Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7

From	Mel Gorman <mgorman@techsingularity.net>
Newsgroups	linux.kernel
Subject	Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7
Date	2016-12-07 18:40 +0100
Message-ID	<sLOme-34v-19@gated-at.bofh.it> (permalink)
References	(1 earlier) <sLLRo-1pk-21@gated-at.bofh.it> <sLMNs-1Yv-19@gated-at.bofh.it> <sLNzP-2yE-3@gated-at.bofh.it> <sLNzQ-2yE-9@gated-at.bofh.it> <sLO2S-2Y5-29@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Wed, Dec 07, 2016 at 11:11:08AM -0600, Christoph Lameter wrote:
> On Wed, 7 Dec 2016, Mel Gorman wrote:
> 
> > 3.0-era kernels had better fragmentation control, higher success rates at
> > allocation etc. I vaguely recall that it had fewer sources of high-order
> > allocations but I don't remember specifics and part of that could be the
> > lack of THP at the time. The overhead was massive due to massive stalls
> > and excessive reclaim -- hours to complete some high-allocation stress
> > tests even if the success rate was high.
> 
> There were a couple of high order page reclaim improvements implemented
> at that time that were later abandoned. I think higher order pages were
> more available than now.

There were, the cost was high -- lumpy reclaim was a major source of the
cost but not the only one. The cost of allocation offset any benefit of
having them. At least for hugepages it did, I don't know about SLUB because
I didn't quantify if the benefit of SLUB using huge pages was offset by
the allocation cost (I doubt it). The cost later became intolerable when
THP started hitting those paths routinely.

It's not simply a case of going back to how fragmentation control was
managed then because it'll simply reintroduce excessive stalls in
allocation paths.

-- 
Mel Gorman
SUSE Labs

Thread

[PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-07 11:20 +0100
  Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Christoph Lameter <cl@linux.com> - 2016-12-07 16:00 +0100
    Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-07 17:00 +0100
      Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Christoph Lameter <cl@linux.com> - 2016-12-07 17:50 +0100
        Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-07 17:50 +0100
          Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Christoph Lameter <cl@linux.com> - 2016-12-07 18:20 +0100
            Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-07 18:40 +0100
  Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Eric Dumazet <eric.dumazet@gmail.com> - 2016-12-07 20:10 +0100
    Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Eric Dumazet <eric.dumazet@gmail.com> - 2016-12-07 20:20 +0100
    Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-07 20:50 +0100
      Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Eric Dumazet <eric.dumazet@gmail.com> - 2016-12-07 21:20 +0100
        Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-07 22:30 +0100
          Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-08 00:30 +0100
            Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Jesper Dangaard Brouer <brouer@redhat.com> - 2016-12-08 09:30 +0100
              Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-08 10:20 +0100
                Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Jesper Dangaard Brouer <brouer@redhat.com> - 2016-12-08 11:50 +0100
                Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-08 12:10 +0100
                Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Jesper Dangaard Brouer <brouer@redhat.com> - 2016-12-08 15:50 +0100
                Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-08 16:20 +0100
                Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Jesper Dangaard Brouer <brouer@redhat.com> - 2016-12-08 18:30 +0100
                Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Mel Gorman <mgorman@techsingularity.net> - 2016-12-08 18:40 +0100
                Re: [PATCH] mm: page_alloc: High-order per-cpu page allocator v7 Eric Dumazet <eric.dumazet@gmail.com> - 2016-12-08 17:10 +0100

csiph-web