From: Mel Gorman <mgorman@suse.de>
To: Hillf Danton <dhillf@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Andrea Arcangeli <aarcange@redhat.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Paul Turner <pjt@google.com>,
Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
Christoph Lameter <cl@linux.com>, Rik van Riel <riel@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: Comparison between three trees (was: Latest numa/core release, v17)
Date: Mon, 26 Nov 2012 09:38:26 +0000 [thread overview]
Message-ID: <20121126093826.GG8218@suse.de> (raw)
In-Reply-To: <CAJd=RBCUZn4gvzAME0Xm98TCBRnY_201R3dkKaWMySYr4hNmFA@mail.gmail.com>
On Sun, Nov 25, 2012 at 04:47:15PM +0800, Hillf Danton wrote:
> On 11/24/12, Mel Gorman <mgorman@suse.de> wrote:
> > Warning: This is an insanely long mail and there a lot of data here. Get
> > coffee or something.
> >
> > This is another round of comparisons between the latest released versions
> > of each of three automatic numa balancing trees that are out there.
> >
> > From the series "Automatic NUMA Balancing V5", the kernels tested were
> >
> > stats-v5r1 Patches 1-10. TLB optimisations, migration stats
> > thpmigrate-v5r1 Patches 1-37. Basic placement policy, PMD handling, THP
> > migration etc.
> > adaptscan-v5r1 Patches 1-38. Heavy handed PTE scan reduction
> > delaystart-v5r1 Patches 1-40. Delay the PTE scan until running on a new
> > node
> >
> > If I just say balancenuma, I mean the "delaystart-v5r1" kernel. The other
> > kernels are included so you can see the impact the scan rate adaption
> > patch has and what that might mean for a placement policy using a proper
> > feedback mechanism.
> >
> > The other two kernels were
> >
> > numacore-20121123 It was no longer clear what the deltas between releases
> > and
> > the dependencies might be so I just pulled tip/master on November
> > 23rd, 2012. An earlier pull had serious difficulties and the patch
> > responsible has been dropped since. This is not a like-with-like
> > comparison as the tree contains numerous other patches but it's
> > the best available given the timeframe
> >
> > autonuma-v28fast This is a rebased version of Andrea's autonuma-v28fast
> > branch with Hugh's THP migration patch on top.
>
> FYI, based on how target huge page is selected,
>
> +
> + new_page = alloc_pages_node(numa_node_id(),
> + (GFP_TRANSHUGE | GFP_THISNODE) & ~__GFP_WAIT, HPAGE_PMD_ORDER);
>
> the thp replacement policy is changed to be MORON,
>
That is likely true. When rebasing a policy on top of balancenuma it is
important to keep an eye on what node is used for target migration and
what node is passed to task_numa_fault() and confirm this is the node
the policy expects.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-11-26 9:38 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-22 22:49 [PATCH 00/33] Latest numa/core release, v17 Ingo Molnar
2012-11-22 22:49 ` [PATCH 01/33] mm/generic: Only flush the local TLB in ptep_set_access_flags() Ingo Molnar
2012-11-22 22:49 ` [PATCH 02/33] x86/mm: Only do a local tlb flush " Ingo Molnar
2012-11-22 22:49 ` [PATCH 03/33] x86/mm: Introduce pte_accessible() Ingo Molnar
2012-11-22 22:49 ` [PATCH 04/33] mm: Only flush the TLB when clearing an accessible pte Ingo Molnar
2012-11-22 22:49 ` [PATCH 05/33] x86/mm: Completely drop the TLB flush from ptep_set_access_flags() Ingo Molnar
2012-11-22 22:49 ` [PATCH 06/33] mm: Count the number of pages affected in change_protection() Ingo Molnar
2012-11-22 22:49 ` [PATCH 07/33] mm: Optimize the TLB flush of sys_mprotect() and change_protection() users Ingo Molnar
2012-11-22 22:49 ` [PATCH 08/33] sched, numa, mm: Add last_cpu to page flags Ingo Molnar
