Re: [PATCH v2] scsi_debug: support scsi-mq, queues and locks

2014-07-15 Thread Martin K. Petersen
Rob == Elliott, Robert (Server Storage) elli...@hp.com writes: Rob, Rob When resp_unmap is the caller, though, there is no guarantee that Rob the data will change. Rob Maybe another modparam should be included to cause the driver to Rob purposely ignore unmap requests? That might help more

Re: [PATCH v2] scsi_debug: support scsi-mq, queues and locks

2014-07-14 Thread Douglas Gilbert
: support scsi-mq, queues and locks Resend, looks like the list does not like html attachments. This v2 patch is against Christoph's core-for-3.17 branch which includes scsi-mq V2. Here is a link to a partially updated version of the scsi_debug html page. http://sg.danny.cz/scsi/sdebug26.html

RE: [PATCH v2] scsi_debug: support scsi-mq, queues and locks

2014-07-13 Thread Elliott, Robert (Server Storage)
-Original Message- From: linux-scsi-ow...@vger.kernel.org [mailto:linux-scsi- ow...@vger.kernel.org] On Behalf Of Douglas Gilbert Sent: Monday, 07 July, 2014 8:31 AM To: SCSI development list Subject: [PATCH v2] scsi_debug: support scsi-mq, queues and locks Resend, looks like

Re: [PATCH v2] scsi_debug: support scsi-mq, queues and locks

2014-07-10 Thread Christoph Hellwig
This patch looks reasonable to me. I'd prefer if we didn't have to keep the optional host_lock mode for the long run, but if it's important to you for now we can keep it for a while. And chance you could split updates into a series of updates for future changes? Reviewed-by: Christoph Hellwig