On Thu, Aug 05, 2010 at 05:20:12AM +0300, Avi Kivity wrote:

Why not?  To be clear, I'm talking about an io_submit() with
multiple IO_CMD_FSYNC requests, with a kernel implementation that is
able to batch these requests.

IO_CMD_FSYNC doesn't exist right now, but sure, it means we don't have
to add a new syscall.  I find the aio interface to be horribly
complicated, and it would mean that programs would have to link
against libaio, which again isn't my favorite set of interfaces.  

All of that being said, I do agree that adding a new IO_CMD_FSYNC,
IO_CMD_FSYNCDATA, IO_CMD_FSYNC_NOBARRIER, and
IOCMD_FSYNC_DATA_NOBARRIER would be the simplist thing to do from a
kernel implementation perspective.

						- Ted