On Wed 22 Aug 2012 10:13:44 PM CST, Paolo Bonzini wrote:
Il 22/08/2012 15:13, Stefan Hajnoczi ha scritto:
http://lists.gnu.org/archive/html/qemu-devel/2010-12/msg01741.html
"This is a real problem in practice. IE. the USB CD-ROM on this POWER7
blade limits transfers to 0x1e000 bytes for examp
On 08/21/2012 06:14 PM, Paolo Bonzini wrote:
Il 21/08/2012 11:52, Stefan Hajnoczi ha scritto:
Using /sys/dev/block or /sys/dev/char seems easier, and lets you
retrieve the parameters for block devices too.
what do you mean with "block devices"? Using "/dev/sda" instead of
"/dev/sg0"?
Yes
On Tue 21 Aug 2012 04:53:59 PM CST, Stefan Hajnoczi wrote:
On Tue, Aug 21, 2012 at 9:26 AM, Cong Meng wrote:
Each virtio scsi HBA has global request queue limits. But the passthrough
LUNs (scsi-generic) come from different host HBAs may have different request
queue limits. If the guest sends
On Tue 21 Aug 2012 04:48:17 PM CST, Paolo Bonzini wrote:
Il 21/08/2012 10:23, Cong Meng ha scritto:
+static void sg_get_queue_limits(BlockDriverState *bs, const char *filename)
+{
+DIR *ffs;
+struct dirent *d;
+char path[MAXPATHLEN];
+
+snprintf(path, MAXPATHLEN
by getting the per-LUN queue limits via the the
newly added virtio control request, then setting them properly.
Signed-off-by: Cong Meng
---
drivers/scsi/virtio_scsi.c | 113 +--
include/linux/virtio_scsi.h | 18 +++
2 files changed, 116 insertions
patch responses the newly added virtio control
queue request by returning the per-LUN queue limits.
Signed-off-by: Cong Meng
---
hw/virtio-scsi.c | 65 ++
1 files changed, 65 insertions(+), 0 deletions(-)
diff --git a/hw/virtio-scsi.c b/hw/virtio
This patch adds some queue limit parameters into block drive. And inits them
for sg block drive. Some interfaces are also added for accessing them.
Signed-off-by: Cong Meng
---
block/raw-posix.c | 58 +
block_int.h |4
patch adds a per-LUN parameter query via the control
queue, and defines some parameter query types. The driver can query and set the
needed per-LUN parameters if the device enables this feature.
Signed-off-by: Cong Meng
--
virtio-spec.lyx | 218
Correct the command names of opcode 0x85 and 0xa1, and calculate
their xfer size from CDB.
ChangeLog:
v2: For opcode 0xa1 on TYPE_ROM device, do not calc the xfer size
v3: Complete xfer calculation of all situations
Signed-off-by: Cong Meng
---
hw/scsi-bus.c | 90
On Wed 01 Aug 2012 05:42:08 PM CST, Paolo Bonzini wrote:
Il 01/08/2012 11:05, Cong Meng ha scritto:
+case ATA_PASSTHROUGH_12:
+if (dev->type != TYPE_ROM) {
+if ((buf[2] & 0x3) == 2) {
+cmd->xfer = buf[4] * dev-
Correct the command names of opcode 0x85 and 0xa1, and calculate
their xfer size from CDB.
ChangeLog:
v2: For opcode 0xa1 on TYPE_ROM device, do not calc the xfer size
Signed-off-by: Cong Meng
---
hw/scsi-bus.c | 19 ---
hw/scsi-defs.h |4 ++--
2 files changed, 18
, Paolo Bonzini wrote:
Il 01/08/2012 10:43, Cong Meng ha scritto:
Please make this conditional on the type _not_ being TYPE_ROM.
May I ask why cdrom device should be an exception?
Because CD-ROM devices do not support ATA PASSTHROUGH (the SAT standard
only describes direct access devices---type
On Wed 01 Aug 2012 04:20:28 PM CST, Paolo Bonzini wrote:
Il 01/08/2012 09:53, Cong Meng ha scritto:
Correct the command names of opcode 0x85 and 0xa1, and calculate
their xfer size from CDB.
Signed-off-by: Cong Meng
---
hw/scsi-bus.c | 17 ++---
hw/scsi-defs.h |4
Correct the command names of opcode 0x85 and 0xa1, and calculate
their xfer size from CDB.
Signed-off-by: Cong Meng
---
hw/scsi-bus.c | 17 ++---
hw/scsi-defs.h |4 ++--
2 files changed, 16 insertions(+), 5 deletions(-)
diff --git a/hw/scsi-bus.c b/hw/scsi-bus.c
index
Add two interfaces hotplug() and hot_unplug() to scsi bus info.
The embody scsi bus can implement these two interfaces to signal the HBA driver
of guest kernel to add/remove the scsi device in question.
Signed-off-by: Cong Meng
Signed-off-by: Sen Wang
---
hw/scsi-bus.c | 16
Add two interfaces hotplug() and hot_unplug() to scsi bus info.
The embody scsi bus can implement these two interfaces to signal the HBA driver
of guest kernel to add/remove the scsi device in question.
Signed-off-by: Cong Meng
Signed-off-by: Sen Wang
---
hw/scsi-bus.c | 16
Implement the hotplug() and hot_unplug() interfaces in virtio-scsi, by signal
the virtio_scsi.ko in guest kernel via event virtual queue.
The counterpart patch of virtio_scsi.ko will be sent soon in another thread.
Signed-off-by: Cong Meng
Signed-off-by: Sen Wang
---
hw/virtio-scsi.c | 72
These patches implement the hotplug support for virtio-scsi.
When a new device attaches/detaches to virtio-scsi bus via device_add/device_del
commands, the HBA driver in guest kernel will be signaled to add/remove the scsi
device.
Cong Meng (2):
scsi bus: introduce hotplug() and hot_unplug
On Wed, 2012-06-13 at 12:08 -0700, Nicholas A. Bellinger wrote:
> On Wed, 2012-06-13 at 18:13 +0800, mengcong wrote:
> > Hi folks, I did an IO performance test on the tcm-vhost scsi. I want to
> > share
> > the test result data here.
> >
> >
> > seq-readseq-write
e \
-device virtio-scsi-pci,id=mcbus \
-device scsi-disk,drive=sdb
there is only one scsi HBA.
/dev/sdb is the disk on which all tests have been done.
Is this what you want?
Cong Meng
> Stefan
>
20 matches
Mail list logo
