Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
In-Reply-To: <20180407234812.2bf2b24b@gandalf.local.home>
References: <1523153783-20579-1-git-send-email-zhaoyang.huang@spreadtrum.com> <20180407234812.2bf2b24b@gandalf.local.home>
From:   Zhaoyang Huang <huangzhaoyang@gmail.com>
Date:   Sun, 8 Apr 2018 13:54:59 +0800
Message-ID: <CAGWkznHVGTpvfQOvaOGP6fYDWh0Os0pYXTC3gG_qvW6mCDuybQ@mail.gmail.com>
Subject: Re: [PATCH v1] ringbuffer: Don't choose the process with adj equal OOM_SCORE_ADJ_MIN
To:     Steven Rostedt <rostedt@goodmis.org>
Cc:     Ingo Molnar <mingo@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        kernel-patch-test@lists.linaro.org
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Sun, Apr 8, 2018 at 11:48 AM, Steven Rostedt <rostedt@goodmis.org> wrote:
> On Sun,  8 Apr 2018 10:16:23 +0800
> Zhaoyang Huang <huangzhaoyang@gmail.com> wrote:
>
>> Don't choose the process with adj == OOM_SCORE_ADJ_MIN which
>> over-allocating pages for ring buffers.
>
> Why?
>
> -- Steve
because in oom_evaluate_task, the process with adj == OOM_SCORE_ADJ_MIN will
be suppressed by oom_badness, but with applying your latest patch,
such process will
be selected by oom_task_origin

        if (oom_task_origin(task)) {
                points = ULONG_MAX;
                goto select;
        }

        points = oom_badness(task, NULL, oc->nodemask, oc->totalpages);
        if (!points || points < oc->chosen_points)
                goto next;