On Thu, Jul 05 2007, Tejun Heo wrote:

Hello, Jens.

Jens Axboe wrote:

quoted

On Mon, May 28 2007, Neil Brown wrote:

quoted

I think the implementation priorities here are:

1/ implement a zero-length BIO_RW_BARRIER option.
2/ Use it (or otherwise) to make all dm and md modules handle
   barriers (and loop?).
3/ Devise and implement appropriate fall-backs with-in the block layer
   so that  -EOPNOTSUP is never returned.
4/ Remove unneeded cruft from filesystems (and elsewhere).

This is the start of 1/ above. It's very lightly tested, it's verified
to DTRT here at least and not crash :-)

It gets rid of the ->issue_flush_fn() queue callback, all the driver
knowledge resides in ->prepare_flush_fn() anyways. blkdev_issue_flush()
then just reuses the empty-bio approach to queue an empty barrier, this
should work equally well for stacked and non-stacked devices.

While this patch isn't complete yet, it's clearly the right direction to
go.

Finally took a brief look. :-) I think the sequencing for zero-length
barrier can be better done by pre-setting QUEUE_ORDSEQ_BAR in
start_ordered() rather than short circuiting the request after it's
issued.  What do you think?

Yeah, that might be cleaner and should achieve the same effect. I'll
test!

-- 
Jens Axboe