More playbook executor compatibility fixes

With some earlier changes, continuing to forward failed hosts on
to the iterator with each TQM run() call was causing plays with
max_fail_pct set to fail, as hosts which failed in previous plays
were counting those old failures against the % calculation.

Also changed the linear strategy's calculation to use the internal
failed list, rather than the iterator, as this now represents the
hosts failed during the current run only.

2 files changed, 12 insertions, 4 deletions

diff --git a/lib/ansible/executor/task_queue_manager.py b/lib/ansible/executor/task_queue_manager.py
index ba4970ed66..8373264ef1 100644
--- a/lib/ansible/executor/task_queue_manager.py
+++ b/lib/ansible/executor/task_queue_manager.py
@@ -236,13 +236,16 @@ class TaskQueueManager:
             start_at_done = self._start_at_done,
         )
 
-        # because the TQM may survive multiple play runs, we start by
-        # marking any hosts as failed in the iterator here which may
-        # have been marked as failed in previous runs.
+        # Because the TQM may survive multiple play runs, we start by marking
+        # any hosts as failed in the iterator here which may have been marked
+        # as failed in previous runs. Then we clear the internal list of failed
+        # hosts so we know what failed this round.
         for host_name in self._failed_hosts.keys():
             host = self._inventory.get_host(host_name)
             iterator.mark_host_failed(host)
 
+        self.clear_failed_hosts()
+
         # during initialization, the PlayContext will clear the start_at_task
         # field to signal that a matching task was found, so check that here
         # and remember it so we don't try to skip tasks on future plays
@@ -251,6 +254,11 @@ class TaskQueueManager:
 
         # and run the play using the strategy and cleanup on way out
         play_return = strategy.run(iterator, play_context)
+
+        # now re-save the hosts that failed from the iterator to our internal list
+        for host_name in iterator.get_failed_hosts():
+            self._failed_hosts[host_name] = True
+
         self._cleanup_processes()
         return play_return
 
diff --git a/lib/ansible/plugins/strategy/linear.py b/lib/ansible/plugins/strategy/linear.py
index 0b8f0318c6..2d3396a3b2 100644
--- a/lib/ansible/plugins/strategy/linear.py
+++ b/lib/ansible/plugins/strategy/linear.py
@@ -367,7 +367,7 @@ class StrategyModule(StrategyBase):
                 if iterator._play.max_fail_percentage is not None and len(results) > 0:
                     percentage = iterator._play.max_fail_percentage / 100.0
 
-                    if (len(iterator.get_failed_hosts()) / len(results)) > percentage:
+                    if (len(self._tqm._failed_hosts) / len(results)) > percentage:
                         for host in hosts_left:
                             # don't double-mark hosts, or the iterator will potentially
                             # fail them out of the rescue/always states