c67fe3752a
Jim Schutt reported a problem that pointed at compaction contending
heavily on locks. The workload is straight-forward and in his own words;
The systems in question have 24 SAS drives spread across 3 HBAs,
running 24 Ceph OSD instances, one per drive. FWIW these servers
are dual-socket Intel 5675 Xeons w/48 GB memory. I've got ~160
Ceph Linux clients doing dd simultaneously to a Ceph file system
backed by 12 of these servers.
Early in the test everything looks fine
procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
r b swpd free buff cache si so bi bo in cs us sy id wa st
31 15 0 287216 576 38606628 0 0 2 1158 2 14 1 3 95 0 0
27 15 0 225288 576 38583384 0 0 18 2222016 203357 134876 11 56 17 15 0
28 17 0 219256 576 38544736 0 0 11 2305932 203141 146296 11 49 23 17 0
6 18 0 215596 576 38552872 0 0 7 2363207 215264 166502 12 45 22 20 0
22 18 0 226984 576 38596404 0 0 3 2445741 223114 179527 12 43 23 22 0
and then it goes to pot
procs -------------------memory------------------ ---swap-- -----io---- --system-- -----cpu-------
r b swpd free buff cache si so bi bo in cs us sy id wa st
163 8 0 464308 576 36791368 0 0 11 22210 866 536 3 13 79 4 0
207 14 0 917752 576 36181928 0 0 712 1345376 134598 47367 7 90 1 2 0
123 12 0 685516 576 36296148 0 0 429 1386615 158494 60077 8 84 5 3 0
123 12 0 598572 576 36333728 0 0 1107 1233281 147542 62351 7 84 5 4 0
622 7 0 660768 576 36118264 0 0 557 1345548 151394 59353 7 85 4 3 0
223 11 0 283960 576 36463868 0 0 46 1107160 121846 33006 6 93 1 1 0
Note that system CPU usage is very high blocks being written out has
dropped by 42%. He analysed this with perf and found
perf record -g -a sleep 10
perf report --sort symbol --call-graph fractal,5
34.63% [k] _raw_spin_lock_irqsave
|
|--97.30%-- isolate_freepages
| compaction_alloc
| unmap_and_move
| migrate_pages
| compact_zone
| compact_zone_order
| try_to_compact_pages
| __alloc_pages_direct_compact
| __alloc_pages_slowpath
| __alloc_pages_nodemask
| alloc_pages_vma
| do_huge_pmd_anonymous_page
| handle_mm_fault
| do_page_fault
| page_fault
| |
| |--87.39%-- skb_copy_datagram_iovec
| | tcp_recvmsg
| | inet_recvmsg
| | sock_recvmsg
| | sys_recvfrom
| | system_call
| | __recv
| | |
| | --100.00%-- (nil)
| |
| --12.61%-- memcpy
--2.70%-- [...]
There was other data but primarily it is all showing that compaction is
contended heavily on the zone->lock and zone->lru_lock.
commit [b2eef8c0: mm: compaction: minimise the time IRQs are disabled
while isolating pages for migration] noted that it was possible for
migration to hold the lru_lock for an excessive amount of time. Very
broadly speaking this patch expands the concept.
This patch introduces compact_checklock_irqsave() to check if a lock
is contended or the process needs to be scheduled. If either condition
is true then async compaction is aborted and the caller is informed.
The page allocator will fail a THP allocation if compaction failed due
to contention. This patch also introduces compact_trylock_irqsave()
which will acquire the lock only if it is not contended and the process
does not need to schedule.
Reported-by: Jim Schutt <jaschut@sandia.gov>
Tested-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
109 lines
3.2 KiB
C
109 lines
3.2 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 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
|
|
|
|
#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, bool *contended);
|
|
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 < defer_limit;
|
|
}
|
|
|
|
#else
|
|
static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
|
|
int order, gfp_t gfp_mask, nodemask_t *nodemask,
|
|
bool sync, bool *contended)
|
|
{
|
|
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 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 */
|