Received-SPF: pass (google.com: domain of linux-kernel+bounces-132022-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Date: Thu, 4 Apr 2024 12:12:11 -0700 (PDT)
From: "Christoph Lameter (Ampere)" <cl@linux.com>
To: Ming Yang <yangming73@huawei.com>
cc: penberg@kernel.org, rientjes@google.com, iamjoonsoo.kim@lge.com, 
    akpm@linux-foundation.org, vbabka@suse.cz, roman.gushchin@linux.dev, 
    42.hyeyoo@gmail.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org, 
    zhangliang5@huawei.com, wangzhigang17@huawei.com, liushixin2@huawei.com, 
    alex.chen@huawei.com, pengyi.pengyi@huawei.com, xiqi2@huawei.com
Subject: Re: [PATCH] slub: fix slub segmentation
In-Reply-To: <20240402031025.1097-1-yangming73@huawei.com>
Message-ID: <56193a2c-dadb-108d-4eaf-0a923fc4912b@linux.com>
References: <20240402031025.1097-1-yangming73@huawei.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII; format=flowed

On Tue, 2 Apr 2024, Ming Yang wrote:

> The key point of above allocation flow is: the slab should be alloced
> from the partial of other node first, instead of the buddy system of
> other node directly.


If you use GFP_THISNODE then you will trigger a reclaim pass on the remote 
node. That could generate a performance regression.

We already support this kind of behavior via the node_reclaim / 
zone_reclaiom setting in procfs. Please use that.

The remote buildup of the partial pages can be addressed by changing the 
remote_node_defrag_ratio in the slabs. This will make slub scan remote 
nodes for partial slabs before going into the page allocator.