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:   Wed, 29 Apr 2020 11:00:45 +0200
From:   Michal Hocko <mhocko@kernel.org>
To:     peter enderborg <peter.enderborg@sony.com>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        David Rientjes <rientjes@google.com>,
        Vlastimil Babka <vbabka@suse.cz>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: Re: [patch] mm, oom: stop reclaiming if GFP_ATOMIC will start
 failing soon
Message-ID: <20200429090045.GW28637@dhcp22.suse.cz>
References: <alpine.DEB.2.22.394.2004241347310.70176@chino.kir.corp.google.com>
 <20200425172706.26b5011293e8dc77b1dccaf3@linux-foundation.org>
 <alpine.DEB.2.22.394.2004261959310.80211@chino.kir.corp.google.com>
 <20200427133051.b71f961c1bc53a8e72c4f003@linux-foundation.org>
 <alpine.DEB.2.22.394.2004271558540.248401@chino.kir.corp.google.com>
 <20200427163558.5b08487d63da3cc7a89bf50b@linux-foundation.org>
 <20200428074301.GK28637@dhcp22.suse.cz>
 <94f9b716-b251-79d8-2c8c-70d63a255496@sony.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <94f9b716-b251-79d8-2c8c-70d63a255496@sony.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed 29-04-20 10:31:41, peter enderborg wrote:
> On 4/28/20 9:43 AM, Michal Hocko wrote:
> > On Mon 27-04-20 16:35:58, Andrew Morton wrote:
> > [...]
> >> No consumer of GFP_ATOMIC memory should consume an unbounded amount of
> >> it.
> >> Subsystems such as networking will consume a certain amount and
> >> will then start recycling it.  The total amount in-flight will vary
> >> over the longer term as workloads change.  A dynamically tuning
> >> threshold system will need to adapt rapidly enough to sudden load
> >> shifts, which might require unreasonable amounts of headroom.
> > I do agree. __GFP_HIGH/__GFP_ATOMIC are bound by the size of the
> > reserves under memory pressure. Then allocatios start failing very
> > quickly and users have to cope with that, usually by deferring to a
> > sleepable context. Tuning reserves dynamically for heavy reserves
> > consumers would be possible but I am worried that this is far from
> > trivial.
> >
> > We definitely need to understand what is going on here.  Why doesn't
> > kswapd + N*direct reclaimers do not provide enough memory to satisfy
> > both N threads + reserves consumers? How many times those direct
> > reclaimers have to retry?
> 
> Was this not supposed to be avoided with PSI, user-space should
> a fair change to take actions before it goes bad in user-space?

Yes, PSI is certainly a tool to help userspace make actions on heavy
reclaim. And I agree that if there is a desire to trigger the oom killer
early as David states elsewhere in the thread then this approach should
be considered.
-- 
Michal Hocko
SUSE Labs