On Mon, Apr 17, 2023 at 6:54 AM Sergey Senozhatsky
<senozhatsky@xxxxxxxxxxxx> wrote:
>
> 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
The numbers seem to be better when using an atomic vs. a mutex, is
this just noise or significant difference? (I am not familiar with
lock-stat).
>
> 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>
FWIW,
Reviewed-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
> ---
> 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
>
