Il giorno 27/lug/2011, alle ore 20:31, Christoph Hellwig <h...@lst.de> ha scritto:
> Did you test this at all? > Yes! Not at kernel level :-) Usually I trust documentation and man pages. > On Wed, Jul 27, 2011 at 08:25:25PM +0200, Frediano Ziglio wrote: >> + case QEMU_AIO_FLUSH: >> + io_prep_fdsync(iocbs, fd); >> + break; > > Looks great, but doesn't work as expected. > > Hint: grep for aio_fsync in the linux kernel. > Thanks. I'll try to port misaligned access to Linux AIO. Also I'll add some comments on code to avoid somebody do the same mistache I did. Mainly however -k qemu-img and aio=native in blockdev options are silently ignored if nocache is not enabled. Also I notice that combining XFS, Linux AIO, O_DIRECT and O_DSYNC give impressive performance but currently there is no way to specify all that flags together cause nocache enable O_DIRECT while O_DSYNC is enabled with writethrough. Frediano