mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-31 16:38:12 +00:00
4943308556
Mike Kravetz reports that "hugetlb allocations could stall for minutes or hours when should_compact_retry() would return true more often then it should. Specifically, this was in the case where compact_result was COMPACT_DEFERRED and COMPACT_PARTIAL_SKIPPED and no progress was being made." The problem is that the compaction_withdrawn() test in should_compact_retry() includes compaction outcomes that are only possible on low compaction priority, and results in a retry without increasing the priority. This may result in furter reclaim, and more incomplete compaction attempts. With this patch, compaction priority is raised when possible, or should_compact_retry() returns false. The COMPACT_SKIPPED result doesn't really fit together with the other outcomes in compaction_withdrawn(), as that's a result caused by insufficient order-0 pages, not due to low compaction priority. With this patch, it is moved to a new compaction_needs_reclaim() function, and for that outcome we keep the current logic of retrying if it looks like reclaim will be able to help. Link: http://lkml.kernel.org/r/20190806014744.15446-4-mike.kravetz@oracle.com Reported-by: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Tested-by: Mike Kravetz <mike.kravetz@oracle.com> Cc: Hillf Danton <hdanton@sina.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
258 lines
7.3 KiB
C
258 lines
7.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#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_FULL,
|
|
MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_FULL,
|
|
COMPACT_PRIO_SYNC_LIGHT,
|
|
MIN_COMPACT_COSTLY_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 terminated after concluding that the allocation
|
|
* should now succeed
|
|
*/
|
|
COMPACT_SUCCESS,
|
|
};
|
|
|
|
struct alloc_context; /* in mm/internal.h */
|
|
|
|
/*
|
|
* Number of free order-0 pages that should be available above given watermark
|
|
* to make sure compaction has reasonable chance of not running out of free
|
|
* pages that it needs to isolate as migration target during its work.
|
|
*/
|
|
static inline unsigned long compact_gap(unsigned int order)
|
|
{
|
|
/*
|
|
* Although all the isolations for migration are temporary, compaction
|
|
* free scanner may have up to 1 << order pages on its list and then
|
|
* try to split an (order - 1) free page. At that point, a gap of
|
|
* 1 << order might not be enough, so it's safer to require twice that
|
|
* amount. Note that the number of pages on the list is also
|
|
* effectively limited by COMPACT_CLUSTER_MAX, as that's the maximum
|
|
* that the migrate scanner can have isolated on migrate list, and free
|
|
* scanner is only invoked when the number of isolated free pages is
|
|
* lower than that. But it's not worth to complicate the formula here
|
|
* as a bigger gap for higher orders than strictly necessary can also
|
|
* improve chances of compaction success.
|
|
*/
|
|
return 2UL << order;
|
|
}
|
|
|
|
#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_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,
|
|
struct page **page);
|
|
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_SUCCESS)
|
|
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 needs reclaim to be performed first, so it can continue. */
|
|
static inline bool compaction_needs_reclaim(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;
|
|
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* Compaction has backed off for some reason after doing some work or none
|
|
* at all. It might be throttling or lock contention. Retrying might be still
|
|
* worthwhile, but with a higher priority if allowed.
|
|
*/
|
|
static inline bool compaction_withdrawn(enum compact_result result)
|
|
{
|
|
/*
|
|
* 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 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_needs_reclaim(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 */
|
|
|
|
struct node;
|
|
#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 */
|