Merge branch 'da-files-does-not-schedule-duplicated-jobs' into 'master'

Geo - Does not schedule duplicated jobs while backfilling uploads, LFS objects and job artifacts

See merge request gitlab-org/gitlab!20324

ee/app/workers/geo/file_download_dispatch_worker.rb

@@ -65,7 +65,7 @@ module Geo
     end
 
     def job_finders
-      @job_finders ||= [
+      [
         Geo::FileDownloadDispatchWorker::AttachmentJobFinder.new(scheduled_file_ids(Gitlab::Geo::Replication::USER_UPLOADS_OBJECT_TYPES)),
         Geo::FileDownloadDispatchWorker::LfsObjectJobFinder.new(scheduled_file_ids(:lfs)),
         Geo::FileDownloadDispatchWorker::JobArtifactJobFinder.new(scheduled_file_ids(:job_artifact))

ee/changelogs/unreleased/da-files-does-not-schedule-duplicated-jobs.yml

+---
+title: Geo - Does not schedule duplicated jobs while backfilling uploads, LFS objects
+  and job artifacts
+merge_request: 20324
+author:
+type: other

ee/spec/workers/geo/file_download_dispatch_worker_spec.rb

@@ -42,6 +42,21 @@ describe Geo::FileDownloadDispatchWorker, :geo, :geo_fdw do
     subject.perform
   end
 
+  it 'does not schedule duplicated jobs' do
+    lfs_object_1 = create(:lfs_object, :with_file)
+    lfs_object_2 = create(:lfs_object, :with_file)
+
+    stub_const('Geo::Scheduler::SchedulerWorker::DB_RETRIEVE_BATCH_SIZE', 5)
+    secondary.update!(files_max_capacity: 2)
+    allow(Gitlab::SidekiqStatus).to receive(:job_status).with([]).and_return([]).twice
+    allow(Gitlab::SidekiqStatus).to receive(:job_status).with(%w[123 456]).and_return([true, true], [true, true], [false, false])
+
+    expect(Geo::FileDownloadWorker).to receive(:perform_async).with('lfs', lfs_object_1.id).once.and_return('123')
+    expect(Geo::FileDownloadWorker).to receive(:perform_async).with('lfs', lfs_object_2.id).once.and_return('456')
+
+    subject.perform
+  end
+
   context 'with attachments (Upload records)' do
     let(:upload) { create(:upload) }