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 12/25] mm, compaction: Keep migration source private to a single compaction instance
Date: Wed, 16 Jan 2019 16:45:59 +0100	[thread overview]
Message-ID: <0d02b611-85a7-b161-1310-883c4b1594f8@suse.cz> (raw)
In-Reply-To: <20190104125011.16071-13-mgorman@techsingularity.net>

On 1/4/19 1:49 PM, Mel Gorman wrote:
> Due to either a fast search of the free list or a linear scan, it is
> possible for multiple compaction instances to pick the same pageblock
> for migration.  This is lucky for one scanner and increased scanning for
> all the others. It also allows a race between requests on which first
> allocates the resulting free block.
> 
> This patch tests and updates the pageblock skip for the migration scanner
> carefully. When isolating a block, it will check and skip if the block is
> already in use. Once the zone lock is acquired, it will be rechecked so
> that only one scanner can set the pageblock skip for exclusive use. Any
> scanner contending will continue with a linear scan. The skip bit is
> still set if no pages can be isolated in a range.

Also the skip bit will remain set even if pages *could* be isolated,
AFAICS there's no clearing after a block was finished with
nr_isolated>0. Is it intended? Note even previously it wasn't ideal,
because when pageblock was visited multiple times due to
COMPACT_CLUSTER_MAX, it would be marked with skip bit if the last visit
failed to isolate, even if the previous visits didn't.

> While this may result
> in redundant scanning, it avoids unnecessarily acquiring the zone lock
> when there are no suitable migration sources.



> 1-socket thpscale
>                                         4.20.0                 4.20.0
>                                  findmig-v2r15          isolmig-v2r15
> Amean     fault-both-1         0.00 (   0.00%)        0.00 *   0.00%*
> Amean     fault-both-3      3505.69 (   0.00%)     3066.68 *  12.52%*
> Amean     fault-both-5      5794.13 (   0.00%)     4298.49 *  25.81%*
> Amean     fault-both-7      7663.09 (   0.00%)     5986.99 *  21.87%*
> Amean     fault-both-12    10983.36 (   0.00%)     9324.85 (  15.10%)
> Amean     fault-both-18    13602.71 (   0.00%)    13350.05 (   1.86%)
> Amean     fault-both-24    16145.77 (   0.00%)    13491.77 *  16.44%*
> Amean     fault-both-30    19753.82 (   0.00%)    15630.86 *  20.87%*
> Amean     fault-both-32    20616.16 (   0.00%)    17428.50 *  15.46%*
> 
> This is the first patch that shows a significant reduction in latency as
> multiple compaction scanners do not operate on the same blocks. There is
> a small increase in the success rate
> 
>                                4.20.0-rc6             4.20.0-rc6
>                              findmig-v1r4           isolmig-v1r4
> Percentage huge-3        90.58 (   0.00%)       95.84 (   5.81%)
> Percentage huge-5        91.34 (   0.00%)       94.19 (   3.12%)
> Percentage huge-7        92.21 (   0.00%)       93.78 (   1.71%)
> Percentage huge-12       92.48 (   0.00%)       94.33 (   2.00%)
> Percentage huge-18       91.65 (   0.00%)       94.15 (   2.72%)
> Percentage huge-24       90.23 (   0.00%)       94.23 (   4.43%)
> Percentage huge-30       90.17 (   0.00%)       95.17 (   5.54%)
> Percentage huge-32       89.72 (   0.00%)       93.59 (   4.32%)
> 
> Compaction migrate scanned    54168306    25516488
> Compaction free scanned      800530954    87603321
> 
> Migration scan rates are reduced by 52%.

Wonder how much of that is due to not clearing as pointed out above.
Also interesting how free scanned was reduced so disproportionally.

> Signed-off-by: Mel Gorman <mgorman@techsingularity.net>

  reply	other threads:[~2019-01-16 15:46 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 [this message]
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
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=0d02b611-85a7-b161-1310-883c4b1594f8@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).