| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Mon, 29 Jun 2015 16:07:11 +0900
From: Minchan Kim <minchan@...nel.org>
To: Sergey Senozhatsky <sergey.senozhatsky@...il.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
Sergey Senozhatsky <sergey.senozhatsky.work@...il.com>
Subject: Re: [RFC][PATCHv3 7/7] zsmalloc: register a shrinker to trigger
auto-compaction
On Thu, Jun 18, 2015 at 08:46:44PM +0900, Sergey Senozhatsky wrote:
> Perform automatic pool compaction by a shrinker when system
> is getting tight on memory.
>
> User-space has a very little knowledge regarding zsmalloc fragmentation
> and basically has no mechanism to tell whether compaction will result
> in any memory gain. Another issue is that user space is not always
> aware of the fact that system is getting tight on memory. Which leads
> to very uncomfortable scenarios when user space may start issuing
> compaction 'randomly' or from crontab (for example). Fragmentation
> is not always necessarily bad, allocated and unused objects, after all,
> may be filled with the data later, w/o the need of allocating a new
> zspage. On the other hand, we obviously don't want to waste memory
> when systems needs it.
>
> Compaction now has a relatively quick pool scan so we are able to
> estimate the number of pages that will be freed easily, which makes it
> possible to call this function from a shrinker->count_objects() callback.
> We also abort compaction as soon as we detect that we can't free any
> pages any more, preventing wasteful objects migrations.
>
> Minchan Kim proposed to use the shrinker (the original patch was too
> aggressive and was attempting to perform compaction for every
> ALMOST_EMPTY zspage).
>
> Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@...il.com>
> Suggested-by: Minchan Kim <minchan@...nel.org>
> ---
> mm/zsmalloc.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++++------
> 1 file changed, 71 insertions(+), 7 deletions(-)
>
> diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
> index c9aea0a..692b7dc 100644
> --- a/mm/zsmalloc.c
> +++ b/mm/zsmalloc.c
> @@ -247,7 +247,9 @@ struct zs_pool {
> atomic_long_t pages_allocated;
> /* How many objects were migrated */
> unsigned long num_migrated;
> -
> + /* Compact classes */
> + struct shrinker shrinker;
> + bool shrinker_enabled;
> #ifdef CONFIG_ZSMALLOC_STAT
> struct dentry *stat_dentry;
> #endif
> @@ -1730,12 +1732,9 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class)
>
> while ((dst_page = isolate_target_page(class))) {
> cc.d_page = dst_page;
> - /*
> - * If there is no more space in dst_page, resched
> - * and see if anyone had allocated another zspage.
> - */
> +
> if (!migrate_zspage(pool, class, &cc))
> - break;
> + goto out;
It should retry with another target_page instead of going out.
>
> putback_zspage(pool, class, dst_page);
> }
> @@ -1750,7 +1749,9 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class)
> cond_resched();
> spin_lock(&class->lock);
> }
> -
> +out:
> + if (dst_page)
> + putback_zspage(pool, class, dst_page);
> if (src_page)
> putback_zspage(pool, class, src_page);
>
> @@ -1774,6 +1775,65 @@ unsigned long zs_compact(struct zs_pool *pool)
> }
> EXPORT_SYMBOL_GPL(zs_compact);
>
> +static unsigned long zs_shrinker_scan(struct shrinker *shrinker,
> + struct shrink_control *sc)
> +{
> + unsigned long freed;
> + struct zs_pool *pool = container_of(shrinker, struct zs_pool,
> + shrinker);
> +
> + freed = pool->num_migrated;
> + /* Compact classes and calculate compaction delta */
> + freed = zs_compact(pool) - freed;
Returns migrated object count.
> +
> + return freed ? freed : SHRINK_STOP;
> +}
> +
> +static unsigned long zs_shrinker_count(struct shrinker *shrinker,
> + struct shrink_control *sc)
> +{
> + int i;
> + struct size_class *class;
> + unsigned long to_free = 0;
> + struct zs_pool *pool = container_of(shrinker, struct zs_pool,
> + shrinker);
> +
> + if (!pool->shrinker_enabled)
> + return 0;
> +
> + for (i = zs_size_classes - 1; i >= 0; i--) {
> + class = pool->size_class[i];
> + if (!class)
> + continue;
> + if (class->index != i)
> + continue;
> +
> + spin_lock(&class->lock);
> + to_free += zs_can_compact(class);
But it returns wasted_obj / max_obj_per_zspage?
> + spin_unlock(&class->lock);
> + }
> +
> + return to_free;
> +}
> +
> +static void zs_unregister_shrinker(struct zs_pool *pool)
> +{
> + if (pool->shrinker_enabled) {
> + unregister_shrinker(&pool->shrinker);
> + pool->shrinker_enabled = false;
> + }
> +}
> +
> +static int zs_register_shrinker(struct zs_pool *pool)
> +{
> + pool->shrinker.scan_objects = zs_shrinker_scan;
> + pool->shrinker.count_objects = zs_shrinker_count;
> + pool->shrinker.batch = 0;
> + pool->shrinker.seeks = DEFAULT_SEEKS;
> +
> + return register_shrinker(&pool->shrinker);
> +}
> +
> /**
> * zs_create_pool - Creates an allocation pool to work from.
> * @flags: allocation flags used to allocate pool metadata
> @@ -1859,6 +1919,9 @@ struct zs_pool *zs_create_pool(char *name, gfp_t flags)
> if (zs_pool_stat_create(name, pool))
> goto err;
>
> + /* Not critical, we still can use the pool */
> + if (zs_register_shrinker(pool) == 0)
> + pool->shrinker_enabled = true;
> return pool;
>
> err:
> @@ -1871,6 +1934,7 @@ void zs_destroy_pool(struct zs_pool *pool)
> {
> int i;
>
> + zs_unregister_shrinker(pool);
> zs_pool_stat_destroy(pool);
>
> for (i = 0; i < zs_size_classes; i++) {
> --
> 2.4.4
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists