Re: [PATCH] x86_64/lib: improve the performance of memmove

[Miao Xie <miaox@cn.fujitsu.com>]

On Fri, 17 Sep 2010 08:55:18 +0800, ykzhao wrote:
> On Thu, 2010-09-16 at 15:16 +0800, Miao Xie wrote:
>> On Thu, 16 Sep 2010 08:48:25 +0200 (cest), Andi Kleen wrote:
>>>> When the dest and the src do overlap and the memory area is large, memmove
>>>> of
>>>> x86_64 is very inefficient, and it led to bad performance, such as btrfs's
>>>> file
>>>> deletion performance. This patch improved the performance of memmove on
>>>> x86_64
>>>> by using __memcpy_bwd() instead of byte copy when doing large memory area
>>>> copy
>>>> (len>   64).
>>>
>>>
>>> I still don't understand why you don't simply use a backwards
>>> string copy (with std) ? That should be much simpler and
>>> hopefully be as optimized for kernel copies on recent CPUs.
>>
>> But according to the comment of memcpy, some CPUs don't support "REP" instruction,
> 
> Where do you find that the "REP" instruction is not supported on some
> CPUs? The comment in arch/x86/lib/memcpy_64.s only states that some CPUs
> will run faster when using string copy instruction.

Sorry! I misread the comment.

>> so I think we must implement a backwards string copy by other method for those CPUs,
>> But that implement is complex, so I write it as a function -- __memcpy_bwd().
> 
> Will you please look at tip/x86/ tree(mem branch)? The memory copy on
> x86_64 is already optimized.

Thanks for your reminding! It is very helpful.
Miao
 
> thanks.
>      Yakui
>>
>> Thanks!
>> Miao
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
> 
>