| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 21 Sep 2012 11:46:23 +0100
From: Mel Gorman <mgorman@...e.de>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Richard Davies <richard@...chsys.com>,
Shaohua Li <shli@...nel.org>, Rik van Riel <riel@...hat.com>,
Avi Kivity <avi@...hat.com>,
QEMU-devel <qemu-devel@...gnu.org>, KVM <kvm@...r.kernel.org>,
Linux-MM <linux-mm@...ck.org>,
LKML <linux-kernel@...r.kernel.org>, Mel Gorman <mgorman@...e.de>
Subject: [PATCH 9/9] mm: compaction: Restart compaction from near where it left off
This is almost entirely based on Rik's previous patches and discussions
with him about how this might be implemented.
Order > 0 compaction stops when enough free pages of the correct page
order have been coalesced. When doing subsequent higher order allocations,
it is possible for compaction to be invoked many times.
However, the compaction code always starts out looking for things to compact
at the start of the zone, and for free pages to compact things to at the
end of the zone.
This can cause quadratic behaviour, with isolate_freepages starting at
the end of the zone each time, even though previous invocations of the
compaction code already filled up all free memory on that end of the zone.
This can cause isolate_freepages to take enormous amounts of CPU with
certain workloads on larger memory systems.
This patch caches where the migration and free scanner should start from on
subsequent compaction invocations using the pageblock-skip information. When
compaction starts it begins from the cached restart points and will
update the cached restart points until a page is isolated or a pageblock
is skipped that would have been scanned by synchronous compaction.
Signed-off-by: Mel Gorman <mgorman@...e.de>
Acked-by: Rik van Riel <riel@...hat.com>
---
include/linux/mmzone.h | 4 ++++
mm/compaction.c | 54 ++++++++++++++++++++++++++++++++++++++++--------
mm/internal.h | 4 ++++
3 files changed, 53 insertions(+), 9 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a456361..e7792a3 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -370,6 +370,10 @@ struct zone {
int all_unreclaimable; /* All pages pinned */
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
unsigned long compact_blockskip_expire;
+
+ /* pfns where compaction scanners should start */
+ unsigned long compact_cached_free_pfn;
+ unsigned long compact_cached_migrate_pfn;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
diff --git a/mm/compaction.c b/mm/compaction.c
index 9276bc8..4bd96f3 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -79,6 +79,9 @@ static void reset_isolation_suitable(struct zone *zone)
*/
if (time_before(jiffies, zone->compact_blockskip_expire))
return;
+
+ zone->compact_cached_migrate_pfn = start_pfn;
+ zone->compact_cached_free_pfn = end_pfn;
zone->compact_blockskip_expire = jiffies + (HZ * 5);
/* Walk the zone and mark every pageblock as suitable for isolation */
@@ -99,13 +102,29 @@ static void reset_isolation_suitable(struct zone *zone)
* 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 page *page, unsigned long nr_isolated)
+static void update_pageblock_skip(struct compact_control *cc,
+ struct page *page, unsigned long nr_isolated,
+ bool migrate_scanner)
{
+ struct zone *zone = cc->zone;
if (!page)
return;
- if (!nr_isolated)
+ if (!nr_isolated) {
+ unsigned long pfn = page_to_pfn(page);
set_pageblock_skip(page);
+
+ /* Update where compaction should restart */
+ if (migrate_scanner) {
+ if (!cc->finished_update_migrate &&
+ pfn > zone->compact_cached_migrate_pfn)
+ zone->compact_cached_migrate_pfn = pfn;
+ } else {
+ if (!cc->finished_update_free &&
+ pfn < zone->compact_cached_free_pfn)
+ zone->compact_cached_free_pfn = pfn;
+ }
+ }
}
static inline bool should_release_lock(spinlock_t *lock)
@@ -315,7 +334,7 @@ out:
/* Update the pageblock-skip if the whole pageblock was scanned */
if (blockpfn == end_pfn)
- update_pageblock_skip(valid_page, total_isolated);
+ update_pageblock_skip(cc, valid_page, total_isolated, false);
return total_isolated;
}
@@ -530,6 +549,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
*/
if (!cc->sync && last_pageblock_nr != pageblock_nr &&
!migrate_async_suitable(get_pageblock_migratetype(page))) {
+ cc->finished_update_migrate = true;
goto next_pageblock;
}
@@ -578,6 +598,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
VM_BUG_ON(PageTransCompound(page));
/* Successfully isolated */
+ cc->finished_update_migrate = true;
del_page_from_lru_list(page, lruvec, page_lru(page));
list_add(&page->lru, migratelist);
cc->nr_migratepages++;
@@ -604,7 +625,7 @@ next_pageblock:
/* Update the pageblock-skip if the whole pageblock was scanned */
if (low_pfn == end_pfn)
- update_pageblock_skip(valid_page, nr_isolated);
+ update_pageblock_skip(cc, valid_page, nr_isolated, true);
trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
@@ -685,8 +706,10 @@ static void isolate_freepages(struct zone *zone,
* looking for free pages, the search will restart here as
* page migration may have returned some pages to the allocator
*/
- if (isolated)
+ if (isolated) {
+ cc->finished_update_free = true;
high_pfn = max(high_pfn, pfn);
+ }
}
/* split_free_page does not map the pages */
@@ -883,6 +906,8 @@ unsigned long compaction_suitable(struct zone *zone, int order)
static int compact_zone(struct zone *zone, struct compact_control *cc)
{
int ret;
+ unsigned long start_pfn = zone->zone_start_pfn;
+ unsigned long end_pfn = zone->zone_start_pfn + zone->spanned_pages;
ret = compaction_suitable(zone, cc->order);
switch (ret) {
@@ -895,10 +920,21 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
;
}
- /* Setup to move all movable pages to the end of the zone */
- cc->migrate_pfn = zone->zone_start_pfn;
- cc->free_pfn = cc->migrate_pfn + zone->spanned_pages;
- cc->free_pfn &= ~(pageblock_nr_pages-1);
+ /*
+ * Setup to move all movable pages to the end of the zone. Used cached
+ * information on where the scanners should start but check that it
+ * is initialised by ensuring the values are within zone boundaries.
+ */
+ cc->migrate_pfn = zone->compact_cached_migrate_pfn;
+ cc->free_pfn = zone->compact_cached_free_pfn;
+ if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
+ cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
+ zone->compact_cached_free_pfn = cc->free_pfn;
+ }
+ if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
+ cc->migrate_pfn = start_pfn;
+ zone->compact_cached_migrate_pfn = cc->migrate_pfn;
+ }
/* Clear pageblock skip if there are numerous alloc failures */
if (zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT)
diff --git a/mm/internal.h b/mm/internal.h
index fbf5ddc..7052289 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -122,6 +122,10 @@ struct compact_control {
unsigned long migrate_pfn; /* isolate_migratepages search base */
bool sync; /* Synchronous migration */
bool ignore_skip_hint; /* Scan blocks even if marked skip */
+ bool finished_update_free; /* True when the zone cached pfns are
+ * no longer being updated
+ */
+ bool finished_update_migrate;
int order; /* order a direct compactor needs */
int migratetype; /* MOVABLE, RECLAIMABLE etc */
--
1.7.9.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists