diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py
--- a/swh/storage/in_memory.py
+++ b/swh/storage/in_memory.py
@@ -74,6 +74,7 @@
         for content in contents:
             key = self._content_key(content)
             if key in self._contents:
+                self._objects[key].append(('skipped_content', content['sha1']))
                 continue
             for algorithm in DEFAULT_ALGORITHMS:
                 if content[algorithm] in self._content_indexes[algorithm]:
@@ -169,7 +170,7 @@
         """
         return self._content_add(contents, with_data=False)
 
-    def content_get(self, ids):
+    def content_get(self, ids, start=0, end=-1):
         """Retrieve in bulk contents and their data.
 
         This function may yield more blobs than provided sha1 identifiers,
@@ -1170,7 +1171,8 @@
                 'origin': origin_id,
                 'visit': visit_id,
             }
-
+            key = (origin_id, visit_id)
+            self._objects[key].append(('origin_visit', origin_id))
             if self.journal_writer:
                 origin = self.origin_get([{'id': origin_id}])[0]
                 del origin['id']
@@ -1514,12 +1516,12 @@
         if key not in self._objects:
             person_id = len(self._persons) + 1
             self._persons.append(dict(person))
-            self._objects[key].append(('person', person_id))
         else:
             person_id = self._objects[key][0][1]
             p = next(self.person_get([person_id]))
             person.update(p.items())
         person['id'] = person_id
+        self._objects[key].append(('person', person_id))
 
     @staticmethod
     def _content_key(content):
diff --git a/swh/storage/storage.py b/swh/storage/storage.py
--- a/swh/storage/storage.py
+++ b/swh/storage/storage.py
@@ -334,7 +334,7 @@
 
         return summary
 
-    def content_get(self, content):
+    def content_get(self, content, start=0, end=-1):
         """Retrieve in bulk contents and their data.
 
         This generator yields exactly as many items than provided sha1
@@ -369,7 +369,10 @@
                 yield None
                 continue
 
-            yield {'sha1': obj_id, 'data': data}
+            if end != -1:
+                yield {'sha1': obj_id, 'data': data[start:end]}
+            else:
+                yield {'sha1': obj_id, 'data': data}
 
     @db_transaction()
     def content_get_range(self, start, end, limit=1000, db=None, cur=None):