![Bartlomiej Zolnierkiewicz](/assets/img/avatar_default.png)
When MIGRATE_UNMOVABLE pages are freed from MIGRATE_UNMOVABLE type pageblock (and some MIGRATE_MOVABLE pages are left in it) waiting until an allocation takes ownership of the block may take too long. The type of the pageblock remains unchanged so the pageblock cannot be used as a migration target during compaction. Fix it by: * Adding enum compact_mode (COMPACT_ASYNC_[MOVABLE,UNMOVABLE], and COMPACT_SYNC) and then converting sync field in struct compact_control to use it. * Adding nr_pageblocks_skipped field to struct compact_control and tracking how many destination pageblocks were of MIGRATE_UNMOVABLE type. If COMPACT_ASYNC_MOVABLE mode compaction ran fully in try_to_compact_pages() (COMPACT_COMPLETE) it implies that there is not a suitable page for allocation. In this case then check how if there were enough MIGRATE_UNMOVABLE pageblocks to try a second pass in COMPACT_ASYNC_UNMOVABLE mode. * Scanning the MIGRATE_UNMOVABLE pageblocks (during COMPACT_SYNC and COMPACT_ASYNC_UNMOVABLE compaction modes) and building a count based on finding PageBuddy pages, page_count(page) == 0 or PageLRU pages. If all pages within the MIGRATE_UNMOVABLE pageblock are in one of those three sets change the whole pageblock type to MIGRATE_MOVABLE. My particular test case (on a ARM EXYNOS4 device with 512 MiB, which means 131072 standard 4KiB pages in 'Normal' zone) is to: - allocate 120000 pages for kernel's usage - free every second page (60000 pages) of memory just allocated - allocate and use 60000 pages from user space - free remaining 60000 pages of kernel memory (now we have fragmented memory occupied mostly by user space pages) - try to allocate 100 order-9 (2048 KiB) pages for kernel's usage The results: - with compaction disabled I get 11 successful allocations - with compaction enabled - 14 successful allocations - with this patch I'm able to get all 100 successful allocations NOTE: If we can make kswapd aware of order-0 request during compaction, we can enhance kswapd with changing mode to COMPACT_ASYNC_FULL (COMPACT_ASYNC_MOVABLE + COMPACT_ASYNC_UNMOVABLE). Please see the following thread: http://marc.info/?l=linux-mm&m=133552069417068&w=2 [minchan@kernel.org: minor cleanups] Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
129 lines
3.8 KiB
C
129 lines
3.8 KiB
C
#ifndef _LINUX_COMPACTION_H
|
|
#define _LINUX_COMPACTION_H
|
|
|
|
#include <linux/node.h>
|
|
|
|
/* Return values for compact_zone() and try_to_compact_pages() */
|
|
/* compaction didn't start as it was not possible or direct reclaim was more suitable */
|
|
#define COMPACT_SKIPPED 0
|
|
/* compaction should continue to another pageblock */
|
|
#define COMPACT_CONTINUE 1
|
|
/* direct compaction partially compacted a zone and there are suitable pages */
|
|
#define COMPACT_PARTIAL 2
|
|
/* The full zone was compacted */
|
|
#define COMPACT_COMPLETE 3
|
|
|
|
/*
|
|
* compaction supports three modes
|
|
*
|
|
* COMPACT_ASYNC_MOVABLE uses asynchronous migration and only scans
|
|
* MIGRATE_MOVABLE pageblocks as migration sources and targets.
|
|
* COMPACT_ASYNC_UNMOVABLE uses asynchronous migration and only scans
|
|
* MIGRATE_MOVABLE pageblocks as migration sources.
|
|
* MIGRATE_UNMOVABLE pageblocks are scanned as potential migration
|
|
* targets and convers them to MIGRATE_MOVABLE if possible
|
|
* COMPACT_SYNC uses synchronous migration and scans all pageblocks
|
|
*/
|
|
enum compact_mode {
|
|
COMPACT_ASYNC_MOVABLE,
|
|
COMPACT_ASYNC_UNMOVABLE,
|
|
COMPACT_SYNC,
|
|
};
|
|
|
|
#ifdef CONFIG_COMPACTION
|
|
extern int sysctl_compact_memory;
|
|
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *length, loff_t *ppos);
|
|
extern int sysctl_extfrag_threshold;
|
|
extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
|
|
void __user *buffer, size_t *length, loff_t *ppos);
|
|
|
|
extern int fragmentation_index(struct zone *zone, unsigned int order);
|
|
extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
|
|
int order, gfp_t gfp_mask, nodemask_t *mask,
|
|
bool sync);
|
|
extern int compact_pgdat(pg_data_t *pgdat, int order);
|
|
extern unsigned long compaction_suitable(struct zone *zone, int order);
|
|
|
|
/* Do not skip compaction more than 64 times */
|
|
#define COMPACT_MAX_DEFER_SHIFT 6
|
|
|
|
/*
|
|
* Compaction is deferred when compaction fails to result in a page
|
|
* allocation success. 1 << compact_defer_limit compactions are skipped up
|
|
* to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
|
|
*/
|
|
static inline void defer_compaction(struct zone *zone, int order)
|
|
{
|
|
zone->compact_considered = 0;
|
|
zone->compact_defer_shift++;
|
|
|
|
if (order < zone->compact_order_failed)
|
|
zone->compact_order_failed = order;
|
|
|
|
if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
|
|
zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
|
|
}
|
|
|
|
/* Returns true if compaction should be skipped this time */
|
|
static inline bool compaction_deferred(struct zone *zone, int order)
|
|
{
|
|
unsigned long defer_limit = 1UL << zone->compact_defer_shift;
|
|
|
|
if (order < zone->compact_order_failed)
|
|
return false;
|
|
|
|
/* Avoid possible overflow */
|
|
if (++zone->compact_considered > defer_limit)
|
|
zone->compact_considered = defer_limit;
|
|
|
|
return zone->compact_considered < (1UL << zone->compact_defer_shift);
|
|
}
|
|
|
|
#else
|
|
static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
|
|
int order, gfp_t gfp_mask, nodemask_t *nodemask,
|
|
bool sync)
|
|
{
|
|
return COMPACT_CONTINUE;
|
|
}
|
|
|
|
static inline int compact_pgdat(pg_data_t *pgdat, int order)
|
|
{
|
|
return COMPACT_CONTINUE;
|
|
}
|
|
|
|
static inline unsigned long compaction_suitable(struct zone *zone, int order)
|
|
{
|
|
return COMPACT_SKIPPED;
|
|
}
|
|
|
|
static inline void defer_compaction(struct zone *zone, int order)
|
|
{
|
|
}
|
|
|
|
static inline bool compaction_deferred(struct zone *zone, int order)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
#endif /* CONFIG_COMPACTION */
|
|
|
|
#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
|
|
extern int compaction_register_node(struct node *node);
|
|
extern void compaction_unregister_node(struct node *node);
|
|
|
|
#else
|
|
|
|
static inline int compaction_register_node(struct node *node)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void compaction_unregister_node(struct node *node)
|
|
{
|
|
}
|
|
#endif /* CONFIG_COMPACTION && CONFIG_SYSFS && CONFIG_NUMA */
|
|
|
|
#endif /* _LINUX_COMPACTION_H */
|