On Thu, 2011-12-01 at 04:07 -0500, Christoph Hellwig wrote: > On Thu, Dec 01, 2011 at 01:04:09AM -0800, Nicholas A. Bellinger wrote: > > Anyways, will need to poke at this with some older devices to make sure > > it work's in practice, but if your really sure w/ blk_execute_rq_nowait > > is enforcing scsi_device->queue_depth, I'll go ahead and drop the legacy > > usage with ->depth_left in target-core now. > > scsi_request_fn never goes over the various queue depth limits. If it > ever in the last 10 years it was a bad bug that probably got fixed > rather quickly. > > Do you have any details on the issues that you saw? > I'm thinking mismatch between what's reported in ->can_queue and ->queue_depth with multiple LUNs per host, that a few LLDs (including megaraid) got wrong at some point in early 2.6. -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
