Re: [PATCH V4] mm/thp: Allocate transparent hugepages on local node

["Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>]

Vlastimil Babka <vbabka@suse.cz> writes:

> On 01/21/2015 01:48 AM, Andrew Morton wrote:
>> On Tue, 20 Jan 2015 17:04:31 +0530 "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> wrote:
>>> + * Should be called with the mm_sem of the vma hold.
>> 
>> That's a pretty cruddy sentence, isn't it?  Copied from
>> alloc_pages_vma().  "vma->vm_mm->mmap_sem" would be better.
>> 
>> And it should tell us whether mmap_sem required a down_read or a
>> down_write.  What purpose is it serving?
>
> This is already said for mmap_sem further above this comment line, which
> should be just deleted (and from alloc_hugepage_vma comment too).
>
>>> + *
>>> + */
>>> +struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma,
>>> +				unsigned long addr, int order)
>> 
>> This pointlessly bloats the kernel if CONFIG_TRANSPARENT_HUGEPAGE=n?
>> 
>> 
>> 
>> --- a/mm/mempolicy.c~mm-thp-allocate-transparent-hugepages-on-local-node-fix
>> +++ a/mm/mempolicy.c
>
> How about this cleanup on top? I'm not fully decided on the GFP_TRANSHUGE test.
> This is potentially false positive, although I doubt anything else uses the same
> gfp mask bits.

IMHO I found that to be more complex.

>
> Should "hugepage" be extra bool parameter instead? Should I #ifdef the parameter
> only for CONFIG_TRANSPARENT_HUGEPAGE, or is it not worth the ugliness?
>

I guess if we really want to consolidate both the functions, we should
try the above, without all those #ifdef. It is just one extra arg.  But
then is the reason to consolidate that strong ?

-aneesh

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>