[dpdk-dev,v3] vhost: Expose virtio interrupt need on rte_vhost API

  Performance tests with the OVS DPDK datapath have shown 
that the tx throughput over a vhostuser port into a VM with 
an interrupt-based virtio driver is limited by the overhead
incurred by virtio interrupts. The OVS PMD spends up to 30% 
of its cycles in system calls kicking the eventfd. Also the core
running the vCPU is heavily loaded with generating the virtio
interrupts in KVM on the host and handling these interrupts
in the virtio-net driver in the guest. This limits the throughput
to about 500-700 Kpps with a single vCPU.

OVS is trying to address this issue by batching packets to a
vhostuser port for some time to limit the virtio interrupt 
frequency. With a 50 us batching period we have measured an
iperf3  throughput increase by 15% and a PMD utilization
decrease from 45% to 30%.

On the other hand, guests using virtio PMDs do not profit from
time-based tx batching. Instead they experience a 2-3%
performance penalty and an average latency increase of 
30-40 us. OVS therefore intends to apply time-based tx 
batching only for vhostuser tx queues that need to trigger
virtio interrupts.

Today this information is hidden inside the rte_vhost library
and not accessible to users of the API. This patch adds a
function to the API to query it.

Signed-off-by: Jan Scheurich <jan.scheurich@ericsson.com>

---

v2 -> v3:
	Fixed even more white-space errors and warnings
v1 -> v2:
	Fixed too long commit lines
	Fixed white-space errors and warnings

 lib/librte_vhost/rte_vhost.h | 12 ++++++++++++
 lib/librte_vhost/vhost.c     | 19 +++++++++++++++++++
 2 files changed, 31 insertions(+)
  

Friendly reminder: 
Could somebody please have a look at this patch now that the DPDK
summit is over?

Thanks, Jan

> -----Original Message-----
> From: Jan Scheurich
> Sent: Saturday, 23 September, 2017 22:32
> To: 'dev@dpdk.org' <dev@dpdk.org>
> Subject: [PATCH v3] vhost: Expose virtio interrupt need on rte_vhost API
> 
> Performance tests with the OVS DPDK datapath have shown
> that the tx throughput over a vhostuser port into a VM with
> an interrupt-based virtio driver is limited by the overhead
> incurred by virtio interrupts. The OVS PMD spends up to 30%
> of its cycles in system calls kicking the eventfd. Also the core
> running the vCPU is heavily loaded with generating the virtio
> interrupts in KVM on the host and handling these interrupts
> in the virtio-net driver in the guest. This limits the throughput
> to about 500-700 Kpps with a single vCPU.
> 
> OVS is trying to address this issue by batching packets to a
> vhostuser port for some time to limit the virtio interrupt
> frequency. With a 50 us batching period we have measured an
> iperf3  throughput increase by 15% and a PMD utilization
> decrease from 45% to 30%.
> 
> On the other hand, guests using virtio PMDs do not profit from
> time-based tx batching. Instead they experience a 2-3%
> performance penalty and an average latency increase of
> 30-40 us. OVS therefore intends to apply time-based tx
> batching only for vhostuser tx queues that need to trigger
> virtio interrupts.
> 
> Today this information is hidden inside the rte_vhost library
> and not accessible to users of the API. This patch adds a
> function to the API to query it.
> 
> Signed-off-by: Jan Scheurich <jan.scheurich@ericsson.com>
> 
> ---
> 
> v2 -> v3:
> 	Fixed even more white-space errors and warnings
> v1 -> v2:
> 	Fixed too long commit lines
> 	Fixed white-space errors and warnings
> 
>  lib/librte_vhost/rte_vhost.h | 12 ++++++++++++
>  lib/librte_vhost/vhost.c     | 19 +++++++++++++++++++
>  2 files changed, 31 insertions(+)
> 
> diff --git a/lib/librte_vhost/rte_vhost.h b/lib/librte_vhost/rte_vhost.h
> index 8c974eb..d62338b 100644
> --- a/lib/librte_vhost/rte_vhost.h
> +++ b/lib/librte_vhost/rte_vhost.h
> @@ -444,6 +444,18 @@ int rte_vhost_get_vhost_vring(int vid, uint16_t vring_idx,
>   */
>  uint32_t rte_vhost_rx_queue_count(int vid, uint16_t qid);
> 
> +/**
> + * Does the virtio driver request interrupts for a vhost tx queue?
> + *
> + * @param vid
> + *  vhost device ID
> + * @param qid
> + *  virtio queue index in mq case
> + * @return
> + *  1 if true, 0 if false
> + */
> +int rte_vhost_tx_interrupt_requested(int vid, uint16_t qid);
> +
>  #ifdef __cplusplus
>  }
>  #endif
> diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
> index 0b6aa1c..c6e636e 100644
> --- a/lib/librte_vhost/vhost.c
> +++ b/lib/librte_vhost/vhost.c
> @@ -503,3 +503,22 @@ struct virtio_net *
> 
>  	return *((volatile uint16_t *)&vq->avail->idx) - vq->last_avail_idx;
>  }
> +
> +int rte_vhost_tx_interrupt_requested(int vid, uint16_t qid)
> +{
> +	struct virtio_net *dev;
> +	struct vhost_virtqueue *vq;
> +
> +	dev = get_device(vid);
> +	if (dev == NULL)
> +		return 0;
> +
> +	vq = dev->virtqueue[qid];
> +	if (vq == NULL)
> +		return 0;
> +
> +	if (unlikely(vq->enabled == 0 || vq->avail == NULL))
> +		return 0;
> +
> +	return !(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT);
> +}
  

Adding maintainers to Cc

On Sat, Sep 23, 2017 at 08:31:37PM +0000, Jan Scheurich wrote:
[...]
>Today this information is hidden inside the rte_vhost library
>and not accessible to users of the API. This patch adds a
>function to the API to query it.

Since you add to the API please also document
it in doc/guides/prog_guide/vhost_lib.rst. 

Apart from that the patch looks good to me.

regards,
Jens
  

On Sat, Sep 23, 2017 at 08:31:37PM +0000, Jan Scheurich wrote:
...
> +int rte_vhost_tx_interrupt_requested(int vid, uint16_t qid)
> +{
> +	struct virtio_net *dev;
> +	struct vhost_virtqueue *vq;
> +
> +	dev = get_device(vid);
> +	if (dev == NULL)
> +		return 0;
> +
> +	vq = dev->virtqueue[qid];
> +	if (vq == NULL)
> +		return 0;
> +
> +	if (unlikely(vq->enabled == 0 || vq->avail == NULL))
> +		return 0;
> +
> +	return !(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT);

Two comments here:

- as you see, the flags is stored at vq->avail, which is stored at the
  shared memory. That means, the virtio driver could change the value
  at any time.

  That said, this API should not be intended to be invoked once. Then
  you have to invoke it repeatedly, which might be a bit costy.

- OTOH, you might want to try "rte_vhost_get_vhost_vring" API, which
  exposes the vq->avail, therefore, the interrupt flag is also exposed.

	--yliu