Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue, 25 Jan 2022 18:59:50 +0000
From:   Matthew Wilcox <willy@infradead.org>
To:     "Kirill A. Shutemov" <kirill@shutemov.name>
Cc:     Khalid Aziz <khalid.aziz@oracle.com>, akpm@linux-foundation.org,
        longpeng2@huawei.com, arnd@arndb.de, dave.hansen@linux.intel.com,
        david@redhat.com, rppt@kernel.org, surenb@google.com,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [RFC PATCH 0/6] Add support for shared PTEs across processes
Message-ID: <YfBIpmxvc0+mFByf@casper.infradead.org>
References: <cover.1642526745.git.khalid.aziz@oracle.com>
 <20220125114212.ks2qtncaahi6foan@box.shutemov.name>
 <Ye/5yUyEqO0ws0G5@casper.infradead.org>
 <20220125135917.ezi6itozrchsdcxg@box.shutemov.name>
 <YfAEqzTeBJSIOKcA@casper.infradead.org>
 <20220125185705.wf7p2l77vggipfry@box.shutemov.name>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220125185705.wf7p2l77vggipfry@box.shutemov.name>
Precedence: bulk

On Tue, Jan 25, 2022 at 09:57:05PM +0300, Kirill A. Shutemov wrote:
> On Tue, Jan 25, 2022 at 02:09:47PM +0000, Matthew Wilcox wrote:
> > > I think zero-API approach (plus madvise() hints to tweak it) is worth
> > > considering.
> > 
> > I think the zero-API approach actually misses out on a lot of
> > possibilities that the mshare() approach offers.  For example, mshare()
> > allows you to mmap() many small files in the shared region -- you
> > can't do that with zeroAPI.
> 
> Do you consider a use-case for many small files to be common? I would
> think that the main consumer of the feature to be mmap of huge files.
> And in this case zero enabling burden on userspace side sounds like a
> sweet deal.

mmap() of huge files is certainly the Oracle use-case.  With occasional
funny business like mprotect() of a single page in the middle of a 1GB
hugepage.

The approach of designating ranges of a process's address space as
sharable with other processes felt like the cleaner & frankly more
interesting approach that opens up use-cases other than "hurr, durr, we
are Oracle, we like big files, kernel get out of way now, transactions
to perform".