Merge branch '244848-skip-cleanup-for-forks' into 'master'

Refuse to perform an LFS clean on projects that are fork roots

Closes #244848

See merge request gitlab-org/gitlab!41703

changelogs/unreleased/244848-skip-cleanup-for-forks.yml

+---
+title: Refuse to perform an LFS clean on projects that are fork roots
+merge_request: 41703
+author:
+type: fixed

doc/raketasks/cleanup.md

@@ -10,6 +10,10 @@ DANGER: **Danger:**
 Do not run this within 12 hours of a GitLab upgrade. This is to ensure that all background migrations
 have finished, which otherwise may lead to data loss.
 
+CAUTION: **WARNING:**
+Removing LFS files from a project with forks is currently unsafe. The rake task
+will refuse to run on projects with forks.
+
 When you remove LFS files from a repository's history, they become orphaned and continue to consume
 disk space. With this Rake task, you can remove invalid references from the database, which
 will allow garbage collection of LFS files.

lib/gitlab/cleanup/orphan_lfs_file_references.rb

@@ -17,6 +17,14 @@ module Gitlab
       end
 
       def run!
+        # If this project is an LFS storage project (e.g. is the root of a fork
+        # network), what it is safe to remove depends on the sum of its forks.
+        # For now, skip cleaning up LFS for this complicated case
+        if project.forks_count > 0 && project.lfs_storage_project == project
+          log_info("Skipping orphan LFS check for #{project.name_with_namespace} as it is a fork root")
+          return
+        end
+
         log_info("Looking for orphan LFS files for project #{project.name_with_namespace}")
 
         remove_orphan_references

spec/lib/gitlab/cleanup/orphan_lfs_file_references_spec.rb

@@ -3,6 +3,8 @@
 require 'spec_helper'
 
 RSpec.describe Gitlab::Cleanup::OrphanLfsFileReferences do
+  include ProjectForksHelper
+
   let(:null_logger) { Logger.new('/dev/null') }
   let(:project) { create(:project, :repository, lfs_enabled: true) }
   let(:lfs_object) { create(:lfs_object) }
@@ -85,4 +87,42 @@ RSpec.describe Gitlab::Cleanup::OrphanLfsFileReferences do
       .to receive(:get_all_lfs_pointers)
       .and_return(oids.map { |oid| OpenStruct.new(lfs_oid: oid) })
   end
+
+  context 'LFS for forked projects' do
+    let!(:fork_root) { create(:project, :repository, lfs_enabled: true) }
+    let!(:fork_internal) { fork_project(fork_root, nil, repository: true) }
+    let!(:fork_leaf) { fork_project(fork_internal, nil, repository: true) }
+
+    let(:dry_run) { true }
+
+    context 'root node' do
+      let(:project) { fork_root }
+
+      it 'skips cleanup' do
+        expect(service).not_to receive(:remove_orphan_references)
+
+        service.run!
+      end
+    end
+
+    context 'internal node' do
+      let(:project) { fork_internal }
+
+      it 'runs cleanup' do
+        expect(service).to receive(:remove_orphan_references)
+
+        service.run!
+      end
+    end
+
+    context 'leaf node' do
+      let(:project) { fork_leaf }
+
+      it 'runs cleanup' do
+        expect(service).to receive(:remove_orphan_references)
+
+        service.run!
+      end
+    end
+  end
 end