On Sun 22-04-18 07:18:57, Michal Hocko wrote: > On Sat 21-04-18 20:45:11, David Rientjes wrote: [...] > Maybe invoking the reaper as suggested by Tetsuo will help here. Maybe > we will come up with something more smart. But I would like to have a > stop gap solution for stable that is easy enough. And your patch is not > doing that because it adds a very subtle dependency on the page lock. > So please stop repeating your arguments all over and either come with > an argument which proves me wrong and the lock_page dependency is not > real or come with an alternative solution which doesn't make > MMF_OOM_SKIP depend on the page lock. I though I would give this a try but I am at a conference and quite busy. Tetsuo are you willing to give it a try so that we have something to compare and decide, please? -- Michal Hocko SUSE Labs
