From: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Subject: mm, compaction: keep migration source private to a single compaction instance
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. While this may result
in redundant scanning, it avoids unnecessarily acquiring the zone lock
when there are no suitable migration sources.
1-socket thpscale
Amean fault-both-1 0.00 ( 0.00%) 0.00 * 0.00%*
Amean fault-both-3 3390.40 ( 0.00%) 3024.41 ( 10.80%)
Amean fault-both-5 5082.28 ( 0.00%) 4749.30 ( 6.55%)
Amean fault-both-7 7012.51 ( 0.00%) 6454.95 ( 7.95%)
Amean fault-both-12 11346.63 ( 0.00%) 10324.83 ( 9.01%)
Amean fault-both-18 15324.19 ( 0.00%) 12896.82 * 15.84%*
Amean fault-both-24 16088.50 ( 0.00%) 13470.60 * 16.27%*
Amean fault-both-30 18723.42 ( 0.00%) 17143.99 ( 8.44%)
Amean fault-both-32 18612.01 ( 0.00%) 17743.91 ( 4.66%)
5.0.0-rc1 5.0.0-rc1
findmig-v3r15 isolmig-v3r15
Percentage huge-3 89.83 ( 0.00%) 92.96 ( 3.48%)
Percentage huge-5 91.96 ( 0.00%) 93.26 ( 1.41%)
Percentage huge-7 92.85 ( 0.00%) 93.63 ( 0.84%)
Percentage huge-12 92.74 ( 0.00%) 92.80 ( 0.07%)
Percentage huge-18 91.71 ( 0.00%) 91.62 ( -0.10%)
Percentage huge-24 92.13 ( 0.00%) 91.50 ( -0.69%)
Percentage huge-30 93.79 ( 0.00%) 92.73 ( -1.13%)
Percentage huge-32 91.27 ( 0.00%) 91.94 ( 0.74%)
This shows a reasonable reduction in latency as multiple compaction
scanners do not operate on the same blocks with a similar allocation
success rate.
Compaction migrate scanned 41093126 25646769
Migration scan rates are reduced by 38%.
Link: http://lkml.kernel.org/r/20190118175136.31341-11-mgorman@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Dan Carpenter <dan.carpenter@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: YueHaibing <yuehaibing@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/compaction.c | 124 ++++++++++++++++++++++++++++++++++++----------
1 file changed, 99 insertions(+), 25 deletions(-)
--- a/mm/compaction.c~mm-compaction-keep-migration-source-private-to-a-single-compaction-instance
+++ a/mm/compaction.c
@@ -286,12 +286,51 @@ void reset_isolation_suitable(pg_data_t
}
/*
+ * Sets the pageblock skip bit if it was clear. Note that this is a hint as
+ * locks are not required for read/writers. Returns true if it was already set.
+ */
+static bool test_and_set_skip(struct compact_control *cc, struct page *page,
+ unsigned long pfn)
+{
+ bool skip;
+
+ /* Do no update if skip hint is being ignored */
+ if (cc->ignore_skip_hint)
+ return false;
+
+ if (!IS_ALIGNED(pfn, pageblock_nr_pages))
+ return false;
+
+ skip = get_pageblock_skip(page);
+ if (!skip && !cc->no_set_skip_hint)
+ set_pageblock_skip(page);
+
+ return skip;
+}
+
+static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
+{
+ struct zone *zone = cc->zone;
+
+ pfn = pageblock_end_pfn(pfn);
+
+ /* Set for isolation rather than compaction */
+ if (cc->no_set_skip_hint)
+ return;
+
+ if (pfn > zone->compact_cached_migrate_pfn[0])
+ zone->compact_cached_migrate_pfn[0] = pfn;
+ if (cc->mode != MIGRATE_ASYNC &&
+ pfn > zone->compact_cached_migrate_pfn[1])
+ zone->compact_cached_migrate_pfn[1] = pfn;
+}
+
+/*
* If no pages were isolated then mark this pageblock to be skipped in the
* 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,
- bool migrate_scanner)
+ struct page *page, unsigned long nr_isolated)
{
struct zone *zone = cc->zone;
unsigned long pfn;
@@ -310,16 +349,8 @@ static void update_pageblock_skip(struct
pfn = page_to_pfn(page);
/* Update where async and sync compaction should restart */
- if (migrate_scanner) {
- if (pfn > zone->compact_cached_migrate_pfn[0])
- zone->compact_cached_migrate_pfn[0] = pfn;
- if (cc->mode != MIGRATE_ASYNC &&
- pfn > zone->compact_cached_migrate_pfn[1])
- zone->compact_cached_migrate_pfn[1] = pfn;
- } else {
- if (pfn < zone->compact_cached_free_pfn)
- zone->compact_cached_free_pfn = pfn;
- }
+ if (pfn < zone->compact_cached_free_pfn)
+ zone->compact_cached_free_pfn = pfn;
}
#else
static inline bool isolation_suitable(struct compact_control *cc,
@@ -334,10 +365,19 @@ static inline bool pageblock_skip_persis
}
static inline void update_pageblock_skip(struct compact_control *cc,
- struct page *page, unsigned long nr_isolated,
- bool migrate_scanner)
+ struct page *page, unsigned long nr_isolated)
{
}
+
+static void update_cached_migrate(struct compact_control *cc, unsigned long pfn)
+{
+}
+
+static bool test_and_set_skip(struct compact_control *cc, struct page *page,
+ unsigned long pfn)
+{
+ return false;
+}
#endif /* CONFIG_COMPACTION */
/*
@@ -567,7 +607,7 @@ isolate_fail:
/* Update the pageblock-skip if the whole pageblock was scanned */
if (blockpfn == end_pfn)
- update_pageblock_skip(cc, valid_page, total_isolated, false);
+ update_pageblock_skip(cc, valid_page, total_isolated);
cc->total_free_scanned += nr_scanned;
if (total_isolated)
@@ -702,6 +742,7 @@ isolate_migratepages_block(struct compac
unsigned long start_pfn = low_pfn;
bool skip_on_failure = false;
unsigned long next_skip_pfn = 0;
+ bool skip_updated = false;
/*
* Ensure that there are not too many pages isolated from the LRU
@@ -768,8 +809,19 @@ isolate_migratepages_block(struct compac
page = pfn_to_page(low_pfn);
- if (!valid_page)
+ /*
+ * Check if the pageblock has already been marked skipped.
