linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Rik van Riel <riel@redhat.com>
To: Mel Gorman <mgorman@suse.de>
Cc: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Hugh Dickins <hughd@google.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Paul Turner <pjt@google.com>,
	Lee Schermerhorn <Lee.Schermerhorn@hp.com>,
	Alex Shi <lkml.alex@gmail.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Linux-MM <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 36/46] mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
Date: Wed, 21 Nov 2012 14:46:14 -0500	[thread overview]
Message-ID: <50AD2F86.3090303@redhat.com> (raw)
In-Reply-To: <20121121191547.GM8218@suse.de>

On 11/21/2012 02:15 PM, Mel Gorman wrote:
> On Wed, Nov 21, 2012 at 07:25:37PM +0100, Ingo Molnar wrote:

>> As mentioned in my other mail, this patch of yours looks very
>> similar to the numa/core commit attached below, mostly written
>> by Peter:
>>
>>    30f93abc6cb3 sched, numa, mm: Add the scanning page fault machinery

> Just to compare, this is the wording in "autonuma: memory follows CPU
> algorithm and task/mm_autonuma stats collection"
>
> +/*
> + * In this function we build a temporal CPU_node<->page relation by
> + * using a two-stage autonuma_last_nid filter to remove short/unlikely
> + * relations.

Looks like the comment came from sched/numa, but the original code
came from autonuma:

https://lkml.org/lkml/2012/8/22/629

If you want to do a real historical dig, we may still have a picture
of the whiteboard where Karen and I came up with the idea of only
migrating a page after the second touch from the same node :)

That was trying to solve the "how can we make migrate on fault as
cheap as possible?" question, and reviewing some earlier autonuma
codebase.

Not that any of this matters in the least.  AutoNUMA, sched/numa,
and balancenuma have all evolved a lot because they were able to
copy good ideas from each other, and discard overly complex or
simply bad ideas (eg. the NUMA syscalls or async page migration),
while replacing them with simpler, better ideas from the other
code bases.

Now that we (mostly) agree on what the basic infrastructure should
look like, we can figure out which placement policies work best for
various workloads.

Then we can make a choice depending on what works best, independent
of who wrote what.

