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;
Subject: Re: [PATCH] mm/vmscan: don't scan adjust too much if current is not
 kswapd
To:     Mel Gorman <mgorman@techsingularity.net>
Cc:     Mel Gorman <mgorman@suse.de>, Matthew Wilcox <willy@infradead.org>,
        Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
References: <20220914023318.549118-1-zhanghongchen@loongson.cn>
 <20220914155142.bf388515a39fb45bae987231@linux-foundation.org>
 <6bcb4883-03d0-88eb-4c42-84fff0a9a141@loongson.cn>
 <YyLUGnqtZXn4MjJF@casper.infradead.org>
 <54813a74-cc0e-e470-c632-78437a0d0ad4@loongson.cn>
 <YyLpls9/t6LKQefS@casper.infradead.org>
 <b52b3f49-ebf5-6f63-da1a-f57711c3f97d@loongson.cn>
 <YyQ2m9vU/plyBNas@casper.infradead.org>
 <4bd0012e-77ff-9d0d-e295-800471994aeb@loongson.cn>
 <c3f4d1bb-418c-fbf5-c251-fd448f4d4e86@loongson.cn>
 <20220921091303.hihmb3qvfvl3s365@techsingularity.net>
From:   Hongchen Zhang <zhanghongchen@loongson.cn>
Message-ID: <f946fbd8-89f6-67c9-44c1-10ef6e3bdb68@loongson.cn>
Date:   Wed, 21 Sep 2022 18:14:30 +0800
User-Agent: Mozilla/5.0 (X11; Linux loongarch64; rv:68.0) Gecko/20100101
 Thunderbird/68.7.0
MIME-Version: 1.0
In-Reply-To: <20220921091303.hihmb3qvfvl3s365@techsingularity.net>
Content-Type: text/plain; charset=iso-8859-15; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Precedence: bulk

Hi Mel,

Thanks for your reply.

On 2022/9/21 pm 5:13, Mel Gorman wrote:
> On Tue, Sep 20, 2022 at 10:23:05AM +0800, Hongchen Zhang wrote:
>> Hi Mel,
>>
>> The scan adjust algorithm was originally introduced by you from
>> commmit e82e0561dae9 ("mm: vmscan: obey proportional scanning requirements
>> for kswapd"), any suggestion about this fix patch?
>> In short, proportional scanning is not friendly to processes other than
>> kswapd.
>>
> 
> I suspect that 6eb90d649537 ("mm: vmscan: fix extreme overreclaim and swap
> floods") is a more appropriate fix. While it also has a fairness impact,
> it's a more general approach that is likely more robust and while
> fairness is important, completely thrashing a full LRU is neither fair
> nor expected.
> 
OK,got it. Let's wait for the 6eb90d649537 ("mm: vmscan: fix extreme 
overreclaim and swap floods") enter the stable repository.

Best Regards
Hongchen Zhang