Re: [PATCH -mm v2 1/3] slub: never fail to shrink cache

[Balbir Singh]

On Thu, Jan 29, 2015 at 3:27 AM, Andrew Morton
<akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
> On Wed, 28 Jan 2015 19:22:49 +0300 Vladimir Davydov <vdavydov@xxxxxxxxxxxxx> wrote:
>
>> SLUB's version of __kmem_cache_shrink() not only removes empty slabs,
>> but also tries to rearrange the partial lists to place slabs filled up
>> most to the head to cope with fragmentation. To achieve that, it
>> allocates a temporary array of lists used to sort slabs by the number of
>> objects in use. If the allocation fails, the whole procedure is aborted.
>>
>> This is unacceptable for the kernel memory accounting extension of the
>> memory cgroup, where we want to make sure that kmem_cache_shrink()
>> successfully discarded empty slabs. Although the allocation failure is
>> utterly unlikely with the current page allocator implementation, which
>> retries GFP_KERNEL allocations of order <= 2 infinitely, it is better
>> not to rely on that.
>>
>> This patch therefore makes __kmem_cache_shrink() allocate the array on
>> stack instead of calling kmalloc, which may fail. The array size is
>> chosen to be equal to 32, because most SLUB caches store not more than
>> 32 objects per slab page. Slab pages with <= 32 free objects are sorted
>> using the array by the number of objects in use and promoted to the head
>> of the partial list, while slab pages with > 32 free objects are left in
>> the end of the list without any ordering imposed on them.
>>
>> ...
>>
>> @@ -3375,51 +3376,56 @@ int __kmem_cache_shrink(struct kmem_cache *s)
>>       struct kmem_cache_node *n;
>>       struct page *page;
>>       struct page *t;
>> -     int objects = oo_objects(s->max);
>> -     struct list_head *slabs_by_inuse =
>> -             kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL);
>> +     LIST_HEAD(discard);
>> +     struct list_head promote[SHRINK_PROMOTE_MAX];
>
> 512 bytes of stack.  The call paths leading to __kmem_cache_shrink()
> are many and twisty.  How do we know this isn't a problem?
>
> The logic behind choosing "32" sounds rather rubbery.  What goes wrong
> if we use, say, "4"?

This much space in the stack may be fertile grounds for kernel stack
overflow code execution :) Another perspective could be that there
should be allocations that are not penalized to a particular cgroup
(from an accounting perspective), should come from the reserved  pool.

Balbir Singh.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/