+ * Only the aligned PFN is checked as the caller isolates
+ * COMPACT_CLUSTER_MAX at a time so the second call must
+ * not falsely conclude that the block should be skipped.
+ */
+ if (!valid_page && IS_ALIGNED(low_pfn, pageblock_nr_pages)) {
+ if (!cc->ignore_skip_hint && get_pageblock_skip(page)) {
+ low_pfn = end_pfn;
+ goto isolate_abort;
+ }
valid_page = page;
+ }
/*
* Skip if free. We read page order here without zone lock
@@ -850,8 +902,19 @@ isolate_migratepages_block(struct compac
if (!locked) {
locked = compact_trylock_irqsave(zone_lru_lock(zone),
&flags, cc);
- if (!locked)
+
+ /* Allow future scanning if the lock is contended */
+ if (!locked) {
+ clear_pageblock_skip(page);
break;
+ }
+
+ /* Try get exclusive access under lock */
+ if (!skip_updated) {
+ skip_updated = true;
+ if (test_and_set_skip(cc, page, low_pfn))
+ goto isolate_abort;
+ }
/* Recheck PageLRU and PageCompound under lock */
if (!PageLRU(page))
@@ -929,15 +992,20 @@ isolate_fail:
if (unlikely(low_pfn > end_pfn))
low_pfn = end_pfn;
+isolate_abort:
if (locked)
spin_unlock_irqrestore(zone_lru_lock(zone), flags);
/*
- * Update the pageblock-skip information and cached scanner pfn,
- * if the whole pageblock was scanned without isolating any page.
+ * Updated the cached scanner pfn if the pageblock was scanned
+ * without isolating a page. The pageblock may not be marked
+ * skipped already if there were no LRU pages in the block.
*/
- if (low_pfn == end_pfn)
- update_pageblock_skip(cc, valid_page, nr_isolated, true);
+ if (low_pfn == end_pfn && !nr_isolated) {
+ if (valid_page && !skip_updated)
+ set_pageblock_skip(valid_page);
+ update_cached_migrate(cc, low_pfn);
+ }
trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
nr_scanned, nr_isolated);
@@ -1323,8 +1391,6 @@ static unsigned long fast_find_migratebl
nr_scanned++;
free_pfn = page_to_pfn(freepage);
if (free_pfn < high_pfn) {
- update_fast_start_pfn(cc, free_pfn);
-
/*
* Avoid if skipped recently. Ideally it would
* move to the tail but even safe iteration of
@@ -1341,6 +1407,7 @@ static unsigned long fast_find_migratebl
/* Reorder to so a future search skips recent pages */
move_freelist_tail(freelist, freepage);
+ update_fast_start_pfn(cc, free_pfn);
pfn = pageblock_start_pfn(free_pfn);
cc->fast_search_fail = 0;
set_pageblock_skip(freepage);
@@ -1429,8 +1496,15 @@ static isolate_migrate_t isolate_migrate
if (!page)
continue;
- /* If isolation recently failed, do not retry */
- if (!isolation_suitable(cc, page) && !fast_find_block)
+ /*
+ * If isolation recently failed, do not retry. Only check the
+ * pageblock once. COMPACT_CLUSTER_MAX causes a pageblock
+ * to be visited multiple times. Assume skip was checked
+ * before making it "skip" so other compaction instances do
+ * not scan the same block.
+ */
+ if (IS_ALIGNED(low_pfn, pageblock_nr_pages) &&
+ !fast_find_block && !isolation_suitable(cc, page))
continue;
/*
_
