On 2019/01/26 11:41, Arkadiusz Miśkiewicz wrote: > dmesg: > http://ixion.pld-linux.org/~arekm/cgroup-oom-2.txt What is wrong with this output? It seems to me that the OOM killer is killing processes as soon as python 3 fork()s one. Although "potentially unexpected fatal signal 7." messages due to handling SIGBUS at get_signal() after the OOM reaper reclaimed the OOM victim's memory is a bit noisy, I don't think that something is wrong. Jan 26 03:33:49 xps kernel: python3 invoked oom-killer: gfp_mask=0x6000c0(GFP_KERNEL), order=0, oom_score_adj=0 Jan 26 03:33:52 xps kernel: potentially unexpected fatal signal 7. You seem to be monitoring cgroup statistic values for only 1 minute, but since the fork bombs might take longer than 1 minute, I'm not sure that the statistic values after terminating cg.py and waited for a while (e.g. 1 minute) is still showing unexpected values.
