śr., 24 mar 2021 o 10:37 Christopher Faulet <cfau...@haproxy.com> napisał(a):
> However, reading the other trace Maciej sent (bussy_thread_peers.txt), it > seems > possible to stop a memory allocation from other places. Thus, I guess we > must > find a more global way to prevent the lua stack dump. > I'm not sure which part of trace you're referring to but I need to clarify that both "bussy_thread_peers.txt" and "free_thread_spoe_lua.txt" occurred at the same time but on different threads (free_thread_spoe_lua on thread 10 and bussy_thread_peers on other threads). So If I understand it correctly thread 10 locked itself and other threads looping to acquire lock.