Re: [Lsf-pc] [LSF/MM/BPF TOPIC] Do not pin pages for various direct-io scheme

From: Dan Williams <dan.j.williams@intel.com>
To: Jerome Glisse <jglisse@redhat.com>
Cc: linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	linux-mm <linux-mm@kvack.org>,
	 lsf-pc@lists.linux-foundation.org, Jens Axboe <axboe@kernel.dk>,
	 Benjamin LaHaise <bcrl@kvack.org>
Subject: Re: [Lsf-pc] [LSF/MM/BPF TOPIC] Do not pin pages for various direct-io scheme
Date: Wed, 22 Jan 2020 07:56:50 -0800	[thread overview]
Message-ID: <CAPcyv4hF-bagqZk-n_2QyvG5zE=5uSWJnbkDsfY3FYHT0+F6FQ@mail.gmail.com> (raw)
In-Reply-To: <20200122050012.GD76712@redhat.com>

On Tue, Jan 21, 2020 at 9:04 PM Jerome Glisse <jglisse@redhat.com> wrote:
>
> On Tue, Jan 21, 2020 at 08:19:54PM -0800, Dan Williams wrote:
> > On Tue, Jan 21, 2020 at 6:34 PM <jglisse@redhat.com> wrote:
> > >
> > > From: Jérôme Glisse <jglisse@redhat.com>
> > >
> > > Direct I/O does pin memory through GUP (get user page) this does
> > > block several mm activities like:
> > >     - compaction
> > >     - numa
> > >     - migration
> > >     ...
> > >
> > > It is also troublesome if the pinned pages are actualy file back
> > > pages that migth go under writeback. In which case the page can
> > > not be write protected from direct-io point of view (see various
> > > discussion about recent work on GUP [1]). This does happens for
> > > instance if the virtual memory address use as buffer for read
> > > operation is the outcome of an mmap of a regular file.
> > >
> > >
> > > With direct-io or aio (asynchronous io) pages are pinned until
> > > syscall completion (which depends on many factors: io size,
> > > block device speed, ...). For io-uring pages can be pinned an
> > > indifinite amount of time.
> > >
> > >
> > > So i would like to convert direct io code (direct-io, aio and
> > > io-uring) to obey mmu notifier and thus allow memory management
> > > and writeback to work and behave like any other process memory.
> > >
> > > For direct-io and aio this mostly gives a way to wait on syscall
> > > completion. For io-uring this means that buffer might need to be
> > > re-validated (ie looking up pages again to get the new set of
> > > pages for the buffer). Impact for io-uring is the delay needed
> > > to lookup new pages or wait on writeback (if necessary). This
> > > would only happens _if_ an invalidation event happens, which it-
> > > self should only happen under memory preissure or for NUMA
> > > activities.
> >
> > This seems to assume that memory pressure and NUMA migration are rare
> > events. Some of the proposed hierarchical memory management schemes
> > [1] might impact that assumption.
> >
> > [1]: http://lore.kernel.org/r/20191101075727.26683-1-ying.huang@intel.com/
> >
>
> Yes, it is true that it will likely becomes more and more an issues.
> We are facing a tough choice here as pining block NUMA or any kind of
> migration and thus might impede performance while invalidating an io-
> uring buffer will also cause a small latency burst. I do not think we
> can make everyone happy but at very least we should avoid pining and
> provide knobs to let user decide what they care more about (ie io with-
> out burst or better NUMA locality).

It's a question of tradeoffs and this proposal seems to have already
decided that the question should be answered in favor a GPU/SVM
centric view of the world without presenting the alternative.
Direct-I/O colliding with GPU operations might also be solved by
always triggering a migration, and applications that care would avoid
colliding operations that slow down their GPU workload. A slow compat
fallback that applications can programmatically avoid is more flexible
than an upfront knob.