Message299033
| Author |
vstinner |
| Recipients |
davin, martin.panter, pitrou, serhiy.storchaka, vstinner |
| Date |
2017年07月24日.23:34:27 |
| SpamBayes Score |
-1.0 |
| Marked as misclassified |
Yes |
| Message-id |
<1500939267.33.0.55391500098.issue26762@psf.upfronthosting.co.za> |
| In-reply-to |
| Content |
> test.test_multiprocessing_spawn.WithProcessesTestPool.test_traceback
Oh, this test only "leaks" dangling processes and threads because PR 2841 was too strict. The problem is that multiprocessing.Pool has thread attributes which hold references to the pool: reference cycle. I don't see any easy way to break these cycles; since I don't understand if a poll is still supposed to be usable after terminate() or not.
Anyway, my intent here was to do a first cleanup. So I modified my PR 2841 to call support.gc_collect() to break reference cycles.
If someone wants to break reference cycles, please open a new issue. IMHO this issue already became enough complex :-) |
|