On 08/28/14 at 09:47am, Christoph Lameter wrote:
> On Thu, 28 Aug 2014, WANG Chao wrote:
>
> > What about failslab_store()? SLAB_FAILSLAB is also a nomerge flag.
>
>
> Subject: slub: Disable tracing and failslab for merged slabs
>
> Tracing of mergeable slabs as well as uses of failslab are
> confusing since the objects of multiple slab caches will be
> affected. Moreover this creates a situation where a mergeable
> slab will become unmergeable.
>
> If tracing or failslab testing is desired then it may be best to
> switch merging off for starters.
>
> Signed-off-by: Christoph Lameter <cl@xxxxxxxxx>
>
> Index: linux/mm/slub.c
> ===================================================================
> --- linux.orig/mm/slub.c 2014-08-08 11:52:30.039681592 -0500
> +++ linux/mm/slub.c 2014-08-28 09:45:58.748840392 -0500
> @@ -4604,6 +4604,14 @@ static ssize_t trace_show(struct kmem_ca
> static ssize_t trace_store(struct kmem_cache *s, const char *buf,
> size_t length)
> {
> + /*
> + * Tracing a merged cache is going to give confusing results
> + * as well as cause other issues like converting a mergeable
> + * cache into an umergeable one.
> + */
> + if (s->refcount > 1)
> + return -EINVAL;
> +
> s->flags &= ~SLAB_TRACE;
> if (buf[0] == '1') {
> s->flags &= ~__CMPXCHG_DOUBLE;
> @@ -4721,6 +4729,9 @@ static ssize_t failslab_show(struct kmem
> static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
> size_t length)
> {
> + if (s->refcount > 1)
> + return -EINVAL;
> +
> s->flags &= ~SLAB_FAILSLAB;
> if (buf[0] == '1')
> s->flags |= SLAB_FAILSLAB;
This works for me. Thanks for the fix.
WANG Chao
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>