All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mel Gorman <mgorman@techsingularity.net>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	Linux List Kernel Mailing <linux-kernel@vger.kernel.org>,
	Linux-MM <linux-mm@kvack.org>,
	Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 18/22] mm, compaction: Reduce premature advancement of the migration target scanner
Date: Fri, 18 Jan 2019 17:51:32 +0000	[thread overview]
Message-ID: <20190118175136.31341-19-mgorman@techsingularity.net> (raw)
In-Reply-To: <20190118175136.31341-1-mgorman@techsingularity.net>

The fast isolation of free pages allows the cached PFN of the free
scanner to advance faster than necessary depending on the contents
of the free list. The key is that fast_isolate_freepages() can update
zone->compact_cached_free_pfn via isolate_freepages_block().  When the
fast search fails, the linear scan can start from a point that has skipped
valid migration targets, particularly pageblocks with just low-order
free pages. This can cause the migration source/target scanners to meet
prematurely causing a reset.

This patch starts by avoiding an update of the pageblock skip information
and cached PFN from isolate_freepages_block() and puts the responsibility
of updating that information in the callers. The fast scanner will update
the cached PFN if and only if it finds a block that is higher than the
existing cached PFN and sets the skip if the pageblock is full or nearly
full. The linear scanner will update skipped information and the cached
PFN only when a block is completely scanned. The total impact is that
the free scanner advances more slowly as it is primarily driven by the
linear scanner instead of the fast search.

                                     5.0.0-rc1              5.0.0-rc1
                               noresched-v3r17         slowfree-v3r17
Amean     fault-both-3      2965.68 (   0.00%)     3036.75 (  -2.40%)
Amean     fault-both-5      3995.90 (   0.00%)     4522.24 * -13.17%*
Amean     fault-both-7      5842.12 (   0.00%)     6365.35 (  -8.96%)
Amean     fault-both-12     9550.87 (   0.00%)    10340.93 (  -8.27%)
Amean     fault-both-18    13304.72 (   0.00%)    14732.46 ( -10.73%)
Amean     fault-both-24    14618.59 (   0.00%)    16288.96 ( -11.43%)
Amean     fault-both-30    16650.96 (   0.00%)    16346.21 (   1.83%)
Amean     fault-both-32    17145.15 (   0.00%)    19317.49 ( -12.67%)

The impact to latency is higher than the last version but it appears to
be due to a slight increase in the free scan rates which is a potential
side-effect of the patch. However, this is necessary for later patches that
are more careful about how pageblocks are treated as earlier iterations
of those patches hit corner cases where the restarts were punishing and
very visible.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/compaction.c | 27 ++++++++++-----------------
 1 file changed, 10 insertions(+), 17 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index 293d9a9e6f00..04ec7d4da719 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -330,10 +330,9 @@ static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
  * future. The information is later cleared by __reset_isolation_suitable().
  */
 static void update_pageblock_skip(struct compact_control *cc,
-			struct page *page, unsigned long nr_isolated)
+			struct page *page, unsigned long pfn)
 {
 	struct zone *zone = cc->zone;
-	unsigned long pfn;
 
 	if (cc->no_set_skip_hint)
 		return;
@@ -341,13 +340,8 @@ static void update_pageblock_skip(struct compact_control *cc,
 	if (!page)
 		return;
 
-	if (nr_isolated)
-		return;
-
 	set_pageblock_skip(page);
 
-	pfn = page_to_pfn(page);
-
 	/* Update where async and sync compaction should restart */
 	if (pfn < zone->compact_cached_free_pfn)
 		zone->compact_cached_free_pfn = pfn;
@@ -365,7 +359,7 @@ static inline bool pageblock_skip_persistent(struct page *page)
 }
 
 static inline void update_pageblock_skip(struct compact_control *cc,
-			struct page *page, unsigned long nr_isolated)
+			struct page *page, unsigned long pfn)
 {
 }
 
@@ -449,7 +443,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 				bool strict)
 {
 	int nr_scanned = 0, total_isolated = 0;
-	struct page *cursor, *valid_page = NULL;
+	struct page *cursor;
 	unsigned long flags = 0;
 	bool locked = false;
 	unsigned long blockpfn = *start_pfn;
@@ -476,9 +470,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 		if (!pfn_valid_within(blockpfn))
 			goto isolate_fail;
 
-		if (!valid_page)
-			valid_page = page;
-
 		/*
 		 * For compound pages such as THP and hugetlbfs, we can save
 		 * potentially a lot of iterations if we skip them at once.
@@ -566,10 +557,6 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	if (strict && blockpfn < end_pfn)
 		total_isolated = 0;
 
-	/* Update the pageblock-skip if the whole pageblock was scanned */
-	if (blockpfn == end_pfn)
-		update_pageblock_skip(cc, valid_page, total_isolated);
-
 	cc->total_free_scanned += nr_scanned;
 	if (total_isolated)
 		count_compact_events(COMPACTISOLATED, total_isolated);
@@ -1293,8 +1280,10 @@ fast_isolate_freepages(struct compact_control *cc)
 		}
 	}
 
-	if (highest && highest > cc->zone->compact_cached_free_pfn)
+	if (highest && highest >= cc->zone->compact_cached_free_pfn) {
+		highest -= pageblock_nr_pages;
 		cc->zone->compact_cached_free_pfn = highest;
+	}
 
 	cc->total_free_scanned += nr_scanned;
 	if (!page)
@@ -1374,6 +1363,10 @@ static void isolate_freepages(struct compact_control *cc)
 		isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn,
 					freelist, false);
 
