zsmalloc pool can be compacted concurrently by many contexts,
e.g.
cc1 handle_mm_fault()
do_anonymous_page()
__alloc_pages_slowpath()
try_to_free_pages()
do_try_to_free_pages(
lru_gen_shrink_node()
shrink_slab()
do_shrink_slab()
zs_shrinker_scan()
zs_compact()
This creates unnecessary contention as all those processes
compete for access to the same classes. A single compaction
process is enough. Moreover contention that is created by
multiple compaction processes impact other zsmalloc functions,
e.g. zs_malloc(), since zsmalloc uses "global" pool->lock to
synchronize access to pool.
Introduce pool compaction mutex and permit only one compaction
context at a time. This reduces overall pool->lock contention.
/proc/lock-stat after make -j$((`nproc`+1)) linux kernel for
&pool->lock#3:
Base Patched
------------------------------------------
con-bounces 2035730 1540066
contentions 2343871 1774348
waittime-min 0.10 0.10
waittime-max 4004216.24 2745.22
waittime-total 101334168.29 67865414.91
waittime-avg 43.23 38.25
acq-bounces 2895765 2186745
acquisitions 6247686 5136943
holdtime-min 0.07 0.07
holdtime-max 2605507.97 482439.16
holdtime-total 9998599.59 5107151.01
holdtime-avg 1.60 0.99
Test run time:
Base
2775.15user 1709.13system 2:13.82elapsed 3350%CPU
Patched
2608.25user 1439.03system 2:03.63elapsed 3273%CPU
Signed-off-by: Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx>
---
mm/zsmalloc.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index cc81dfba05a0..dfec2fc6a30f 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -264,6 +264,7 @@ struct zs_pool {
struct work_struct free_work;
#endif
spinlock_t lock;
+ atomic_t compaction_in_progress;
};
struct zspage {
@@ -2274,6 +2275,9 @@ unsigned long zs_compact(struct zs_pool *pool)
struct size_class *class;
unsigned long pages_freed = 0;
+ if (atomic_xchg(&pool->compaction_in_progress, 1))
+ return 0;
+
for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
class = pool->size_class[i];
if (class->index != i)
@@ -2281,6 +2285,7 @@ unsigned long zs_compact(struct zs_pool *pool)
pages_freed += __zs_compact(pool, class);
}
atomic_long_add(pages_freed, &pool->stats.pages_compacted);
+ atomic_set(&pool->compaction_in_progress, 0);
return pages_freed;
}
@@ -2388,6 +2393,7 @@ struct zs_pool *zs_create_pool(const char *name)
init_deferred_free(pool);
spin_lock_init(&pool->lock);
+ atomic_set(&pool->compaction_in_progress, 0);
pool->name = kstrdup(name, GFP_KERNEL);
if (!pool->name)
--
2.40.0.634.g4ca3ef3211-goog
