On Wed, Aug 04 2010 at 10:16pm -0400,
Jun'ichi Nomura [off-list ref] wrote:

Hi Christoph,

(08/04/10 17:54), Christoph Hellwig wrote:

quoted

On Wed, Aug 04, 2010 at 01:57:37PM +0900, Kiyoshi Ueda wrote:

quoted

quoted

-		if (unlikely(dm_rq_is_flush_request(rq))) {
+		if (rq->cmd_flags & REQ_FLUSH) {
 			BUG_ON(md->flush_request);
 			md->flush_request = rq;
 			blk_start_request(rq);

Current request-based device-mapper's flush code depends on
the block-layer's barrier behavior which dispatches only one request
at a time when flush is needed.
In other words, current request-based device-mapper can't handle
other requests while a flush request is in progress.

I'll take a look how I can fix the request-based device-mapper to
cope with it.  I think it'll take time for carefull investigation.

Given that request based device mapper doesn't even look at the
block numbers from what I can see just removing any special casing
for REQ_FLUSH should probably do it.

Special casing is necessary because device-mapper may have to
send multiple copies of REQ_FLUSH request to multiple
targets, while normal request is just sent to single target.

Yes, request-based DM is meant to have all the same capabilities as
bio-based DM.  So in theory it should support multiple targets but in
practice it doesn't.  DM's multipath target is the only consumer of
request-based DM and it only ever clones a single flush request
(num_flush_requests = 1).

So why not remove all of request-based DM's barrier infrastructure and
simply rely on the revised block layer to sequence the FLUSH+WRITE
request for request-based DM?

Given that we do not have a request-based DM target that requires
cloning multiple FLUSH requests its unused code that is delaying DM
support for the new FLUSH+FUA work (NOTE: bio-based DM obviously still
needs work in this area).

Once we have a need for using request-based DM for something other than
multipath we can take a fresh look at implementing rq-based FLUSH+FUA.

Mike

p.s. I know how hard NEC worked on request-based DM's barrier support;
so I'm not suggesting this lightly.  For me it just seems like we're
carrying complexity in DM that hasn't ever been required.