linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vlastimil Babka <vbabka@suse.cz>
To: Mel Gorman <mgorman@techsingularity.net>, Linux-MM <linux-mm@kvack.org>
Cc: David Rientjes <rientjes@google.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	ying.huang@intel.com, kirill@shutemov.name,
	Andrew Morton <akpm@linux-foundation.org>,
	Linux List Kernel Mailing <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 14/25] mm, compaction: Avoid rescanning the same pageblock multiple times
Date: Thu, 17 Jan 2019 16:16:54 +0100	[thread overview]
Message-ID: <67b95fef-6f9a-a91f-c1b2-1c3fbc9330ca@suse.cz> (raw)
In-Reply-To: <20190104125011.16071-15-mgorman@techsingularity.net>

On 1/4/19 1:50 PM, Mel Gorman wrote:
> Pageblocks are marked for skip when no pages are isolated after a scan.
> However, it's possible to hit corner cases where the migration scanner
> gets stuck near the boundary between the source and target scanner. Due
> to pages being migrated in blocks of COMPACT_CLUSTER_MAX, pages that
> are migrated can be reallocated before the pageblock is complete. The
> pageblock is not necessarily skipped so it can be rescanned multiple
> times. Similarly, a pageblock with some dirty/writeback pages may fail
> to isolate and be rescanned until writeback completes which is wasteful.

     ^ migrate? If we failed to isolate, then it wouldn't bump nr_isolated.
Wonder if we could do better checks and not isolate pages that cannot be at the
moment migrated anyway.

> 
> This patch tracks if a pageblock is being rescanned. If so, then the entire
> pageblock will be migrated as one operation. This narrows the race window
> during which pages can be reallocated during migration. Secondly, if there
> are pages that cannot be isolated then the pageblock will still be fully
> scanned and marked for skipping. On the second rescan, the pageblock skip
> is set and the migration scanner makes progress.
> 
>                                         4.20.0                 4.20.0
>                               finishscan-v2r15         norescan-v2r15
> Amean     fault-both-3      3729.80 (   0.00%)     2872.13 *  23.00%*
> Amean     fault-both-5      5148.49 (   0.00%)     4330.56 *  15.89%*
> Amean     fault-both-7      7393.24 (   0.00%)     6496.63 (  12.13%)
> Amean     fault-both-12    11709.32 (   0.00%)    10280.59 (  12.20%)
> Amean     fault-both-18    16626.82 (   0.00%)    11079.19 *  33.37%*
> Amean     fault-both-24    19944.34 (   0.00%)    17207.80 *  13.72%*
> Amean     fault-both-30    23435.53 (   0.00%)    17736.13 *  24.32%*
> Amean     fault-both-32    23948.70 (   0.00%)    18509.41 *  22.71%*
> 
>                                    4.20.0                 4.20.0
>                          finishscan-v2r15         norescan-v2r15
> Percentage huge-1         0.00 (   0.00%)        0.00 (   0.00%)
> Percentage huge-3        88.39 (   0.00%)       96.87 (   9.60%)
> Percentage huge-5        92.07 (   0.00%)       94.63 (   2.77%)
> Percentage huge-7        91.96 (   0.00%)       93.83 (   2.03%)
> Percentage huge-12       93.38 (   0.00%)       92.65 (  -0.78%)
> Percentage huge-18       91.89 (   0.00%)       93.66 (   1.94%)
> Percentage huge-24       91.37 (   0.00%)       93.15 (   1.95%)
> Percentage huge-30       92.77 (   0.00%)       93.16 (   0.42%)
> Percentage huge-32       87.97 (   0.00%)       92.58 (   5.24%)
> 
> The fault latency reduction is large and while the THP allocation
> success rate is only slightly higher, it's already high at this
> point of the series.
> 
> Compaction migrate scanned    60718343.00    31772603.00
> Compaction free scanned      933061894.00    63267928.00

Hm I thought the order of magnitude difference between migrate and free scanned
was already gone at this point as reported in the previous 2 patches. Or is this
from different system/configuration? Anyway, encouraging result. I would expect
that after "Keep migration source private to a single compaction instance" sets
the skip bits much more early and aggressively, the rescans would not happen
anymore thanks to those, even if cached pfns were not updated.

> Migration scan rates are reduced by 48% and free scan rates are
> also reduced as the same migration source block is not being selected
> multiple times. The corner case where migration scan rates go through the
> roof due to a dirty/writeback pageblock located at the boundary of the
> migration/free scanner did not happen in this case. When it does happen,
> the scan rates multiple by factors measured in the hundreds and would be
> misleading to present.
> 
> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

Acked-by: Vlastimil Babka <vbabka@suse.cz>


  reply	other threads:[~2019-01-17 15:16 UTC|newest]