+		/* Update the skip hint if the full pageblock was scanned */
+		if (isolate_start_pfn == block_end_pfn)
+			update_pageblock_skip(cc, page, block_start_pfn);
+
 		/* Are enough freepages isolated? */
 		if (cc->nr_freepages >= cc->nr_migratepages) {
 			if (isolate_start_pfn >= block_end_pfn) {
-- 
2.16.4


  parent reply	other threads:[~2019-01-18 17:54 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-18 17:51 [PATCH 00/22] Increase success rates and reduce latency of compaction v3 Mel Gorman
2019-01-18 17:51 ` [PATCH 01/22] mm, compaction: Shrink compact_control Mel Gorman
2019-01-18 17:51 ` [PATCH 02/22] mm, compaction: Rearrange compact_control Mel Gorman
2019-01-18 17:51 ` [PATCH 03/22] mm, compaction: Remove last_migrated_pfn from compact_control Mel Gorman
2019-01-18 17:51 ` [PATCH 04/22] mm, compaction: Remove unnecessary zone parameter in some instances Mel Gorman
2019-01-18 17:51 ` [PATCH 05/22] mm, compaction: Rename map_pages to split_map_pages Mel Gorman
2019-01-18 17:51 ` [PATCH 06/22] mm, migrate: Immediately fail migration of a page with no migration handler Mel Gorman
2019-01-18 17:51 ` [PATCH 07/22] mm, compaction: Always finish scanning of a full pageblock Mel Gorman
2019-01-18 17:51 ` [PATCH 08/22] mm, compaction: Ignore the fragmentation avoidance boost for isolation and compaction Mel Gorman
2019-01-18 17:51 ` [PATCH 09/22] mm, compaction: Use free lists to quickly locate a migration source Mel Gorman
2019-01-31 13:55   ` Vlastimil Babka
2019-01-31 14:12     ` Vlastimil Babka
2019-02-01 15:06     ` Mel Gorman
2019-02-04  8:55       ` [PATCH] mm, compaction: Use free lists to quickly locate a migration source -fix Mel Gorman
2019-02-08 17:10   ` [PATCH 09/22] mm, compaction: Use free lists to quickly locate a migration source Vlastimil Babka
2019-01-18 17:51 ` [PATCH 10/22] mm, compaction: Keep migration source private to a single compaction instance Mel Gorman
2019-01-18 17:51 ` [PATCH 11/22] mm, compaction: Use free lists to quickly locate a migration target Mel Gorman
2019-01-31 14:52   ` Vlastimil Babka
2019-02-01 14:51     ` Mel Gorman
2019-02-01 14:58       ` Vlastimil Babka
2019-02-04 12:01         ` [PATCH] mm, compaction: Use free lists to quickly locate a migration source -fix Mel Gorman
2021-01-12  5:19     ` [PATCH] mm, compaction: make sure we isolate a valid freepage when high_pfn is used Rokudo Yan
2021-01-12  9:10       ` Mel Gorman
2021-01-12  9:47         ` [PATCH] mm, compaction: move high_pfn to the for loop scope Rokudo Yan
2021-01-12 10:45           ` Mel Gorman
2021-01-12 10:48           ` Vlastimil Babka
2021-01-12 22:27           ` Andrew Morton
2021-01-18  7:41             ` Rokudo Yan
2021-01-18  9:42               ` Mel Gorman
2019-01-18 17:51 ` [PATCH 12/22] mm, compaction: Avoid rescanning the same pageblock multiple times Mel Gorman
2019-01-18 17:51 ` [PATCH 13/22] mm, compaction: Finish pageblock scanning on contention Mel Gorman
2019-01-18 17:51 ` [PATCH 14/22] mm, compaction: Check early for huge pages encountered by the migration scanner Mel Gorman
2019-01-18 17:51 ` [PATCH 15/22] mm, compaction: Keep cached migration PFNs synced for unusable pageblocks Mel Gorman
2019-01-18 17:51 ` [PATCH 16/22] mm, compaction: Rework compact_should_abort as compact_check_resched Mel Gorman
2019-01-18 17:51 ` [PATCH 17/22] mm, compaction: Do not consider a need to reschedule as contention Mel Gorman
2019-01-18 17:51 ` Mel Gorman [this message]
2019-01-18 17:51 ` [PATCH 19/22] mm, compaction: Round-robin the order while searching the free lists for a target Mel Gorman
2019-01-18 17:51 ` [PATCH 20/22] mm, compaction: Sample pageblocks for free pages Mel Gorman
2019-01-31 15:39   ` Vlastimil Babka
2019-01-18 17:51 ` [PATCH 21/22] mm, compaction: Be selective about what pageblocks to clear skip hints Mel Gorman
2019-01-31 15:45   ` Vlastimil Babka
2019-01-18 17:51 ` [PATCH 22/22] mm, compaction: Capture a page under direct compaction Mel Gorman
2019-01-31 16:11   ` Vlastimil Babka
2019-02-01 14:38     ` [PATCH] mm, compaction: Capture a page under direct compaction -fix Mel Gorman
2019-01-24  8:53 ` [PATCH 00/22] Increase success rates and reduce latency of compaction v3 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=20190118175136.31341-19-mgorman@techsingularity.net \
    --to=mgorman@techsingularity.net \
    --cc=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=rientjes@google.com \
    --cc=vbabka@suse.cz \
    --subject='Re: [PATCH 18/22] mm, compaction: Reduce premature advancement of the migration target scanner' \
    /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

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.