[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241112000334.ppzn3fap5glivpxl@offworld>
Date: Mon, 11 Nov 2024 16:03:34 -0800
From: Davidlohr Bueso <dave@...olabs.net>
To: Suren Baghdasaryan <surenb@...gle.com>
Cc: akpm@...ux-foundation.org, willy@...radead.org, liam.howlett@...cle.com,
lorenzo.stoakes@...cle.com, mhocko@...e.com, vbabka@...e.cz,
hannes@...xchg.org, mjguzik@...il.com, oliver.sang@...el.com,
mgorman@...hsingularity.net, david@...hat.com, peterx@...hat.com,
oleg@...hat.com, paulmck@...nel.org, brauner@...nel.org,
dhowells@...hat.com, hdanton@...a.com, hughd@...gle.com,
minchan@...gle.com, jannh@...gle.com, shakeel.butt@...ux.dev,
souravpanda@...gle.com, pasha.tatashin@...een.com,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
kernel-team@...roid.com
Subject: Re: [PATCH 0/4] move per-vma lock into vm_area_struct
On Mon, 11 Nov 2024, Suren Baghdasaryan wrote:
>I'm not really trying to claim performance gains here. I just want to
>make sure there are no regressions.
You might also fine tune the atomics with acquire/release standard locking
semantics, you will probably see better numbers in Android than what you
currently have in patch 3 with full barriers - and not particularly risky
as callers expect that behaviour already.
Thanks,
Davidlohr
Powered by blists - more mailing lists