Re: dm ioctl: Restore __GFP_HIGH in copy_params()

From: Michal Hocko <mhocko@kernel.org>
To: Mike Snitzer <snitzer@redhat.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>,
	Junaid Shahid <junaids@google.com>,
	David Rientjes <rientjes@google.com>,
	Alasdair Kergon <agk@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, andreslc@google.com, gthelen@google.com,
	vbabka@suse.cz, linux-kernel@vger.kernel.org
Subject: Re: dm ioctl: Restore __GFP_HIGH in copy_params()
Date: Tue, 23 May 2017 08:49:44 +0200	[thread overview]
Message-ID: <20170523064944.GA12818@dhcp22.suse.cz> (raw)
In-Reply-To: <20170522180415.GA25340@redhat.com>

On Mon 22-05-17 14:04:15, Mike Snitzer wrote:
> On Mon, May 22 2017 at 11:03am -0400,
> Michal Hocko <mhocko@kernel.org> wrote:
> 
> > On Mon 22-05-17 10:52:44, Mikulas Patocka wrote:
> > > 
> > > 
> > > On Mon, 22 May 2017, Michal Hocko wrote:
> > [...] 
> > > > I am not sure I understand. OOM killer is invoked for _all_ allocations
> > > > <= PAGE_ALLOC_COSTLY_ORDER that do not have __GFP_NORETRY as long as the
> > > > OOM killer is not disabled (oom_killer_disable) and that only happens
> > > > from the PM suspend path which makes sure that no userspace is active at
> > > > the time. AFAIU this is a userspace triggered path and so the later
> > > > shouldn't apply to it and GFP_KERNEL should be therefore sufficient.
> > > > Relying to a portion of memory reserves to prevent from deadlock seems
> > > > fundamentaly broken  to me.
> > > > 
> > > 
> > > The lvm2 was designed this way - it is broken, but there is not much that 
> > > can be done about it - fixing this would mean major rewrite. The only 
> > > thing we can do about it is to lower the deadlock probability with 
> > > __GFP_HIGH (or PF_MEMALLOC that was used some times ago).
> 
> Yes, lvm2 was originally designed to to have access to memory reserves
> to ensure forward progress.  But if the mm subsystem has improved to
> allow for the required progress without lvm2 trying to stake a claim on
> those reserves then we'll gladly avoid (ab)using them.
> 
> > But let me repeat. GFP_KERNEL allocation for order-0 page will not fail.
> 
> OK, but will it be serviced immediately?  Not failing isn't useful if it
> never completes.

Well, GFP_KERNEL will not guarantee an immediate success of course.
There is nothing like that. Nor __GFP_HIGH will guarantee that, though,
because reserves can get easily depleted by some workloads. You would
have to use a dedicated memory pool to accomplish what you really need.

-- 
Michal Hocko
SUSE Labs