kernel_optimize_test/include/linux/compaction.h
Vlastimil Babka c3486f5376 mm, compaction: simplify contended compaction handling
Async compaction detects contention either due to failing trylock on
zone->lock or lru_lock, or by need_resched().  Since 1f9efdef4f ("mm,
compaction: khugepaged should not give up due to need_resched()") the
code got quite complicated to distinguish these two up to the
__alloc_pages_slowpath() level, so different decisions could be taken
for khugepaged allocations.

After the recent changes, khugepaged allocations don't check for
contended compaction anymore, so we again don't need to distinguish lock
and sched contention, and simplify the current convoluted code a lot.

However, I believe it's also possible to simplify even more and
completely remove the check for contended compaction after the initial
async compaction for costly orders, which was originally aimed at THP
page fault allocations.  There are several reasons why this can be done
now:

- with the new defaults, THP page faults no longer do reclaim/compaction at
  all, unless the system admin has overridden the default, or application has
  indicated via madvise that it can benefit from THP's. In both cases, it
  means that the potential extra latency is expected and worth the benefits.
- even if reclaim/compaction proceeds after this patch where it previously
  wouldn't, the second compaction attempt is still async and will detect the
  contention and back off, if the contention persists
- there are still heuristics like deferred compaction and pageblock skip bits
  in place that prevent excessive THP page fault latencies

Link: http://lkml.kernel.org/r/20160721073614.24395-9-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-07-28 16:07:41 -07:00

227 lines
6.1 KiB
C

#ifndef _LINUX_COMPACTION_H
#define _LINUX_COMPACTION_H
/*
* Determines how hard direct compaction should try to succeed.
* Lower value means higher priority, analogically to reclaim priority.
*/
enum compact_priority {
COMPACT_PRIO_SYNC_LIGHT,
MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
COMPACT_PRIO_ASYNC,
INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC
};
/* Return values for compact_zone() and try_to_compact_pages() */
/* When adding new states, please adjust include/trace/events/compaction.h */
enum compact_result {
/* For more detailed tracepoint output - internal to compaction */
COMPACT_NOT_SUITABLE_ZONE,
/*
* compaction didn't start as it was not possible or direct reclaim
* was more suitable
*/
COMPACT_SKIPPED,
/* compaction didn't start as it was deferred due to past failures */
COMPACT_DEFERRED,
/* compaction not active last round */
COMPACT_INACTIVE = COMPACT_DEFERRED,
/* For more detailed tracepoint output - internal to compaction */
COMPACT_NO_SUITABLE_PAGE,
/* compaction should continue to another pageblock */
COMPACT_CONTINUE,
/*
* The full zone was compacted scanned but wasn't successfull to compact
* suitable pages.
*/
COMPACT_COMPLETE,
/*
* direct compaction has scanned part of the zone but wasn't successfull
* to compact suitable pages.
*/
COMPACT_PARTIAL_SKIPPED,
/* compaction terminated prematurely due to lock contentions */
COMPACT_CONTENDED,
/*
* direct compaction partially compacted a zone and there might be
* suitable pages
*/
COMPACT_PARTIAL,
};
struct alloc_context; /* in mm/internal.h */
#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 sysctl_compact_unevictable_allowed;
extern int fragmentation_index(struct zone *zone, unsigned int order);
extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
unsigned int order, unsigned int alloc_flags,
const struct alloc_context *ac, enum compact_priority prio);
extern void compact_pgdat(pg_data_t *pgdat, int order);
extern void reset_isolation_suitable(pg_data_t *pgdat);
extern enum compact_result compaction_suitable(struct zone *zone, int order,
unsigned int alloc_flags, int classzone_idx);
extern void defer_compaction(struct zone *zone, int order);
extern bool compaction_deferred(struct zone *zone, int order);
extern void compaction_defer_reset(struct zone *zone, int order,
bool alloc_success);
extern bool compaction_restarting(struct zone *zone, int order);
/* Compaction has made some progress and retrying makes sense */
static inline bool compaction_made_progress(enum compact_result result)
{
/*
* Even though this might sound confusing this in fact tells us
* that the compaction successfully isolated and migrated some
* pageblocks.
*/
if (result == COMPACT_PARTIAL)
return true;
return false;
}
/* Compaction has failed and it doesn't make much sense to keep retrying. */
static inline bool compaction_failed(enum compact_result result)
{
/* All zones were scanned completely and still not result. */
if (result == COMPACT_COMPLETE)
return true;
return false;
}
/*
* Compaction has backed off for some reason. It might be throttling or
* lock contention. Retrying is still worthwhile.
*/
static inline bool compaction_withdrawn(enum compact_result result)
{
/*
* Compaction backed off due to watermark checks for order-0
* so the regular reclaim has to try harder and reclaim something.
*/
if (result == COMPACT_SKIPPED)
return true;
/*
* If compaction is deferred for high-order allocations, it is
* because sync compaction recently failed. If this is the case
* and the caller requested a THP allocation, we do not want
* to heavily disrupt the system, so we fail the allocation
* instead of entering direct reclaim.
*/
if (result == COMPACT_DEFERRED)
return true;
/*
* If compaction in async mode encounters contention or blocks higher
* priority task we back off early rather than cause stalls.
*/
if (result == COMPACT_CONTENDED)
return true;
/*
* Page scanners have met but we haven't scanned full zones so this
* is a back off in fact.
*/
if (result == COMPACT_PARTIAL_SKIPPED)
return true;
return false;
}
bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
int alloc_flags);
extern int kcompactd_run(int nid);
extern void kcompactd_stop(int nid);
extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx);
#else
static inline void compact_pgdat(pg_data_t *pgdat, int order)
{
}
static inline void reset_isolation_suitable(pg_data_t *pgdat)
{
}
static inline enum compact_result 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;
}
static inline bool compaction_made_progress(enum compact_result result)
{
return false;
}
static inline bool compaction_failed(enum compact_result result)
{
return false;
}
static inline bool compaction_withdrawn(enum compact_result result)
{
return true;
}
static inline int kcompactd_run(int nid)
{
return 0;
}
static inline void kcompactd_stop(int nid)
{
}
static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
{
}
#endif /* CONFIG_COMPACTION */
#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
struct node;
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 */