From: Mel Gorman <mgorman@suse.de>
To: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
Andrea Arcangeli <aarcange@redhat.com>,
Ingo Molnar <mingo@kernel.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Hugh Dickins <hughd@google.com>,
Thomas Gleixner <tglx@linutronix.de>,
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 13/19] mm: mempolicy: Use _PAGE_NUMA to migrate pages
Date: Wed, 7 Nov 2012 12:32:18 +0000 [thread overview]
Message-ID: <20121107123218.GY8218@suse.de> (raw)
In-Reply-To: <5099627A.20205@redhat.com>
On Tue, Nov 06, 2012 at 02:18:18PM -0500, Rik van Riel wrote:
> On 11/06/2012 04:14 AM, Mel Gorman wrote:
> >Note: Based on "mm/mpol: Use special PROT_NONE to migrate pages" but
> > sufficiently different that the signed-off-bys were dropped
> >
> >Combine our previous _PAGE_NUMA, mpol_misplaced and migrate_misplaced_page()
> >pieces into an effective migrate on fault scheme.
> >
> >Note that (on x86) we rely on PROT_NONE pages being !present and avoid
> >the TLB flush from try_to_unmap(TTU_MIGRATION). This greatly improves the
> >page-migration performance.
> >
> >Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
> >Signed-off-by: Mel Gorman <mgorman@suse.de>
>
>
> > page = vm_normal_page(vma, addr, pte);
> > BUG_ON(!page);
> >+
> >+ get_page(page);
> >+ current_nid = page_to_nid(page);
> >+ target_nid = mpol_misplaced(page, vma, addr);
> >+ if (target_nid == -1)
> >+ goto clear_pmdnuma;
> >+
> >+ pte_unmap_unlock(ptep, ptl);
> >+ migrate_misplaced_page(page, target_nid);
> >+ page = NULL;
> >+
> >+ ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
> >+ if (!pte_same(*ptep, pte))
> >+ goto out_unlock;
> >+
>
> I see you tried to avoid the extraneous TLB flush
> from inside migrate_misplaced_page.
Yeah, I leave the pte_numa in place until after the migration to avoid it.
> However,
> try_to_unmap_one calls ptep_clear_flush, which will
> currently still result in a remote TLB flush for
> a _PAGE_NUMA pte, despite the pte not being
> accessible for memory accesses (_PAGE_PRESENT not set).
>
Well spotted, I'll fix it up.
> Furthermore, if migrate_misplaced_page moved the page,
> the !pte_same check will return false, and you will
> get a double fault.
>
Yes, you're right. autonuma avoids this problem by clearing _PAGE_NUMA
before the migration happens but then it will incur the TLB flush
overhead.
> I wonder if migrate_misplaced_page should return a
> struct page* or a pfn, so we can compute what "pte"
> _should_ be, corrected for the new pfn, feed that
> value to pte_same, and then avoid the double fault?
>
I think I can do that without reaching too far into migrate.c by abusing
the migration callback handler to return the location of the new page.
I'll see what I can do.
> Also, we may want the change for ptep_clear_flush
> that avoids flushing remote TLBs for a pte without
> the _PAGE_PRESENT bit set.
>
Maybe but initially I'll limit it to try_to_unmap_one.
Thanks!
