Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: Plumbers 2018 - Performance and Scalability Microconference
To:     John Hubbard <jhubbard@nvidia.com>,
        Daniel Jordan <daniel.m.jordan@oracle.com>,
        linux-kernel@vger.kernel.org,
        "linux-mm@kvack.org" <linux-mm@kvack.org>
Cc:     Aaron Lu <aaron.lu@intel.com>, alex.kogan@oracle.com,
        akpm@linux-foundation.org, boqun.feng@gmail.com, brouer@redhat.com,
        dave@stgolabs.net, dave.dice@oracle.com,
        Dhaval Giani <dhaval.giani@oracle.com>, ktkhai@virtuozzo.com,
        ldufour@linux.vnet.ibm.com, Pavel.Tatashin@microsoft.com,
        paulmck@linux.vnet.ibm.com, shady.issa@oracle.com,
        tariqt@mellanox.com, tglx@linutronix.de, tim.c.chen@intel.com,
        vbabka@suse.cz, yang.shi@linux.alibaba.com, shy828301@gmail.com,
        Huang Ying <ying.huang@intel.com>, subhra.mazumdar@oracle.com,
        Steven Sistare <steven.sistare@oracle.com>, jwadams@google.com,
        ashwinch@google.com, sqazi@google.com,
        Shakeel Butt <shakeelb@google.com>, walken@google.com,
        rientjes@google.com, junaids@google.com,
        Neha Agarwal <nehaagarwal@google.com>
References: <1dc80ff6-f53f-ae89-be29-3408bf7d69cc@oracle.com>
 <35c2c79f-efbe-f6b2-43a6-52da82145638@nvidia.com>
From:   Waiman Long <longman@redhat.com>
Organization: Red Hat
Message-ID: <55b44432-ade5-f090-bfe7-ea20f3e87285@redhat.com>
Date:   Mon, 10 Sep 2018 13:09:36 -0400
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.2.0
MIME-Version: 1.0
In-Reply-To: <35c2c79f-efbe-f6b2-43a6-52da82145638@nvidia.com>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 8BIT
Content-Language: en-US
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 09/08/2018 12:13 AM, John Hubbard wrote:
>
> Hi Daniel and all,
>
> I'm interested in the first 3 of those 4 topics, so if it doesn't conflict with HMM topics or
> fix-gup-with-dma topics, I'd like to attend. GPUs generally need to access large chunks of
> memory, and that includes migrating (dma-copying) pages around.  
>
> So for example a multi-threaded migration of huge pages between normal RAM and GPU memory is an 
> intriguing direction (and I realize that it's a well-known topic, already). Doing that properly
> (how many threads to use?) seems like it requires scheduler interaction.
>
> It's also interesting that there are two main huge page systems (THP and Hugetlbfs), and I sometimes
> wonder the obvious thing to wonder: are these sufficiently different to warrant remaining separate,
> long-term?  Yes, I realize they're quite different in some ways, but still, one wonders. :)

One major difference between hugetlbfs and THP is that the former has to
be explicitly managed by the applications that use it whereas the latter
is done automatically without the applications being aware that THP is
being used at all. Performance wise, THP may or may not increase
application performance depending on the exact memory access pattern,
though the chance is usually higher that an application will benefit
than suffer from it.

If an application know what it is doing, using hughtblfs can boost
performance more than it can ever achieved by THP. Many large enterprise
applications, like Oracle DB, are using hugetlbfs and explicitly disable
THP. So unless THP can improve its performance to a level that is
comparable to hugetlbfs, I won't see the later going away.

Cheers,
Longman