linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Feng Tang <feng.tang@intel.com>
To: Michal Hocko <mhocko@suse.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
Date: Thu, 4 Mar 2021 16:14:14 +0800	[thread overview]
Message-ID: <20210304081414.GC43191@shbuild999.sh.intel.com> (raw)
In-Reply-To: <20210303172250.wbp47skyuf6r37wi@intel.com>

On Wed, Mar 03, 2021 at 09:22:50AM -0800, Ben Widawsky wrote:
> 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.

As discussed earlier in the thread, one less hacky solution is to clear
__GFP_DIRECT_RECLAIM bit so that it won't go into direct reclaim, but still
wakeup the kswapd of target nodes and retry, which sits now between 'Preferred hard'
and 'Preferred soft' :)

For current MPOL_PREFERRED, its semantic is also 'Preferred hard', that it
will check free memory of other nodes before entering slowpath waiting.

Thanks,
Feng


  reply	other threads:[~2021-03-04  8:15 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-03 10:20 [PATCH v3 00/14] Introduced multi-preference mempolicy Feng Tang
2021-03-03 10:20 ` [PATCH v3 01/14] mm/mempolicy: Add comment for missing LOCAL Feng Tang
2021-03-10  6:27   ` Feng Tang
2021-03-03 10:20 ` [PATCH v3 02/14] mm/mempolicy: convert single preferred_node to full nodemask Feng Tang
2021-03-03 10:20 ` [PATCH v3 03/14] mm/mempolicy: Add MPOL_PREFERRED_MANY for multiple preferred nodes Feng Tang
2021-03-03 10:20 ` [PATCH v3 04/14] mm/mempolicy: allow preferred code to take a nodemask Feng Tang
2021-03-03 10:20 ` [PATCH v3 05/14] mm/mempolicy: refactor rebind code for PREFERRED_MANY Feng Tang
2021-03-03 10:20 ` [PATCH v3 06/14] mm/mempolicy: kill v.preferred_nodes Feng Tang
2021-03-03 10:20 ` [PATCH v3 07/14] mm/mempolicy: handle MPOL_PREFERRED_MANY like BIND Feng Tang
2021-03-03 10:20 ` [PATCH v3 08/14] mm/mempolicy: Create a page allocator for policy Feng Tang
2021-03-03 10:20 ` [PATCH v3 09/14] mm/mempolicy: Thread allocation for many preferred Feng Tang
2021-03-03 10:20 ` [PATCH v3 10/14] mm/mempolicy: VMA " Feng Tang
2021-03-03 10:20 ` [PATCH v3 11/14] mm/mempolicy: huge-page " Feng Tang
2021-03-03 10:20 ` [PATCH v3 12/14] mm/mempolicy: Advertise new MPOL_PREFERRED_MANY Feng Tang
2021-03-03 10:20 ` [PATCH v3 13/14] mem/mempolicy: unify mpol_new_preferred() and mpol_new_preferred_many() Feng Tang
2021-03-03 10:20 ` [PATCH v3 RFC 14/14] mm: speedup page alloc for MPOL_PREFERRED_MANY by adding a NO_SLOWPATH gfp bit Feng Tang
2021-03-03 11:39   ` Michal Hocko
2021-03-03 12:07     ` Feng Tang
2021-03-03 12:18       ` Feng Tang
2021-03-03 12:32         ` Michal Hocko
2021-03-03 13:18           ` Feng Tang
2021-03-03 13:46             ` Feng Tang
2021-03-03 13:59               ` Michal Hocko
2021-03-03 16:31                 ` Ben Widawsky
2021-03-03 16:48                   ` Dave Hansen
2021-03-10  5:19                     ` Feng Tang
2021-03-10  9:44                       ` Michal Hocko
2021-03-10 11:49                         ` Feng Tang
2021-03-03 17:14                   ` Michal Hocko
2021-03-03 17:22                     ` Ben Widawsky
2021-03-04  8:14                       ` Feng Tang [this message]
2021-03-04 12:59                         ` Michal Hocko
2021-03-05  2:21                           ` Feng Tang
2021-03-04 12:57                       ` Michal Hocko
2021-03-03 13:53             ` Michal Hocko

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210304081414.GC43191@shbuild999.sh.intel.com \
    --to=feng.tang@intel.com \
    --cc=aarcange@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=rdunlap@infradead.org \
    --cc=rientjes@google.com \
    --cc=vbabka@suse.cz \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).