Message11286

I just found out that the stack is so exhausted that even the System.out.println() causes a subsequent StackOverflowError, which prevents the expected output. So it's not a JVM bug, while a very inconvenient behavior: The JVM should have some extra stack memory to guarantee that debug outputs, close and unlock operations can pass even in a catch or finally block right after a StackOverflowError.
So, how shall we deal with this situation?
On one hand, this scenario is pathological and we maybe shouldn't spend too much effort on it.
On the other hand, having potential for deadlocks is an unbearable situation in the test suite. However, just dropping test_endless_recursion(self) is maybe not what we want either (while the easiest short-term solution, especially with 2.7.1 release in mind). Suggestions?