@@ -453,7 +453,39 @@ int scsi_req_parse(SCSIRequest *req, uint8_t *buf)
int scsi_req_setup(SCSIRequest *req, int is_write, uint64_t lba, uint64_t count)
{
- req->cmd.buf[0] = is_write ? WRITE_12 : READ_12;
+ /*
+ * Set the req->cmd.len and fill in the CDB's Logical Block Address and
+ * Transfer length (block count) that is required by SG_IO passthrough
+ * in hw/scsi-generic.c:execute_command_run()
+ */
+ if (lba > 0x00000000ffffffff) {
+ req->cmd.len = 16;
+ req->cmd.buf[0] = is_write ? WRITE_16 : READ_16;
+ req->cmd.buf[2] = (lba >> 56) & 0xff;
+ req->cmd.buf[3] = (lba >> 48) & 0xff;
+ req->cmd.buf[4] = (lba >> 40) & 0xff;
+ req->cmd.buf[5] = (lba >> 32) & 0xff;
+ req->cmd.buf[6] = (lba >> 24) & 0xff;
+ req->cmd.buf[7] = (lba >> 16) & 0xff;
+ req->cmd.buf[8] = (lba >> 8) & 0xff;
+ req->cmd.buf[9] = lba & 0xff;
+ req->cmd.buf[10] = (count >> 24) & 0xff;
+ req->cmd.buf[11] = (count >> 16) & 0xff;
+ req->cmd.buf[12] = (count >> 8) & 0xff;
+ req->cmd.buf[13] = count & 0xff;
+ } else {
+ req->cmd.len = 12;
+ req->cmd.buf[0] = is_write ? WRITE_12 : READ_12;
+ req->cmd.buf[2] = (lba >> 24) & 0xff;
+ req->cmd.buf[3] = (lba >> 16) & 0xff;
+ req->cmd.buf[4] = (lba >> 8) & 0xff;
+ req->cmd.buf[5] = lba & 0xff;
+ req->cmd.buf[6] = (count >> 24) & 0xff;
+ req->cmd.buf[7] = (count >> 16) & 0xff;
+ req->cmd.buf[8] = (count >> 8) & 0xff;
+ req->cmd.buf[9] = count & 0xff;
+ }
+
req->cmd.mode = is_write ? SCSI_XFER_TO_DEV : SCSI_XFER_FROM_DEV;
req->cmd.lba = lba;
req->cmd.xfer = count * req->dev->blocksize;
and the the link containing the commit proper:
http://git.kernel.org/?p=virt/kvm/nab/qemu-kvm.git;a=commitdiff;h=6a1a11bfbcde49bb864fe40cf3b254b1ed607c72
So far using the LTP-Disktest O_DIRECT benchmark with 8 threads and 64k
blocksize in a guest with 4 VCPUs and 2048MB memory to a SG_IO <->
TCM/RAMDISK_DR backstore running on a KVM 5500 series Nehalem host, I am
seeing ~8.9 Gb/sec (~1050 MB/sec) of bandwith to megasas with the large
blocksizes. Seperately I am able to mkfs and mount filesystems from
within KVM guest, shutdown and then mount locally with TCM_Loop on the
host, etc.
Here is how it looks in action so far:
http://linux-iscsi.org/images/Megasas-SGIO-TCM_Loop-05012010.png
In order to achieve these results I am running with the recommended
MEGASAS_MAX_FRAMES=1000, and two extra kernel patches for seting
include/scsi/sg.h:SG_MAX_QUEUE=128 and increasing TCM_Loop's SCSI LLD
settings for struct scsi_host_template to can_queue=1024,
cmd_per_lun=1024, and max_sectors=256.
@@ -240,7 +240,7 @@ typedef struct sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */
#define SG_DEF_RESERVED_SIZE SG_SCATTER_SZ /* load time option */
/* maximum outstanding requests, write() yields EDOM if exceeded */
-#define SG_MAX_QUEUE 16
+#define SG_MAX_QUEUE 128
#define SG_BIG_BUFF SG_DEF_RESERVED_SIZE /* for backward compatibility */
@@ -391,11 +391,11 @@ static struct scsi_host_template tcm_loop_driver_template = {
.eh_device_reset_handler = NULL,
.eh_host_reset_handler = NULL,
.bios_param = NULL,
- .can_queue = 1,
+ .can_queue = 1024,
.this_id = -1,
.sg_tablesize = 256,
- .cmd_per_lun = 1,
- .max_sectors = 128,
+ .cmd_per_lun = 1024,
+ .max_sectors = 256,
.use_clustering = DISABLE_CLUSTERING,
.module = THIS_MODULE,
};