Clean orphaned files in object storage

changelogs/unreleased/46535-orphaned-uploads.yml

+---
+title: Clean orphaned files in object storage
+merge_request: 20918
+author:
+type: added

doc/raketasks/cleanup.md

@@ -53,3 +53,32 @@ I, [2018-07-27T12:08:33.689869 #89817]  INFO -- : Did move to lost and found /op
 I, [2018-07-27T12:08:33.755624 #89817]  INFO -- : Did fix /opt/gitlab/embedded/service/gitlab-rails/public/uploads/foo/bar/89a0f7b0b97008a4a18cedccfdcd93fb/foo.txt -> /opt/gitlab/embedded/service/gitlab-rails/public/uploads/qux/foo/bar/89a0f7b0b97008a4a18cedccfdcd93fb/foo.txt
 I, [2018-07-27T12:08:33.760257 #89817]  INFO -- : Did move to lost and found /opt/gitlab/embedded/service/gitlab-rails/public/uploads/foo/bar/1dd6f0f7eefd2acc4c2233f89a0f7b0b/image.png -> /opt/gitlab/embedded/service/gitlab-rails/public/uploads/-/project-lost-found/foo/bar/1dd6f0f7eefd2acc4c2233f89a0f7b0b/image.png
 ```
+
+Remove object store upload files if they don't exist in GitLab database.
+
+```
+# omnibus-gitlab
+sudo gitlab-rake gitlab:cleanup:remote_upload_files
+
+# installation from source
+bundle exec rake gitlab:cleanup:remote_upload_files RAILS_ENV=production
+```
+
+Example output:
+
+```
+$ sudo gitlab-rake gitlab:cleanup:remote_upload_files
+
+I, [2018-08-02T10:26:13.995978 #45011]  INFO -- : Looking for orphaned remote uploads to remove. Dry run...
+I, [2018-08-02T10:26:14.120400 #45011]  INFO -- : Can be moved to lost and found: @hashed/6b/DSC_6152.JPG
+I, [2018-08-02T10:26:14.120482 #45011]  INFO -- : Can be moved to lost and found: @hashed/79/02/7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451/711491b29d3eb08837798c4909e2aa4d/DSC00314.jpg
+I, [2018-08-02T10:26:14.120634 #45011]  INFO -- : To cleanup these files run this command with DRY_RUN=false
+```
+
+```
+$ sudo gitlab-rake gitlab:cleanup:remote_upload_files DRY_RUN=false
+
+I, [2018-08-02T10:26:47.598424 #45087]  INFO -- : Looking for orphaned remote uploads to remove...
+I, [2018-08-02T10:26:47.753131 #45087]  INFO -- : Moved to lost and found: @hashed/6b/DSC_6152.JPG -> lost_and_found/@hashed/6b/DSC_6152.JPG
+I, [2018-08-02T10:26:47.764356 #45087]  INFO -- : Moved to lost and found: @hashed/79/02/7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451/711491b29d3eb08837798c4909e2aa4d/DSC00314.jpg -> lost_and_found/@hashed/79/02/7902699be42c8a8e46fbbb4501726517e86b22c56a189f7625a6da49081b2451/711491b29d3eb08837798c4909e2aa4d/DSC00314.jpg
+```

lib/gitlab/cleanup/remote_uploads.rb

+# frozen_string_literal: true
+module Gitlab
+  module Cleanup
+    class RemoteUploads
+      attr_reader :logger
+
+      BATCH_SIZE = 100
+
+      def initialize(logger: nil)
+        @logger = logger || Rails.logger
+      end
+
+      def run!(dry_run: false)
+        unless configuration.enabled
+          logger.warn "Object storage not enabled. Exit".color(:yellow)
+
+          return
+        end
+
+        logger.info "Looking for orphaned remote uploads to remove#{'. Dry run' if dry_run}..."
+
+        each_orphan_file do |file|
+          info = if dry_run
+                   "Can be moved to lost and found: #{file.key}"
+                 else
+                   new_path = move_to_lost_and_found(file)
+                   "Moved to lost and found: #{file.key} -> #{new_path}"
+                 end
+
+          logger.info(info)
+        end
+      end
+
+      private
+
+      def each_orphan_file
+        # we want to skip files already moved to lost_and_found directory
+        lost_dir_match = "^#{lost_and_found_dir}\/"
+
+        remote_directory.files.each_slice(BATCH_SIZE) do |remote_files|
+          remote_files.reject! { |file| file.key.match(/#{lost_dir_match}/) }
+          file_paths = remote_files.map(&:key)
+          tracked_paths = Upload
+            .where(store: ObjectStorage::Store::REMOTE, path: file_paths)
+            .pluck(:path)
+
+          remote_files.reject! { |file| tracked_paths.include?(file.key) }
+          remote_files.each do |file|
+            yield file
+          end
+        end
+      end
+
+      def move_to_lost_and_found(file)
+        new_path = "#{lost_and_found_dir}/#{file.key}"
+
+        file.copy(configuration['remote_directory'], new_path)
+        file.destroy
+
+        new_path
+      end
+
+      def lost_and_found_dir
+        'lost_and_found'
+      end
+
+      def remote_directory
+        connection.directories.get(configuration['remote_directory'])
+      end
+
+      def connection
+        ::Fog::Storage.new(configuration['connection'].symbolize_keys)
+      end
+
+      def configuration
+        Gitlab.config.uploads.object_store
+      end
+    end
+  end
+end

lib/tasks/gitlab/cleanup.rake

@@ -116,6 +116,16 @@ namespace :gitlab do
       end
     end
 
+    desc 'GitLab | Cleanup | Clean orphan remote upload files that do not exist in the db'
+    task remote_upload_files: :environment do
+      cleaner = Gitlab::Cleanup::RemoteUploads.new(logger: logger)
+      cleaner.run!(dry_run: dry_run?)
+
+      if dry_run?
+        logger.info "To cleanup these files run this command with DRY_RUN=false".color(:yellow)
+      end
+    end
+
     def remove?
       ENV['REMOVE'] == 'true'
     end

spec/lib/gitlab/cleanup/remote_uploads_spec.rb

+# frozen_string_literal: true
+require 'spec_helper'
+
+describe Gitlab::Cleanup::RemoteUploads do
+  context 'when object_storage is enabled' do
+    let(:connection) { double }
+    let(:directory) { double }
+    let!(:uploads) do
+      [
+        create(:upload, path: 'dir/file1', store: ObjectStorage::Store::REMOTE),
+        create(:upload, path: 'dir/file2', store: ObjectStorage::Store::LOCAL)
+      ]
+    end
+    let(:remote_files) do
+      [
+        double(key: 'dir/file1'),
+        double(key: 'dir/file2'),
+        double(key: 'dir/file3'),
+        double(key: 'lost_and_found/dir/file3')
+      ]
+    end
+
+    before do
+      stub_uploads_object_storage(FileUploader)
+
+      expect(::Fog::Storage).to receive(:new).and_return(connection)
+
+      expect(connection).to receive(:directories).and_return(double(get: directory))
+      expect(directory).to receive(:files).and_return(remote_files)
+    end
+
+    context 'when dry_run is set to false' do
+      subject { described_class.new.run!(dry_run: false) }
+
+      it 'moves files that are not in uploads table' do
+        expect(remote_files[0]).not_to receive(:copy)
+        expect(remote_files[0]).not_to receive(:destroy)
+        expect(remote_files[1]).to receive(:copy)
+        expect(remote_files[1]).to receive(:destroy)
+        expect(remote_files[2]).to receive(:copy)
+        expect(remote_files[2]).to receive(:destroy)
+        expect(remote_files[3]).not_to receive(:copy)
+        expect(remote_files[3]).not_to receive(:destroy)
+
+        subject
+      end
+    end
+
+    context 'when dry_run is set to true' do
+      subject { described_class.new.run!(dry_run: true) }
+
+      it 'does not move filese' do
+        expect(remote_files[0]).not_to receive(:copy)
+        expect(remote_files[0]).not_to receive(:destroy)
+        expect(remote_files[1]).not_to receive(:copy)
+        expect(remote_files[1]).not_to receive(:destroy)
+        expect(remote_files[2]).not_to receive(:copy)
+        expect(remote_files[2]).not_to receive(:destroy)
+        expect(remote_files[3]).not_to receive(:copy)
+        expect(remote_files[3]).not_to receive(:destroy)
+
+        subject
+      end
+    end
+  end
+
+  context 'when object_storage is not enabled' do
+    it 'does not connect to any storage' do
+      expect(::Fog::Storage).not_to receive(:new)
+
+      subject
+    end
+  end
+end