Additional performance notes.
diff --git a/TODO b/TODO
index 548df1a..7eaf300 100644
--- a/TODO
+++ b/TODO
@@ -16,6 +16,10 @@
 - Understand why "slower" consumer code is faster and more consistent when performing single-item
+- Cursors should probably all be created at the same time to keep them as close together as possible:
 - I need to get some help doing some low-level profiling the application to find out where
   the bottlenecks are and determining how the Go scheduler is hindering performance, if at all.