Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <e6ff9768-f41d-553c-e858-1b244a461526@bytedance.com>
Date:   Tue, 11 Apr 2023 21:17:27 +0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:102.0)
 Gecko/20100101 Thunderbird/102.9.1
Subject: Re: Re: Re: [PATCH v4] mm: oom: introduce cpuset oom
Content-Language: en-US
To:     Michal Hocko <mhocko@suse.com>
Cc:     =?UTF-8?Q?Michal_Koutn=c3=bd?= <mkoutny@suse.com>,
        Waiman Long <longman@redhat.com>, cgroups@vger.kernel.org,
        linux-mm@kvack.org, rientjes@google.com,
        Zefan Li <lizefan.x@bytedance.com>,
        linux-kernel@vger.kernel.org
References: <20230411065816.9798-1-ligang.bdlg@bytedance.com>
 <3myr57cw3qepul7igpifypxx4xd2buo2y453xlqhdw4xgjokc4@vi3odjfo3ahc>
 <aa3382b4-4046-988f-42ea-8812dba7882b@bytedance.com>
 <ZDVcwuiu3rWEFiTE@dhcp22.suse.cz>
From:   Gang Li <ligang.bdlg@bytedance.com>
In-Reply-To: <ZDVcwuiu3rWEFiTE@dhcp22.suse.cz>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk


On 2023/4/11 21:12, Michal Hocko wrote:
> On Tue 11-04-23 21:04:18, Gang Li wrote:
>>
>>
>> On 2023/4/11 20:23, Michal Koutný wrote:
>>> Hello.
>>>
>>> On Tue, Apr 11, 2023 at 02:58:15PM +0800, Gang Li <ligang.bdlg@bytedance.com> wrote:
>>>> +	cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
>>>> +		if (nodes_equal(cs->mems_allowed, task_cs(current)->mems_allowed)) {
>>>> +			css_task_iter_start(&(cs->css), CSS_TASK_ITER_PROCS, &it);
>>>> +			while (!ret && (task = css_task_iter_next(&it)))
>>>> +				ret = fn(task, arg);
>>>> +			css_task_iter_end(&it);
>>>> +		}
>>>> +	}
>>>> +	rcu_read_unlock();
>>>> +	cpuset_read_unlock();
>>>> +	return ret;
>>>> +}
>>>
>>> I see this traverses all cpusets without the hierarchy actually
>>> mattering that much. Wouldn't the CONSTRAINT_CPUSET better achieved by
>>> globally (or per-memcg) scanning all processes and filtering with:
>>
>> Oh I see, you mean scanning all processes in all cpusets and scanning
>> all processes globally are equivalent.
> 
> Why cannot you simple select a process from the cpuset the allocating
> process belongs to? I thought the whole idea was to handle well
> partitioned workloads.
>

Yes I can :) It's much easier.

>>> 	nodes_intersect(current->mems_allowed, p->mems_allowed
>>
>> Perhaps it would be better to use nodes_equal first, and if no suitable
>> victim is found, then downgrade to nodes_intersect?
> 
> How can this happen?
> 
>> NUMA balancing mechanism tends to keep memory on the same NUMA node, and
>> if the selected victim's memory happens to be on a node that does not
>> intersect with the current process's node, we still won't be able to
>> free up any memory.
> 
> AFAIR NUMA balancing doesn't touch processes with memory policies.