Mercurial > pylearn
changeset 1241:6801451a86bb
Add a point I brought during the last architecture meeting.
| author | Pascal Lamblin <lamblinp@iro.umontreal.ca> |
|---|---|
| date | Thu, 23 Sep 2010 12:02:58 -0400 |
| parents | 317049b21b77 |
| children | 316410a38f6f 7b86c1772932 |
| files | doc/v2_planning/requirements.txt |
| diffstat | 1 files changed, 4 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- a/doc/v2_planning/requirements.txt Thu Sep 23 12:02:16 2010 -0400 +++ b/doc/v2_planning/requirements.txt Thu Sep 23 12:02:58 2010 -0400 @@ -112,6 +112,10 @@ This requirement is aimed at enabling process migration and job control as well as post-hoc analysis of experiment results. +PL: I'm not sure it the job should have to return its current state. I think +it would be enough that it returns a consistent checkpoint, even if it is from +some time in the past (ideally, not more than a few minutes ago). + OD asks: When you say "The experiment cannot assume that resources written by the experiment will still be there", do you mean we should be able to recover the exact same output after interrupting an experiment, wiping its expdir, and