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;
IronPort-SDR: eeWUMD5TmW44ehesPTe0dDv3zRkGFeu22ePdMUC1BgZBId4XPB5SRxhIFoqXjxWsstSaTkiqzS
 cr324eVhKYFQ==
IronPort-SDR: QCMEmJVGU4YRIlf3c8nrQuc6htZOOa+ZRn+Sspn6ODAOJkoxoLLiK0AydEmNBGlFp5GTZYixn3
 KkjqwcEajcnQ==
Date:   Wed, 3 Mar 2021 09:22:50 -0800
From:   Ben Widawsky <ben.widawsky@intel.com>
To:     Michal Hocko <mhocko@suse.com>
Cc:     Feng Tang <feng.tang@intel.com>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Andrea Arcangeli <aarcange@redhat.com>,
        David Rientjes <rientjes@google.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Randy Dunlap <rdunlap@infradead.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        "Hansen, Dave" <dave.hansen@intel.com>,
        Andi leen <ak@linux.intel.com>,
        "Williams, Dan J" <dan.j.williams@intel.com>
Subject: Re: [PATCH v3 RFC 14/14] mm: speedup page alloc for
 MPOL_PREFERRED_MANY by adding a NO_SLOWPATH gfp bit
Message-ID: <20210303172250.wbp47skyuf6r37wi@intel.com>
Mail-Followup-To: Michal Hocko <mhocko@suse.com>,
        Feng Tang <feng.tang@intel.com>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Andrea Arcangeli <aarcange@redhat.com>,
        David Rientjes <rientjes@google.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Randy Dunlap <rdunlap@infradead.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        "Hansen, Dave" <dave.hansen@intel.com>,
        Andi leen <ak@linux.intel.com>,
        "Williams, Dan J" <dan.j.williams@intel.com>
References: <1614766858-90344-15-git-send-email-feng.tang@intel.com>
 <YD91jTMssJUCupJm@dhcp22.suse.cz>
 <20210303120717.GA16736@shbuild999.sh.intel.com>
 <20210303121833.GB16736@shbuild999.sh.intel.com>
 <YD+BvvM/388AVnmm@dhcp22.suse.cz>
 <20210303131832.GB78458@shbuild999.sh.intel.com>
 <20210303134644.GC78458@shbuild999.sh.intel.com>
 <YD+WR5cpuWhybm2L@dhcp22.suse.cz>
 <20210303163141.v5wu2sfo2zj2qqsw@intel.com>
 <YD/D9hckPOA+41+D@dhcp22.suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <YD/D9hckPOA+41+D@dhcp22.suse.cz>
Precedence: bulk

On 21-03-03 18:14:30, Michal Hocko wrote:
> On Wed 03-03-21 08:31:41, Ben Widawsky wrote:
> > On 21-03-03 14:59:35, Michal Hocko wrote:
> > > On Wed 03-03-21 21:46:44, Feng Tang wrote:
> > > > On Wed, Mar 03, 2021 at 09:18:32PM +0800, Tang, Feng wrote:
> > > > > On Wed, Mar 03, 2021 at 01:32:11PM +0100, Michal Hocko wrote:
> > > > > > On Wed 03-03-21 20:18:33, Feng Tang wrote:
> > > [...]
> > > > > > > One thing I tried which can fix the slowness is:
> > > > > > > 
> > > > > > > +	gfp_mask &= ~(__GFP_DIRECT_RECLAIM | __GFP_KSWAPD_RECLAIM);
> > > > > > > 
> > > > > > > which explicitly clears the 2 kinds of reclaim. And I thought it's too
> > > > > > > hacky and didn't mention it in the commit log.
> > > > > > 
> > > > > > Clearing __GFP_DIRECT_RECLAIM would be the right way to achieve
> > > > > > GFP_NOWAIT semantic. Why would you want to exclude kswapd as well? 
> > > > > 
> > > > > When I tried gfp_mask &= ~__GFP_DIRECT_RECLAIM, the slowness couldn't
> > > > > be fixed.
> > > > 
> > > > I just double checked by rerun the test, 'gfp_mask &= ~__GFP_DIRECT_RECLAIM'
> > > > can also accelerate the allocation much! though is still a little slower than
> > > > this patch. Seems I've messed some of the tries, and sorry for the confusion!
> > > > 
> > > > Could this be used as the solution? or the adding another fallback_nodemask way?
> > > > but the latter will change the current API quite a bit.
> > > 
> > > I haven't got to the whole series yet. The real question is whether the
> > > first attempt to enforce the preferred mask is a general win. I would
> > > argue that it resembles the existing single node preferred memory policy
> > > because that one doesn't push heavily on the preferred node either. So
> > > dropping just the direct reclaim mode makes some sense to me.
> > > 
> > > IIRC this is something I was recommending in an early proposal of the
> > > feature.
> > 
> > My assumption [FWIW] is that the usecases we've outlined for multi-preferred
> > would want more heavy pushing on the preference mask. However, maybe the uapi
> > could dictate how hard to try/not try.
> 
> What does that mean and what is the expectation from the kernel to be
> more or less cast in stone?
> 

(I'm not positive I've understood your question, so correct me if I
misunderstood)

I'm not sure there is a stone-cast way to define it nor should we. At the very
least though, something in uapi that has a general mapping to GFP flags
(specifically around reclaim) for the first round of allocation could make
sense.

In my head there are 3 levels of request possible for multiple nodes:
1. BIND: Those nodes or die.
2. Preferred hard: Those nodes and I'm willing to wait. Fallback if impossible.
3. Preferred soft: Those nodes but I don't want to wait.

Current UAPI in the series doesn't define a distinction between 2, and 3. As I
understand the change, Feng is defining the behavior to be #3, which makes #2
not an option. I sort of punted on defining it entirely, in the beginning.