Linux Virtualization - Jun 2014 - [RFC PATCH 2/2] block: virtio-blk: support multi virt queues per virtio-blk device

On Sat, Jun 14, 2014 at 1:29 AM, Ming Lei <ming.lei at canonical.com>
wrote:
> Firstly this patch supports more than one virtual queues for virtio-blk
> device.
>
> Secondly this patch maps the virtual queue to blk-mq's hardware queue.
>
> With this approach, both scalability and performance problem can be
improved.
>
> Signed-off-by: Ming Lei <ming.lei at canonical.com>
> ---
>  drivers/block/virtio_blk.c |   75
++++++++++++++++++++++++++++++++------------
>  1 file changed, 55 insertions(+), 20 deletions(-)
>
> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
> index f63d358..e0d077d 100644
> --- a/drivers/block/virtio_blk.c
> +++ b/drivers/block/virtio_blk.c
> @@ -16,6 +16,8 @@
>
>  #define PART_BITS 4
>
> +#define MAX_NUM_VQ 16
It would be nice to allocate virtqueues dynamically instead of
hardcoding the limit.  virtio-scsi also allocates virtqueues
dynamically.

Stefan

On Tue, Jun 17, 2014 at 10:40 AM, Stefan Hajnoczi <stefanha at gmail.com>
wrote:
> On Sat, Jun 14, 2014 at 1:29 AM, Ming Lei <ming.lei at canonical.com>
wrote:
>> Firstly this patch supports more than one virtual queues for virtio-blk
>> device.
>>
>> Secondly this patch maps the virtual queue to blk-mq's hardware
queue.
>>
>> With this approach, both scalability and performance problem can be
improved.
>>
>> Signed-off-by: Ming Lei <ming.lei at canonical.com>
>> ---
>>  drivers/block/virtio_blk.c |   75
++++++++++++++++++++++++++++++++------------
>>  1 file changed, 55 insertions(+), 20 deletions(-)
>>
>> diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
>> index f63d358..e0d077d 100644
>> --- a/drivers/block/virtio_blk.c
>> +++ b/drivers/block/virtio_blk.c
>> @@ -16,6 +16,8 @@
>>
>>  #define PART_BITS 4
>>
>> +#define MAX_NUM_VQ 16
>
> It would be nice to allocate virtqueues dynamically instead of
> hardcoding the limit.  virtio-scsi also allocates virtqueues
> dynamically.
virtio-scsi may have lots of LUN, but virtio-blk only has one disk
which needn't lots of hardware queues.

Also it doesn't matter since it isn't part of ABI.

If change on virtio_blk_config is agreed, both host side and
guest side can choose to support dynamic length or pre-defined
length freely.

Thanks,
--
Ming Lei

Il 17/06/2014 17:50, Ming Lei ha scritto:
>> > It would be nice to allocate virtqueues dynamically instead of
>> > hardcoding the limit.  virtio-scsi also allocates virtqueues
>> > dynamically.
> virtio-scsi may have lots of LUN, but virtio-blk only has one disk
> which needn't lots of hardware queues.
If you want to do queue steering based on the guest VCPU number, the 
number of queues must be = to the number of VCPUs shouldn't it?

I tried using a divisor of the number of VCPUs, but couldn't get the 
block layer to deliver interrupts to the right VCPU.

Paolo