Content-Type: multipart/mixed; boundary="===============5666628711190830438==" MIME-Version: 1.0 From: Oleg Nesterov To: lkp@lists.01.org Subject: Re: [sched] Out of memory: Kill process 2999 (rc) score 9 or sacrifice child Date: Sat, 09 Aug 2014 21:24:17 +0200 Message-ID: <20140809192417.GA32704@redhat.com> In-Reply-To: <20140809184616.GQ9918@twins.programming.kicks-ass.net> List-Id: --===============5666628711190830438== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On 08/09, Peter Zijlstra wrote: > > That would suggest we're failing to do the TASK_DEAD thing properly, and > ARGH! bloody obvious why, see the this_rq() comment right before the > finish_task_switch() call in context_switch(). Heh ;) and a similar comment in __schedule() after context_switch(). rq->dead_task or something similar should work I guess, but i should be nullified before finish_lock_switch()... Oleg. --===============5666628711190830438==--