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;
Subject: Re: [PATCH 00/14] per memcg lru_lock
To:     Alex Shi <alex.shi@linux.alibaba.com>, cgroups@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        Andrew Morton <akpm@linux-foundation.org>,
        Mel Gorman <mgorman@techsingularity.net>,
        Tejun Heo <tj@kernel.org>, Michal Hocko <mhocko@kernel.org>
References: <1566294517-86418-1-git-send-email-alex.shi@linux.alibaba.com>
 <6ba1ffb0-fce0-c590-c373-7cbc516dbebd@oracle.com>
 <348495d2-b558-fdfd-a411-89c75d4a9c78@linux.alibaba.com>
From:   Daniel Jordan <daniel.m.jordan@oracle.com>
Message-ID: <b776032e-eabb-64ff-8aee-acc2b3711717@oracle.com>
Date:   Thu, 22 Aug 2019 11:20:52 -0400
MIME-Version: 1.0
In-Reply-To: <348495d2-b558-fdfd-a411-89c75d4a9c78@linux.alibaba.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 8/22/19 7:56 AM, Alex Shi wrote:
> 在 2019/8/22 上午2:00, Daniel Jordan 写道:
>>    https://git.kernel.org/pub/scm/linux/kernel/git/wfg/vm-scalability.git/tree/case-lru-file-readtwice>
>> It's also synthetic but it stresses lru_lock more than just anon alloc/free.  It hits the page activate path, which is where we see this lock in our database, and if enough memory is configured lru_lock also gets stressed during reclaim, similar to [1].
> 
> Thanks for the sharing, this patchset can not help the [1] case, since it's just relief the per container lock contention now.

I should've been clearer.  [1] is meant as an example of someone suffering from lru_lock during reclaim.  Wouldn't your series help per-memcg reclaim?

> Yes, readtwice case could be more sensitive for this lru_lock changes in containers. I may try to use it in container with some tuning. But anyway, aim9 is also pretty good to show the problem and solutions. :)
>>
>> It'd be better though, as Michal suggests, to use the real workload that's causing problems.  Where are you seeing contention?
> 
> We repeatly create or delete a lot of different containers according to servers load/usage, so normal workload could cause lots of pages alloc/remove. 

I think numbers from that scenario would help your case.

> aim9 could reflect part of scenarios. I don't know the DB scenario yet.

We see it during DB shutdown when each DB process frees its memory (zap_pte_range -> mark_page_accessed).  But that's a different thing, clearly Not This Series.

>>> With this patch series, lruvec->lru_lock show no contentions
>>>           &(&lruvec->lru_l...          8          0               0       0               0               0
>>>
>>> and aim9 page_test/brk_test performance increased 5%~50%.
>>
>> Where does the 50% number come in?  The numbers below seem to only show ~4% boost.
> 
> the Setddev/CoeffVar case has about 50% performance increase. one of container's mmtests result as following:
> 
> Stddev    page_test      245.15 (   0.00%)      189.29 (  22.79%)
> Stddev    brk_test      1258.60 (   0.00%)      629.16 (  50.01%)
> CoeffVar  page_test        0.71 (   0.00%)        0.53 (  26.05%)
> CoeffVar  brk_test         1.32 (   0.00%)        0.64 (  51.14%)

Aha.  50% decrease in stdev.