linux-stable/include/linux/compaction.h
Vlastimil Babka 1f9efdef4f mm, compaction: khugepaged should not give up due to need_resched()
Async compaction aborts when it detects zone lock contention or
need_resched() is true.  David Rientjes has reported that in practice,
most direct async compactions for THP allocation abort due to
need_resched().  This means that a second direct compaction is never
attempted, which might be OK for a page fault, but khugepaged is intended
to attempt a sync compaction in such case and in these cases it won't.

This patch replaces "bool contended" in compact_control with an int that
distinguishes between aborting due to need_resched() and aborting due to
lock contention.  This allows propagating the abort through all compaction
functions as before, but passing the abort reason up to
__alloc_pages_slowpath() which decides when to continue with direct
reclaim and another compaction attempt.

Another problem is that try_to_compact_pages() did not act upon the
reported contention (both need_resched() or lock contention) immediately
and would proceed with another zone from the zonelist.  When
need_resched() is true, that means initializing another zone compaction,
only to check again need_resched() in isolate_migratepages() and aborting.
 For zone lock contention, the unintended consequence is that the lock
contended status reported back to the allocator is detrmined from the last
zone where compaction was attempted, which is rather arbitrary.

This patch fixes the problem in the following way:
- async compaction of a zone aborting due to need_resched() or fatal signal
  pending means that further zones should not be tried. We report
  COMPACT_CONTENDED_SCHED to the allocator.
- aborting zone compaction due to lock contention means we can still try
  another zone, since it has different set of locks. We report back
  COMPACT_CONTENDED_LOCK only if *all* zones where compaction was attempted,
  it was aborted due to lock contention.

As a result of these fixes, khugepaged will proceed with second sync
compaction as intended, when the preceding async compaction aborted due to
need_resched().  Page fault compactions aborting due to need_resched()
will spare some cycles previously wasted by initializing another zone
compaction only to abort again.  Lock contention will be reported only
when compaction in all zones aborted due to lock contention, and therefore
it's not a good idea to try again after reclaim.

In stress-highalloc from mmtests configured to use __GFP_NO_KSWAPD, this
has improved number of THP collapse allocations by 10%, which shows
positive effect on khugepaged.  The benchmark's success rates are
unchanged as it is not recognized as khugepaged.  Numbers of compact_stall
and compact_fail events have however decreased by 20%, with
compact_success still a bit improved, which is good.  With benchmark
configured not to use __GFP_NO_KSWAPD, there is 6% improvement in THP
collapse allocations, and only slight improvement in stalls and failures.

[akpm@linux-foundation.org: fix warnings]
Reported-by: David Rientjes <rientjes@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Acked-by: 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>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-09 22:25:54 -04:00

151 lines
4.5 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,
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);
/* 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,
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)
{
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 */