Re: [linus:master] [mpage] 7d28631786: fio.write_iops 27.8% improvement

[Sergey Senozhatsky]

On (23/03/15 08:58), Christoph Hellwig wrote:
> 
> I think this simply accounts for the I/Os now that were skipped
> when using the bdev_read/write path before.

Oh, that would explain it. Otherwise I was slightly surprised (in a good
way) and puzzled.