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2012-11-07 12:32 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-06 9:14 [RFC PATCH 00/19] Foundation for automatic NUMA balancing Mel Gorman
2012-11-06 9:14 ` [PATCH 01/19] mm: compaction: Move migration fail/success stats to migrate.c Mel Gorman
2012-11-06 17:32 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 02/19] mm: migrate: Add a tracepoint for migrate_pages Mel Gorman
2012-11-06 17:33 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 03/19] mm: compaction: Add scanned and isolated counters for compaction Mel Gorman
2012-11-06 17:35 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 04/19] mm: numa: define _PAGE_NUMA Mel Gorman
2012-11-06 18:35 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 05/19] mm: numa: pte_numa() and pmd_numa() Mel Gorman
2012-11-13 9:54 ` Ingo Molnar
2012-11-13 11:24 ` Mel Gorman
2012-11-06 9:14 ` [PATCH 06/19] mm: numa: teach gup_fast about pmd_numa Mel Gorman
2012-11-13 10:07 ` Ingo Molnar
2012-11-13 11:37 ` Mel Gorman
2012-11-13 13:51 ` Ingo Molnar
2012-11-06 9:14 ` [PATCH 07/19] mm: numa: split_huge_page: transfer the NUMA type from the pmd to the pte Mel Gorman
2012-11-06 9:14 ` [PATCH 08/19] mm: numa: Create basic numa page hinting infrastructure Mel Gorman
2012-11-06 18:58 ` Rik van Riel
2012-11-07 10:38 ` Mel Gorman
2012-11-07 10:48 ` Rik van Riel
2012-11-07 11:00 ` Mel Gorman
2012-11-13 10:21 ` Ingo Molnar
2012-11-13 11:50 ` Mel Gorman
2012-11-13 13:49 ` Ingo Molnar
2012-11-13 14:26 ` Mel Gorman
2012-11-06 9:14 ` [PATCH 09/19] mm: mempolicy: Make MPOL_LOCAL a real policy Mel Gorman
2012-11-06 9:14 ` [PATCH 10/19] mm: mempolicy: Add MPOL_MF_NOOP Mel Gorman
2012-11-06 9:14 ` [PATCH 11/19] mm: mempolicy: Check for misplaced page Mel Gorman
2012-11-06 9:14 ` [PATCH 12/19] mm: migrate: Introduce migrate_misplaced_page() Mel Gorman
2012-11-06 19:10 ` Rik van Riel
2012-11-13 9:36 ` Ingo Molnar
2012-11-13 11:43 ` Ingo Molnar
2012-11-13 11:56 ` Mel Gorman
2012-11-13 14:49 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 13/19] mm: mempolicy: Use _PAGE_NUMA to migrate pages Mel Gorman
2012-11-06 19:18 ` Rik van Riel
2012-11-07 12:32 ` Mel Gorman [this message]
2012-11-06 9:14 ` [PATCH 14/19] mm: mempolicy: Add MPOL_MF_LAZY Mel Gorman
2012-11-06 19:19 ` Rik van Riel
2012-11-13 10:25 ` Ingo Molnar
2012-11-13 12:02 ` Mel Gorman
2012-11-06 9:14 ` [PATCH 15/19] mm: numa: Add fault driven placement and migration Mel Gorman
2012-11-06 19:41 ` Rik van Riel
2012-11-07 10:49 ` Mel Gorman
2012-11-07 11:46 ` Rik van Riel
2012-11-13 10:45 ` Ingo Molnar
2012-11-13 12:09 ` Mel Gorman
2012-11-13 13:39 ` Ingo Molnar
2012-11-06 9:14 ` [PATCH 16/19] mm: numa: Add pte updates, hinting and migration stats Mel Gorman
2012-11-06 19:55 ` Rik van Riel
2012-11-07 10:57 ` Mel Gorman
2012-11-07 11:47 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 17/19] mm: numa: Migrate on reference policy Mel Gorman
2012-11-07 11:56 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 18/19] mm: sched: numa: Implement constant, per task Working Set Sampling (WSS) rate Mel Gorman
2012-11-06 19:55 ` Rik van Riel
2012-11-06 9:14 ` [PATCH 19/19] mm: sched: numa: Implement slow start for working set sampling Mel Gorman
2012-11-06 19:56 ` Rik van Riel
2012-11-07 9:27 ` [RFC PATCH 00/19] Foundation for automatic NUMA balancing Zhouping Liu
2012-11-07 15:25 ` Mel Gorman
2012-11-08 6:37 ` Zhouping Liu
[not found] ` <CAOHXNFG=T63dmc3smkJ2juE7HpxTv6qbavBXycRsXiLBzAwMGw@mail.gmail.com>
2012-11-08 7:03 ` Zhouping Liu
2012-11-09 14:42 ` Andrea Arcangeli
2012-11-09 16:12 ` 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=20121107123218.GY8218@suse.de \
--to=mgorman@suse.de \
--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=mingo@kernel.org \
--cc=riel@redhat.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).