On Thu, Jun 1, 2017 at 2:22 PM, Benjamin Mahler <bmah...@apache.org> wrote:
> If I understood correctly, the proposal is to not kill the tasks for > non-partition aware frameworks? That seems like a pretty big change for > frameworks that are not partition aware and expect the old killing > semantics. > Adding to what Neil said, I think most (if not all) non-PA frameworks would've already rescheduled the task after seeing a TASK_LOST. The difference is that previously such tasks can come back to TASK_RUNNING iff master fails over and non-strict registry (default) is used. Now, we are saying tasks can come back to TASK_RUNNING irrespective of master fail over. The assumption/hope is that this shouldn't break existing frameworks in a catastrophic way.