2012-11-22 22:49 ` [PATCH 09/33] sched, mm, numa: Create generic NUMA fault infrastructure, with architectures overrides Ingo Molnar
2012-11-22 22:49 ` [PATCH 10/33] sched: Make find_busiest_queue() a method Ingo Molnar
2012-11-22 22:49 ` [PATCH 11/33] sched, numa, mm: Describe the NUMA scheduling problem formally Ingo Molnar
2012-11-22 22:49 ` [PATCH 12/33] numa, mm: Support NUMA hinting page faults from gup/gup_fast Ingo Molnar
2012-11-22 22:49 ` [PATCH 13/33] mm/migrate: Introduce migrate_misplaced_page() Ingo Molnar
2012-11-22 22:49 ` [PATCH 14/33] mm/migration: Improve migrate_misplaced_page() Ingo Molnar
2012-11-22 22:49 ` [PATCH 15/33] sched, numa, mm, arch: Add variable locality exception Ingo Molnar
2012-11-22 22:49 ` [PATCH 16/33] sched, numa, mm: Add credits for NUMA placement Ingo Molnar
2012-11-22 22:49 ` [PATCH 17/33] sched, mm, x86: Add the ARCH_SUPPORTS_NUMA_BALANCING flag Ingo Molnar
2012-11-22 22:49 ` [PATCH 18/33] sched, numa, mm: Add the scanning page fault machinery Ingo Molnar
2012-12-04 0:56 ` [patch] mm, mempolicy: Introduce spinlock to read shared policy tree David Rientjes
2012-12-20 18:34 ` Linus Torvalds
2012-12-20 22:55 ` David Rientjes
2012-12-21 13:47 ` Mel Gorman
2012-12-21 16:53 ` Linus Torvalds
2012-12-21 18:21 ` Hugh Dickins
2012-12-21 21:51 ` Linus Torvalds
2012-12-21 19:58 ` Mel Gorman
2012-12-21 22:02 ` Linus Torvalds
2012-12-21 23:10 ` Mel Gorman
2012-12-22 0:36 ` Linus Torvalds
2013-01-02 19:43 ` KOSAKI Motohiro
2012-11-22 22:49 ` [PATCH 19/33] sched: Add adaptive NUMA affinity support Ingo Molnar
2012-11-26 20:32 ` Sasha Levin
2012-11-22 22:49 ` [PATCH 20/33] sched: Implement constant, per task Working Set Sampling (WSS) rate Ingo Molnar
2012-11-22 22:49 ` [PATCH 21/33] sched, numa, mm: Count WS scanning against present PTEs, not virtual memory ranges Ingo Molnar
2012-11-22 22:49 ` [PATCH 22/33] sched: Implement slow start for working set sampling Ingo Molnar
2012-11-22 22:49 ` [PATCH 23/33] sched, numa, mm: Interleave shared tasks Ingo Molnar
2012-11-22 22:49 ` [PATCH 24/33] sched: Implement NUMA scanning backoff Ingo Molnar
2012-11-22 22:49 ` [PATCH 25/33] sched: Improve convergence Ingo Molnar
2012-11-22 22:49 ` [PATCH 26/33] sched: Introduce staged average NUMA faults Ingo Molnar
2012-11-22 22:49 ` [PATCH 27/33] sched: Track groups of shared tasks Ingo Molnar
2012-11-22 22:49 ` [PATCH 28/33] sched: Use the best-buddy 'ideal cpu' in balancing decisions Ingo Molnar
2012-11-22 22:49 ` [PATCH 29/33] sched, mm, mempolicy: Add per task mempolicy Ingo Molnar
2012-11-22 22:49 ` [PATCH 30/33] sched: Average the fault stats longer Ingo Molnar
2012-11-22 22:49 ` [PATCH 31/33] sched: Use the ideal CPU to drive active balancing Ingo Molnar
2012-11-22 22:49 ` [PATCH 32/33] sched: Add hysteresis to p->numa_shared Ingo Molnar
2012-11-22 22:49 ` [PATCH 33/33] sched: Track shared task's node groups and interleave their memory allocations Ingo Molnar
2012-11-22 22:53 ` [PATCH 00/33] Latest numa/core release, v17 Ingo Molnar
2012-11-23 6:47 ` Zhouping Liu
2012-11-23 17:32 ` Comparison between three trees (was: Latest numa/core release, v17) Mel Gorman
2012-11-25 8:47 ` Hillf Danton
2012-11-26 9:38 ` Mel Gorman [this message]
2012-11-25 23:37 ` Mel Gorman
2012-11-25 23:40 ` Mel Gorman
2012-11-26 13:33 ` Mel Gorman
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=20121126093826.GG8218@suse.de \
--to=mgorman@suse.de \
--cc=Lee.Schermerhorn@hp.com \
--cc=a.p.zijlstra@chello.nl \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=dhillf@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@kernel.org \
--cc=pjt@google.com \
--cc=riel@redhat.com \
/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).