Date:   Mon, 6 Dec 2021 15:15:01 +0100
From:   Michal Hocko <mhocko@suse.com>
To:     David Hildenbrand <david@redhat.com>
Cc:     Nico Pache <npache@redhat.com>, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, akpm@linux-foundation.org, shakeelb@google.com,
        ktkhai@virtuozzo.com, shy828301@gmail.com, guro@fb.com,
        vbabka@suse.cz, vdavydov.dev@gmail.com, raquini@redhat.com
Subject: Re: [RFC PATCH 2/2] mm/vmscan.c: Prevent allocating shrinker_info on
 offlined nodes
Message-ID: <Ya4a5bHjhF+57raT@dhcp22.suse.cz>
References: <20211206033338.743270-1-npache@redhat.com>
 <20211206033338.743270-3-npache@redhat.com>
 <Ya3WcYKcej8XEI0W@dhcp22.suse.cz>
 <d9d14beb-ee20-7ebb-e007-fbf58fb28535@redhat.com>
 <Ya3r3C/OpnK7OBPt@dhcp22.suse.cz>
 <840cb3d0-61fe-b6cb-9918-69146ba06cf7@redhat.com>
 <Ya3yZWkj2wGRWDMz@dhcp22.suse.cz>
 <51c65635-1dae-6ba4-daf9-db9df0ec35d8@redhat.com>
 <Ya4K0+XCmv3NBmwQ@dhcp22.suse.cz>
 <05157de4-e5df-11fc-fc46-8a9f79d0ddb4@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <05157de4-e5df-11fc-fc46-8a9f79d0ddb4@redhat.com>
Precedence: bulk

On Mon 06-12-21 14:47:13, David Hildenbrand wrote:
> On 06.12.21 14:06, Michal Hocko wrote:
[...]
> > This is certainly possible. But it a) adds a branch to the hotpath and
> > b) it doesn't solve any other potential dereference of garbage node.
> 
> I don't think a) is  a problem but it's easy to measure.

Let me just clarify on this one. This single particular branch will be
indeed hard to match to any performance changes. On a single call of the
allocator it is nothing. But it is a condition that will be executed by
each caller while it won't ever trigger in most systems and workloads.

In other words it will cause a lot of wasted cpu cycles long term. A
more expensive one time initialization is worth in order to have
allocator fast path lighter IMHO.
-- 
Michal Hocko
SUSE Labs