Andi Kleen a écrit :

> 
>>(because of the insane struct file_ra_state f_ra. I wish this structure 
>>were dynamically allocated only for files that really use it)
> 
> 
> How about you submit a patch for that instead? 
> 
> -Andi

OK, could you please comment this patch ?

The problem of dynamically allocating the readahead state data is that the allocation can fail and should not be fatal.
I made some choices that might be not good.

I also chose not to align "file_ra" slab on SLAB_HWCACHE_ALIGN because the object size is 10*sizeof(long), so alignment would loose 
6*sizeof(long) bytes for each object.


[PATCH]

* struct file cleanup : the very large file_ra_state is now allocated only on demand, using a dedicated "file_ra" slab.
	64bits machines handling lot of sockets can save about 72 bytes per file.
* private_data : The field is moved close to f_count and f_op fields to speedup sockfd_lookups

Thank you

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>