On Fri, Dec 5, 2014 at 8:56 PM, Martin K. Petersen <martin.petersen@xxxxxxxxxx> wrote: >>>>>> "Ming" == Ming Lei <ming.lei@xxxxxxxxxxxxx> writes: > > Ming, > > Ming> QEMU SCSI device claims to support UNMAP, WRITE SAME and WRITE > Ming> SAME 16 in LBP VPD page, but only provides "Maximum unmap LBA > Ming> count" in block limits VPD page, and "Maximum write same length" > Ming> isn't set. > > That really sounds like a problem that should be fixed in QEMU SCSI. It can be fixed, but there are lots of old QEMU in production. > > Ming> The default max_discard_sectors(SD_MAX_WS16_BLOCKS) can't work at > Ming> all since it is much bigger than the actual Maximum unmap LBA > Ming> count. > > There is absolutely no correlation between max write same blocks and max > unmap blocks. They are two entirely different commands. If QEMU SCSI Do you have any better idea for the problem? > advertises support for WRITE SAME(16) and does not report a cap in the > block limits VPD then we must expect that it supports the maximum number > of blocks that can be expressed by the command. Unfortunately it doesn't support that, see below log: [ 50.112885] sd 0:0:1:0: [sda] FAILED Result: hostbyte=DID_OK driverbyte=DRIVER_SENSE [ 50.113859] sd 0:0:1:0: [sda] Sense Key : Illegal Request [current] [ 50.113859] sd 0:0:1:0: [sda] Add. Sense: Invalid field in cdb [ 50.113859] sd 0:0:1:0: [sda] CDB: [ 50.113859] Write same(16): 93 08 00 00 00 00 00 00 80 00 00 40 00 00 00 00 [ 50.113859] blk_update_request: critical target error, dev sda, sector 32768 Thanks, Ming Lei -- 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