On Wed, 4 Apr 2018 09:03:47 -0700 Joel Fernandes <joelaf@xxxxxxxxxx> wrote: > > for the tests. Note, without this, I tried to allocate all memory > > (bisecting it with allocations that failed and allocations that > > succeeded), and couldn't trigger an OOM :-/ > > I guess you need to have something *else* other than the write to > buffer_size_kb doing the GFP_KERNEL allocations but unfortunately gets > OOM killed? Yeah, for some reason, my test box seems to always have something doing that, because I trigger an OOM about 2 out of every 3 tries. Here's the tasks that trigger it: lvmetad, crond, systemd-journal, abrt-dump-journ, chronyd, I guess my system is rather busy even when idle :-/ > > Also, I agree with the new patch and its nice idea to do that. Thanks, want to give it a test too? -- Steve
