[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <202108271746.F444DA6C9@keescook>
Date: Fri, 27 Aug 2021 22:28:41 -0700
From: Kees Cook <keescook@...omium.org>
To: Suren Baghdasaryan <surenb@...gle.com>
Cc: akpm@...ux-foundation.org, ccross@...gle.com,
sumit.semwal@...aro.org, mhocko@...e.com, dave.hansen@...el.com,
willy@...radead.org, kirill.shutemov@...ux.intel.com,
vbabka@...e.cz, hannes@...xchg.org, corbet@....net,
viro@...iv.linux.org.uk, rdunlap@...radead.org,
kaleshsingh@...gle.com, peterx@...hat.com, rppt@...nel.org,
peterz@...radead.org, catalin.marinas@....com,
vincenzo.frascino@....com, chinwen.chang@...iatek.com,
axelrasmussen@...gle.com, aarcange@...hat.com, jannh@...gle.com,
apopple@...dia.com, jhubbard@...dia.com, yuzhao@...gle.com,
will@...nel.org, fenghua.yu@...el.com, thunder.leizhen@...wei.com,
hughd@...gle.com, feng.tang@...el.com, jgg@...pe.ca, guro@...com,
tglx@...utronix.de, krisman@...labora.com, chris.hyser@...cle.com,
pcc@...gle.com, ebiederm@...ssion.com, axboe@...nel.dk,
legion@...nel.org, eb@...ix.com, songmuchun@...edance.com,
viresh.kumar@...aro.org, thomascedeno@...gle.com,
sashal@...nel.org, cxfcosmos@...il.com, linux@...musvillemoes.dk,
linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
linux-doc@...r.kernel.org, linux-mm@...ck.org,
kernel-team@...roid.com
Subject: Re: [PATCH v8 3/3] mm: add anonymous vma name refcounting
On Fri, Aug 27, 2021 at 12:18:58PM -0700, Suren Baghdasaryan wrote:
> While forking a process with high number (64K) of named anonymous vmas the
> overhead caused by strdup() is noticeable. Experiments with ARM64 Android
> device show up to 40% performance regression when forking a process with
> 64k unpopulated anonymous vmas using the max name lengths vs the same
> process with the same number of anonymous vmas having no name.
> Introduce anon_vma_name refcounted structure to avoid the overhead of
> copying vma names during fork() and when splitting named anonymous vmas.
> When a vma is duplicated, instead of copying the name we increment the
> refcount of this structure. Multiple vmas can point to the same
> anon_vma_name as long as they increment the refcount. The name member of
> anon_vma_name structure is assigned at structure allocation time and is
> never changed. If vma name changes then the refcount of the original
> structure is dropped, a new anon_vma_name structure is allocated
> to hold the new name and the vma pointer is updated to point to the new
> structure.
> With this approach the fork() performance regressions is reduced 3-4x
> times and with usecases using more reasonable number of VMAs (a few
> thousand) the regressions is not measurable.
I like the refcounting; thank you!
Since patch2 adds a lot of things that are changed by patch3; maybe
combine them?
--
Kees Cook
Powered by blists - more mailing lists