From: Mel Gorman <mgorman@techsingularity.net>
To: Vlastimil Babka <vbabka@suse.cz>
Cc: Linux-MM <linux-mm@kvack.org>,
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 16:00:39 +0000 [thread overview]
Message-ID: <20190117160039.GJ27437@techsingularity.net> (raw)
In-Reply-To: <67b95fef-6f9a-a91f-c1b2-1c3fbc9330ca@suse.cz>
On Thu, Jan 17, 2019 at 04:16:54PM +0100, Vlastimil Babka wrote:
> 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.
>
Potentially but it would be considered a layering violation. There may be
per-fs reasons why a page cannot migrate and no matter how well we check,
there will be race conditions.
> > 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.
There are corner cases that mean there can be large differences for a
single run. In some cases it doesn't matter but this one might have been
unlucky. It's something that occurs less as the series progresses.
> Or is this
> from different system/configuration?
I don't *think* so. While I had multiple machines running tests, I'm
pretty sure I wrote the changelogs based on one machine and only checked
the others had nothing strange.
> 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.
>
Yes and no. The corner case where the scanner gets stuck rescanning one
pageblock can happen when the fast search fails. In that case, the
linear scanner needs to get to the end of a pageblock and if it fails,
it'll simply rescan like a lunatic. This happened specifically for pages
under writeback for me.
> Acked-by: Vlastimil Babka <vbabka@suse.cz>
>
Thanks
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2019-01-17 16:00 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
2019-01-17 16:00 ` Mel Gorman [this message]
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=20190117160039.GJ27437@techsingularity.net \
--to=mgorman@techsingularity.net \
--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=rientjes@google.com \
--cc=vbabka@suse.cz \
--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).