linux-kernel - Re: Re: Re: [PATCH v4] mm: oom: introduce cpuset oom

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <e6ff9768-f41d-553c-e858-1b244a461526@bytedance.com>
Date:   Tue, 11 Apr 2023 21:17:27 +0800
From:   Gang Li <ligang.bdlg@...edance.com>
To:     Michal Hocko <mhocko@...e.com>
Cc:     Michal Koutný <mkoutny@...e.com>,
        Waiman Long <longman@...hat.com>, cgroups@...r.kernel.org,
        linux-mm@...ck.org, rientjes@...gle.com,
        Zefan Li <lizefan.x@...edance.com>,
        linux-kernel@...r.kernel.org
Subject: Re: Re: Re: [PATCH v4] mm: oom: introduce cpuset oom



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@...edance.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.