Merge pull request #675 from coreos-inc/distinctgc

Reduce GC work time and make sure to use distinct query

data/model/repository.py

@@ -74,6 +74,7 @@ def find_repository_with_garbage():
                          (RepositoryTag.lifetime_end_ts <=
                           (epoch_timestamp - Namespace.removed_tag_expiration_s)))
                   .limit(500)
+                  .distinct()
                   .alias('candidates'))
 
     found = (RepositoryTag

workers/gcworker.py

@@ -10,7 +10,7 @@ logger = logging.getLogger(__name__)
 class GarbageCollectionWorker(Worker):
   def __init__(self):
     super(GarbageCollectionWorker, self).__init__()
-    self.add_operation(self._garbage_collection_repos, 10)
+    self.add_operation(self._garbage_collection_repos, 30)
 
   def _garbage_collection_repos(self):
     """ Performs garbage collection on repositories. """