[Sheepdog] [PATCH 3/3] store: use fallocate when allocating new objects

[Christoph Hellwig]

On Fri, Nov 11, 2011 at 08:41:25PM +0900, MORITA Kazutaka wrote:
> ==
> 
> 
> The result was as follows:
> 
>   $ time ./a.out temp pwrite
>   
>   real   0m0.244s
>   user   0m0.000s
>   sys    0m0.008s
> 
>   $ time ./a.out temp fallocate
>   
>   real   0m43.050s
>   user   0m0.000s
>   sys    0m0.060s

Wow, I wonder what glibc is doing there given that you write the
whole block.

> I guess posix_fallocate() causes a severe performance problem under
> the circumstances that write is slow, because it calls lots of
> pwrite() for each ext3 block when fallocate() is not available.

Ok.  Do you want a patch using fallocate and keeping the existing
fallback for now?