/packages | jq --compact-output '.[]' | jq --compact-output '.id,.name,.package_type'
16669383
"generator"
"generic"
16671352
"generator"
"generic"
16672235
"generator"
"generic"
16672237
"generator"
"generic"

glab api --method GET projects/$GL_PROJECT_ID/packages/16669383/package_files | jq --compact-output '.[]' |
 jq --compact-output '.package_id,.file_name,.size'

16669383
"nighly.tar.gz"
10487563

        packages = project.packages.list(order_by="created_at")

        for package in packages:

            package_files = package.package_files.list()
            for package_file in package_files:
                print("Package name: {p} File name: {f} Size {s}".format(
                    p=package.name, f=package_file.file_name, s=render_size_mb(package_file.size)))

glab api --method DELETE projects/$GL_PROJECT_ID/packages/16669383

        packages = project.packages.list(order_by="created_at")
        for package in packages:
            package_size = 0.0

            package_files = package.package_files.list()
            for package_file in package_files:
                print("Package name: {p} File name: {f} Size {s}".format(
                    p=package.name, f=package_file.file_name, s=render_size_mb(package_file.size)))

                package_size =+ package_file.size

            print("Package size: {s}\n\n".format(s=render_size_mb(package_size)))

            threshold_size = 10 * 1024 * 1024

            if (package_size > float(threshold_size)):
                print("Package size {s} > threshold {t}, deleting package.".format(
                    s=render_size_mb(package_size), t=render_size_mb(threshold_size)))
                package.delete()

            threshold_age = 90 * 24 * 60 * 60
            package_age = created_at = calculate_age(package.created_at)

            if (float(package_age > float(threshold_age))):
                print("Package age {a} > threshold {t}, deleting package.".format(
                    a=render_age_time(package_age), t=render_age_time(threshold_age)))
                package.delete()

Package name: generator File name: nighly.tar.gz Size 10.0017
Package size: 10.0017
Package size 10.0017 > threshold 10.0000, deleting package.

Package name: generator File name: 1-nightly.tar.gz Size 1.0004
Package size: 1.0004

Package name: generator File name: 10-nightly.tar.gz Size 10.0018
Package name: generator File name: 20-nightly.tar.gz Size 20.0033
Package size: 20.0033
Package size 20.0033 > threshold 10.0000, deleting package.

# Current Unix timestamp
date +%s

# Convert `created_at` date time with timezone to Unix timestamp
date -d '2023-08-08T18:59:47.581Z' +%s

def render_size_mb(v):
    return "%.4f" % (v / 1024 / 1024)

def render_age_time(v):
    return str(datetime.timedelta(seconds = v))

# Convert `created_at` date time with timezone to Unix timestamp
def calculate_age(created_at_datetime):
    created_at_ts = datetime.datetime.strptime(created_at_datetime, '%Y-%m-%dT%H:%M:%S.%fZ')
    now = datetime.datetime.now()
    return (now - created_at_ts).total_seconds()

include:
    - remote: https://gitlab.com/gitlab-da/use-cases/efficiency/job-artifact-generator/-/raw/main/.gitlab-ci.yml

generator:
    parallel:
        matrix:
            - MB_COUNT: [1, 5, 10, 20, 50]

# .gitlab-ci.yml
include:
    - include_jobs.yml

default:
  artifacts:
      paths:
          - '*.txt'

.gen-tmpl:
    script:
        - dd if=/dev/urandom of=${$MB_COUNT}.txt bs=1048576 count=${$MB_COUNT}

generator:
    extends: [.gen-tmpl]
    parallel:
        matrix:
            - MB_COUNT: [1, 5, 10, 20, 50]
    artifacts:
        untracked: false
        when: on_success
        expire_in: 30 days

# include_jobs.yml
.includeme:
    script:
        - dd if=/dev/urandom of=1.txt bs=1048576 count=1

included-job10:
    script:
        - echo "Servus"
        - !reference [.includeme, script]
    artifacts:
        untracked: false
        when: on_success
        expire_in: 10 days

included-job1:
    script:
        - echo "Gruezi"
        - !reference [.includeme, script]
    artifacts:
        untracked: false
        when: on_success
        expire_in: 1 days

included-job30:
    script:
        - echo "Grias di"
        - !reference [.includeme, script]
    artifacts:
        untracked: false
        when: on_success
        expire_in: 30 days

generate-package:
  parallel:
    matrix:
      - MB_COUNT: [1, 5, 10, 20]
  before_script:
    - apt update && apt -y install curl
  script:
    - dd if=/dev/urandom of="${MB_COUNT}.txt" bs=1048576 count=${MB_COUNT}
    - tar czf "generated-$MB_COUNT-nighly-`date +%s`.tar.gz" "${MB_COUNT}.txt"
    - 'curl --header "JOB-TOKEN: $CI_JOB_TOKEN" --upload-file "generated-$MB_COUNT-nighly-`date +%s`.tar.gz" "${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/generic/generator/`date +%s`/${MB_COUNT}-nightly.tar.gz"'

  artifacts:
    paths:
      - '*.tar.gz'