diff --git a/TODO b/TODO
index 2e3ae50..a69082b 100644
--- a/TODO
+++ b/TODO
@@ -11,6 +11,13 @@ so go back to empty DB, etc.
             (file_refimg_link --> file_refimg_link needs a face_num?)
 
 ### BACKEND
+    -- started on some basic optimisations (commit logs every 100 logs, not each log)
+        - with debugs: import = 04:11, getfiledetails== 0:35:35
+        - without debugs: import == 04:03, getfiledetails == 
+
+    * try again with walk to go through loop once quickly just to add up files,
+    * then start the import dir counting up / progress
+
     *** Need to use thread-safe sessions per Thread, half-assed version did not work
 
     need a manual button to restart it in the GUI, 
@@ -58,7 +65,7 @@ so go back to empty DB, etc.
 
 ### SORTER
     * duplicate files - this sql finds them:
-        select d1.path_prefix, e1.name, f1.hash from entry e1, file f1, dir d1, entry_dir_link edl1, entry e2, file f2 where e1.id = f1.eid and e2.id = f2.eid and d1.eid = edl1.dir_eid and edl1.entry_id = e1.id  and f1.hash = f2.hash and e1.name != e2.name
+        select d1.path_prefix, e1.name, f1.hash, d2.path_prefix, e2.name, f2.hash from entry e1, file f1, dir d1, entry_dir_link edl1, entry e2, file f2, dir d2, entry_dir_link edl2 where e1.id = f1.eid and e2.id = f2.eid and d1.eid = edl1.dir_eid and edl1.entry_id = e1.id and edl2.dir_eid = d2.eid and edl2.entry_id = e2.id  and f1.hash = f2.hash and e1.id != e2.id order by f1.hash, f2.hash;
 
 	* date stuff
 	* exif processing?