ebff398017
Compaction relies on zone watermark checks for decisions such as if it's worth to start compacting in compaction_suitable() or whether compaction should stop in compact_finished(). The watermark checks take classzone_idx and alloc_flags parameters, which are related to the memory allocation request. But from the context of compaction they are currently passed as 0, including the direct compaction which is invoked to satisfy the allocation request, and could therefore know the proper values. The lack of proper values can lead to mismatch between decisions taken during compaction and decisions related to the allocation request. Lack of proper classzone_idx value means that lowmem_reserve is not taken into account. This has manifested (during recent changes to deferred compaction) when DMA zone was used as fallback for preferred Normal zone. compaction_suitable() without proper classzone_idx would think that the watermarks are already satisfied, but watermark check in get_page_from_freelist() would fail. Because of this problem, deferring compaction has extra complexity that can be removed in the following patch. The issue (not confirmed in practice) with missing alloc_flags is opposite in nature. For allocations that include ALLOC_HIGH, ALLOC_HIGHER or ALLOC_CMA in alloc_flags (the last includes all MOVABLE allocations on CMA-enabled systems) the watermark checking in compaction with 0 passed will be stricter than in get_page_from_freelist(). In these cases compaction might be running for a longer time than is really needed. Another issue compaction_suitable() is that the check for "does the zone need compaction at all?" comes only after the check "does the zone have enough free free pages to succeed compaction". The latter considers extra pages for migration and can therefore in some situations fail and return COMPACT_SKIPPED, although the high-order allocation would succeed and we should return COMPACT_PARTIAL. This patch fixes these problems by adding alloc_flags and classzone_idx to struct compact_control and related functions involved in direct compaction and watermark checking. Where possible, all other callers of compaction_suitable() pass proper values where those are known. This is currently limited to classzone_idx, which is sometimes known in kswapd context. However, the direct reclaim callers should_continue_reclaim() and compaction_ready() do not currently know the proper values, so the coordination between reclaim and compaction may still not be as accurate as it could. This can be fixed later, if it's shown to be an issue. Additionaly the checks in compact_suitable() are reordered to address the second issue described above. The effect of this patch should be slightly better high-order allocation success rates and/or less compaction overhead, depending on the type of allocations and presence of CMA. It allows simplifying deferred compaction code in a followup patch. When testing with stress-highalloc, there was some slight improvement (which might be just due to variance) in success rates of non-THP-like allocations. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Minchan Kim <minchan@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Christoph Lameter <cl@linux.com> Acked-by: Rik van Riel <riel@redhat.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
156 lines
4.7 KiB
C
156 lines
4.7 KiB
C
#ifndef _LINUX_COMPACTION_H
|
|
#define _LINUX_COMPACTION_H
|
|
|
|
/* Return values for compact_zone() and try_to_compact_pages() */
|
|
/* compaction didn't start as it was deferred due to past failures */
|
|
#define COMPACT_DEFERRED 0
|
|
/* compaction didn't start as it was not possible or direct reclaim was more suitable */
|
|
#define COMPACT_SKIPPED 1
|
|
/* compaction should continue to another pageblock */
|
|
#define COMPACT_CONTINUE 2
|
|
/* direct compaction partially compacted a zone and there are suitable pages */
|
|
#define COMPACT_PARTIAL 3
|
|
/* The full zone was compacted */
|
|
#define COMPACT_COMPLETE 4
|
|
|
|
/* Used to signal whether compaction detected need_sched() or lock contention */
|
|
/* No contention detected */
|
|
#define COMPACT_CONTENDED_NONE 0
|
|
/* Either need_sched() was true or fatal signal pending */
|
|
#define COMPACT_CONTENDED_SCHED 1
|
|
/* Zone lock or lru_lock was contended in async compaction */
|
|
#define COMPACT_CONTENDED_LOCK 2
|
|
|
|
#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,
|
|
enum migrate_mode mode, int *contended,
|
|
int alloc_flags, int classzone_idx,
|
|
struct zone **candidate_zone);
|
|
extern void compact_pgdat(pg_data_t *pgdat, int order);
|
|
extern void reset_isolation_suitable(pg_data_t *pgdat);
|
|
extern unsigned long compaction_suitable(struct zone *zone, int order,
|
|
int alloc_flags, int classzone_idx);
|
|
|
|
/* 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 < defer_limit;
|
|
}
|
|
|
|
/*
|
|
* Update defer tracking counters after successful compaction of given order,
|
|
* which means an allocation either succeeded (alloc_success == true) or is
|
|
* expected to succeed.
|
|
*/
|
|
static inline void compaction_defer_reset(struct zone *zone, int order,
|
|
bool alloc_success)
|
|
{
|
|
if (alloc_success) {
|
|
zone->compact_considered = 0;
|
|
zone->compact_defer_shift = 0;
|
|
}
|
|
if (order >= zone->compact_order_failed)
|
|
zone->compact_order_failed = order + 1;
|
|
}
|
|
|
|
/* Returns true if restarting compaction after many failures */
|
|
static inline bool compaction_restarting(struct zone *zone, int order)
|
|
{
|
|
if (order < zone->compact_order_failed)
|
|
return false;
|
|
|
|
return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
|
|
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,
|
|
enum migrate_mode mode, int *contended,
|
|
int alloc_flags, int classzone_idx,
|
|
struct zone **candidate_zone)
|
|
{
|
|
return COMPACT_CONTINUE;
|
|
}
|
|
|
|
static inline void compact_pgdat(pg_data_t *pgdat, int order)
|
|
{
|
|
}
|
|
|
|
static inline void reset_isolation_suitable(pg_data_t *pgdat)
|
|
{
|
|
}
|
|
|
|
static inline unsigned long compaction_suitable(struct zone *zone, int order,
|
|
int alloc_flags, int classzone_idx)
|
|
{
|
|
return COMPACT_SKIPPED;
|
|
}
|
|
|
|
static inline void defer_compaction(struct zone *zone, int order)
|
|
{
|
|
}
|
|
|
|
static inline bool compaction_deferred(struct zone *zone, int order)
|
|
{
|
|
return true;
|
|
}
|
|
|
|
#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 */
|