Do load_balance_loop in the new spawned thread instead of compute_loop.

[loba.git] / TODO

diff --git a/TODO b/TODO
index 25c3797915f093160bf7e1b2a4ded7f0cff1a376..69c0b6eb54c3ad7b1555dc9eb2bfd138b6293d9a 100644 (file)
--- a/TODO
+++ b/TODO
@@ -1,10 +1,11 @@
-* verify bookkeeping version.
+* add several metrics
+  - message exchanges : number/volume of sent/received data/ctrl messages
 
-* add minimum (sleep) time between 2 lb iterations ?
+* add options -j/-J : minimum number of iterations?
 
-* add options -j/-J : minimum number of iterations ?
+* add options -f/-F : termination based on flops achieved?
 
-* add a variant to (not) change neighbor load information at send.
+* add a variant to (not) change neighbor load information at send?
 
 * implement loba_* algorithms (start with some trivial one)