-- 
All rights reversed

  parent reply	other threads:[~2012-11-21 19:47 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-11-21 10:21 [PATCH 00/46] Automatic NUMA Balancing V4 Mel Gorman
2012-11-21 10:21 ` [PATCH 01/46] x86: mm: only do a local tlb flush in ptep_set_access_flags() Mel Gorman
2012-11-21 10:21 ` [PATCH 02/46] x86: mm: drop TLB flush from ptep_set_access_flags Mel Gorman
2012-11-21 10:21 ` [PATCH 03/46] mm,generic: only flush the local TLB in ptep_set_access_flags Mel Gorman
2012-11-21 10:21 ` [PATCH 04/46] x86/mm: Introduce pte_accessible() Mel Gorman
2012-11-21 10:21 ` [PATCH 05/46] mm: Only flush the TLB when clearing an accessible pte Mel Gorman
2012-11-21 10:21 ` [PATCH 06/46] mm: Count the number of pages affected in change_protection() Mel Gorman
2012-11-21 10:21 ` [PATCH 07/46] mm: Optimize the TLB flush of sys_mprotect() and change_protection() users Mel Gorman
2012-11-21 10:21 ` [PATCH 08/46] mm: compaction: Move migration fail/success stats to migrate.c Mel Gorman
2012-11-21 10:21 ` [PATCH 09/46] mm: migrate: Add a tracepoint for migrate_pages Mel Gorman
2012-11-21 10:21 ` [PATCH 10/46] mm: compaction: Add scanned and isolated counters for compaction Mel Gorman
2012-11-21 10:21 ` [PATCH 11/46] mm: numa: define _PAGE_NUMA Mel Gorman
2012-11-21 10:21 ` [PATCH 12/46] mm: numa: pte_numa() and pmd_numa() Mel Gorman
2012-11-21 10:21 ` [PATCH 13/46] mm: numa: Support NUMA hinting page faults from gup/gup_fast Mel Gorman
2012-11-21 10:21 ` [PATCH 14/46] mm: numa: split_huge_page: transfer the NUMA type from the pmd to the pte Mel Gorman
2012-11-21 10:21 ` [PATCH 15/46] mm: numa: Create basic numa page hinting infrastructure Mel Gorman
2012-11-21 10:21 ` [PATCH 16/46] mm: mempolicy: Make MPOL_LOCAL a real policy Mel Gorman
2012-11-21 10:21 ` [PATCH 17/46] mm: mempolicy: Add MPOL_MF_NOOP Mel Gorman
2012-11-21 10:21 ` [PATCH 18/46] mm: mempolicy: Check for misplaced page Mel Gorman
2012-11-21 10:21 ` [PATCH 19/46] mm: migrate: Introduce migrate_misplaced_page() Mel Gorman
2012-11-21 10:21 ` [PATCH 20/46] mm: mempolicy: Use _PAGE_NUMA to migrate pages Mel Gorman
2012-11-21 10:21 ` [PATCH 21/46] mm: mempolicy: Add MPOL_MF_LAZY Mel Gorman
2012-11-21 10:21 ` [PATCH 22/46] mm: mempolicy: Implement change_prot_numa() in terms of change_protection() Mel Gorman
2012-11-21 10:21 ` [PATCH 23/46] mm: mempolicy: Hide MPOL_NOOP and MPOL_MF_LAZY from userspace for now Mel Gorman
2012-11-21 10:21 ` [PATCH 24/46] mm: numa: Add fault driven placement and migration Mel Gorman
2012-11-21 10:21 ` [PATCH 25/46] mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Mel Gorman
2012-11-21 10:21 ` [PATCH 26/46] sched, numa, mm: Count WS scanning against present PTEs, not virtual memory ranges Mel Gorman
2012-11-21 10:21 ` [PATCH 27/46] mm: sched: numa: Implement slow start for working set sampling Mel Gorman
2012-11-21 10:21 ` [PATCH 28/46] mm: numa: Add pte updates, hinting and migration stats Mel Gorman
2012-11-21 10:21 ` [PATCH 29/46] mm: numa: Migrate on reference policy Mel Gorman
2012-11-21 10:21 ` [PATCH 30/46] mm: numa: Migrate pages handled during a pmd_numa hinting fault Mel Gorman
2012-11-21 10:21 ` [PATCH 31/46] mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting Mel Gorman
2012-11-21 10:21 ` [PATCH 32/46] mm: numa: Rate limit the amount of memory that is migrated between nodes Mel Gorman
2012-11-21 10:21 ` [PATCH 33/46] mm: numa: Rate limit setting of pte_numa if node is saturated Mel Gorman
2012-11-21 10:21 ` [PATCH 34/46] sched: numa: Slowly increase the scanning period as NUMA faults are handled Mel Gorman
2012-11-21 10:21 ` [PATCH 35/46] mm: numa: Introduce last_nid to the page frame Mel Gorman
2012-11-21 10:21 ` [PATCH 36/46] mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships Mel Gorman
2012-11-21 18:25   ` Ingo Molnar
2012-11-21 19:15     ` Mel Gorman
2012-11-21 19:39       ` Mel Gorman
2012-11-21 19:46       ` Rik van Riel [this message]
2012-11-22  0:05         ` Ingo Molnar
2012-11-21 10:21 ` [PATCH 37/46] mm: numa: Add THP migration for the NUMA working set scanning fault case Mel Gorman
2012-11-21 11:24   ` Mel Gorman
2012-11-21 12:21   ` Mel Gorman
2012-11-21 10:21 ` [PATCH 38/46] sched: numa: Introduce tsk_home_node() Mel Gorman
2012-11-21 10:21 ` [PATCH 39/46] sched: numa: Make find_busiest_queue() a method Mel Gorman
2012-11-21 10:21 ` [PATCH 40/46] sched: numa: Implement home-node awareness Mel Gorman
2012-11-21 10:21 ` [PATCH 41/46] sched: numa: Introduce per-mm and per-task structures Mel Gorman
2012-11-21 10:21 ` [PATCH 42/46] sched: numa: CPU follows memory Mel Gorman
2012-11-21 10:21 ` [PATCH 43/46] sched: numa: Rename mempolicy to HOME Mel Gorman
2012-11-21 10:21 ` [PATCH 44/46] sched: numa: Consider only one CPU per node for CPU-follows-memory Mel Gorman
2012-11-21 10:21 ` [PATCH 45/46] balancenuma: no task swap in finding placement Mel Gorman
2012-11-21 10:21 ` [PATCH 46/46] Simple CPU follow Mel Gorman
2012-11-21 16:53 ` [PATCH 00/46] Automatic NUMA Balancing V4 Mel Gorman
2012-11-21 17:03   ` Ingo Molnar
2012-11-21 17:20     ` Mel Gorman
2012-11-21 17:33       ` Ingo Molnar
2012-11-21 18:02         ` Mel Gorman
2012-11-21 18:21           ` Ingo Molnar
2012-11-21 19:01             ` Mel Gorman
2012-11-21 23:27           ` Ingo Molnar
2012-11-22  9:32             ` Mel Gorman
2012-11-22  9:05         ` Ingo Molnar
2012-11-22  9:43           ` Mel Gorman
2012-11-22 12:56   ` 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=50AD2F86.3090303@redhat.com \
    --to=riel@redhat.com \
    --cc=Lee.Schermerhorn@hp.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lkml.alex@gmail.com \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=pjt@google.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    /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).