Thread overview: 75+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-04 12:49 [PATCH 00/25] Increase success rates and reduce latency of compaction v2 Mel Gorman
2019-01-04 12:49 ` [PATCH 01/25] mm, compaction: Shrink compact_control Mel Gorman
2019-01-04 12:49 ` [PATCH 02/25] mm, compaction: Rearrange compact_control Mel Gorman
2019-01-04 12:49 ` [PATCH 03/25] mm, compaction: Remove last_migrated_pfn from compact_control Mel Gorman
2019-01-04 12:49 ` [PATCH 04/25] mm, compaction: Remove unnecessary zone parameter in some instances Mel Gorman
2019-01-15 11:43   ` Vlastimil Babka
2019-01-04 12:49 ` [PATCH 05/25] mm, compaction: Rename map_pages to split_map_pages Mel Gorman
2019-01-15 11:59   ` Vlastimil Babka
2019-01-04 12:49 ` [PATCH 06/25] mm, compaction: Skip pageblocks with reserved pages Mel Gorman
2019-01-15 12:10   ` Vlastimil Babka
2019-01-15 12:50     ` Mel Gorman
2019-01-16  9:42       ` Mel Gorman
2019-01-04 12:49 ` [PATCH 07/25] mm, migrate: Immediately fail migration of a page with no migration handler Mel Gorman
2019-01-04 12:49 ` [PATCH 08/25] mm, compaction: Always finish scanning of a full pageblock Mel Gorman
2019-01-04 12:49 ` [PATCH 09/25] mm, compaction: Use the page allocator bulk-free helper for lists of pages Mel Gorman
2019-01-15 12:39   ` Vlastimil Babka
2019-01-16  9:46     ` Mel Gorman
2019-01-04 12:49 ` [PATCH 10/25] mm, compaction: Ignore the fragmentation avoidance boost for isolation and compaction Mel Gorman
2019-01-15 13:18   ` Vlastimil Babka
2019-01-04 12:49 ` [PATCH 11/25] mm, compaction: Use free lists to quickly locate a migration source Mel Gorman
2019-01-16 13:15   ` Vlastimil Babka
2019-01-16 14:33     ` Mel Gorman
2019-01-16 15:00       ` Vlastimil Babka
2019-01-16 15:43         ` Mel Gorman
2019-01-04 12:49 ` [PATCH 12/25] mm, compaction: Keep migration source private to a single compaction instance Mel Gorman
2019-01-16 15:45   ` Vlastimil Babka
2019-01-16 16:15     ` Mel Gorman
2019-01-17  9:29       ` Vlastimil Babka
2019-01-17  9:40   ` Vlastimil Babka
2019-01-04 12:49 ` [PATCH 13/25] mm, compaction: Use free lists to quickly locate a migration target Mel Gorman
2019-01-17 14:36   ` Vlastimil Babka
2019-01-17 15:51     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 14/25] mm, compaction: Avoid rescanning the same pageblock multiple times Mel Gorman
2019-01-17 15:16   ` Vlastimil Babka [this message]
2019-01-17 16:00     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 15/25] mm, compaction: Finish pageblock scanning on contention Mel Gorman
2019-01-17 16:38   ` Vlastimil Babka
2019-01-17 17:11     ` Mel Gorman
2019-01-18  8:57       ` Vlastimil Babka
2019-01-04 12:50 ` [PATCH 16/25] mm, compaction: Check early for huge pages encountered by the migration scanner Mel Gorman
2019-01-17 17:01   ` Vlastimil Babka
2019-01-17 17:35     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 17/25] mm, compaction: Keep cached migration PFNs synced for unusable pageblocks Mel Gorman
2019-01-17 17:17   ` Vlastimil Babka
2019-01-17 17:37     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 18/25] mm, compaction: Rework compact_should_abort as compact_check_resched Mel Gorman
2019-01-17 17:27   ` Vlastimil Babka
2019-01-04 12:50 ` [PATCH 19/25] mm, compaction: Do not consider a need to reschedule as contention Mel Gorman
2019-01-17 17:33   ` Vlastimil Babka
2019-01-17 18:05     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 20/25] mm, compaction: Reduce unnecessary skipping of migration target scanner Mel Gorman
2019-01-17 17:58   ` Vlastimil Babka
2019-01-17 19:39     ` Mel Gorman
2019-01-18  9:09       ` Vlastimil Babka
2019-01-04 12:50 ` [PATCH 21/25] mm, compaction: Round-robin the order while searching the free lists for a target Mel Gorman
2019-01-18  9:17   ` Vlastimil Babka
2019-01-04 12:50 ` [PATCH 22/25] mm, compaction: Sample pageblocks for free pages Mel Gorman
2019-01-18 10:38   ` Vlastimil Babka
2019-01-18 13:44     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 23/25] mm, compaction: Be selective about what pageblocks to clear skip hints Mel Gorman
2019-01-18 12:55   ` Vlastimil Babka
2019-01-18 14:10     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 24/25] mm, compaction: Capture a page under direct compaction Mel Gorman
2019-01-18 13:40   ` Vlastimil Babka
2019-01-18 14:39     ` Mel Gorman
2019-01-04 12:50 ` [PATCH 25/25] mm, compaction: Do not direct compact remote memory Mel Gorman
2019-01-18 13:51   ` Vlastimil Babka
2019-01-18 14:46     ` Mel Gorman
2019-01-07 23:43 ` [PATCH 00/25] Increase success rates and reduce latency of compaction v2 Andrew Morton
2019-01-08  9:12   ` Mel Gorman
2019-01-09 11:13 ` [PATCH] mm, compaction: Use free lists to quickly locate a migration target -fix Mel Gorman
2019-01-09 19:27   ` Andrew Morton
2019-01-09 21:26     ` Mel Gorman
2019-01-09 11:15 ` [PATCH] mm, compaction: Finish pageblock scanning on contention -fix Mel Gorman
2019-01-09 11:16 ` [PATCH] mm, compaction: Round-robin the order while searching the free lists for a target -fix 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=67b95fef-6f9a-a91f-c1b2-1c3fbc9330ca@suse.cz \
    --to=vbabka@suse.cz \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=rientjes@google.com \
    --cc=ying.huang@intel.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).