On Sat, 2015-07-25 at 08:48 +0200, Christoph Hellwig wrote: > On Fri, Jul 24, 2015 at 01:32:14PM -0700, Nicholas A. Bellinger wrote: > > We've already been through this discussion a couple of years back when > > target_submit_cmd() first came into existence. > > > > The reason iscsi/iser-target continues to be a special case is due to > > immediate data vs. non immediate data and their respective command > > sequence number ordering requirements. > > I don't see how immediate data plays into this, the write_pending > callbacks can simply skip the data transfer path, similar to what > Bart's port of the latest SRP target to lio does as well. iscsit_execute_cmd() is using iscsit_transport->iscsit_get_dataout() for any remaining solicited data-out (R2T/RDMA_READ) payload when immediate write data is smaller than total EDTL. -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
