Re: [PATCH net-next RFC 4/4] virtio-net: clean tx descriptors from rx napi
>> +static void virtnet_poll_cleantx(struct receive_queue *rq)
>> +{
>> + struct virtnet_info *vi = rq->vq->vdev->priv;
>> + unsigned int index = vq2rxq(rq->vq);
>> + struct send_queue *sq = &vi->sq[index];
>> + struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
>> +
>> + __netif_tx_lock(txq, smp_processor_id());
>> + free_old_xmit_skbs(sq, sq->napi.weight);
>> + __netif_tx_unlock(txq);
>
>
> Should we check tx napi weight here? Or this was treated as an independent
> optimization?
Good point. This was not intended to run in no-napi mode as is.
With interrupts disabled most of the time in that mode, I don't
expect it to be worthwhile using in that case. I'll add the check
for sq->napi.weight != 0.
>> +
>> + if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
>> + netif_wake_subqueue(vi->dev, vq2txq(sq->vq));
>> +}
>> +
>> static int virtnet_poll(struct napi_struct *napi, int budget)
>> {
>> struct receive_queue *rq =
>> @@ -1039,6 +1056,8 @@ static int virtnet_poll(struct napi_struct *napi,
>> int budget)
>> received = virtnet_receive(rq, budget);
>> + virtnet_poll_cleantx(rq);
>> +
>
>
> Better to do the before virtnet_receive() consider refill may allocate
> memory for rx buffers.
Will do.
> Btw, if this is proved to be more efficient. In the future we may consider
> to:
>
> 1) use a single interrupt for both rx and tx
> 2) use a single napi to handle both rx and tx
Agreed, I think that's sensible.
Re: [PATCH net-next RFC 4/4] virtio-net: clean tx descriptors from rx napi
On Mon, Mar 6, 2017 at 12:43 PM, Willem de Bruijn
wrote:
>>> +static void virtnet_poll_cleantx(struct receive_queue *rq)
>>> +{
>>> + struct virtnet_info *vi = rq->vq->vdev->priv;
>>> + unsigned int index = vq2rxq(rq->vq);
>>> + struct send_queue *sq = &vi->sq[index];
>>> + struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
>>> +
>>> + __netif_tx_lock(txq, smp_processor_id());
>>> + free_old_xmit_skbs(sq, sq->napi.weight);
>>> + __netif_tx_unlock(txq);
>>
>>
>> Should we check tx napi weight here? Or this was treated as an independent
>> optimization?
>
> Good point. This was not intended to run in no-napi mode as is.
> With interrupts disabled most of the time in that mode, I don't
> expect it to be worthwhile using in that case. I'll add the check
> for sq->napi.weight != 0.
I'm wrong here. Rx interrupts are not disabled, of course. It is
probably worth benchmarking, then.
Re: [PATCH net-next RFC 4/4] virtio-net: clean tx descriptors from rx napi
On 2017年03月03日 22:39, Willem de Bruijn wrote:
From: Willem de Bruijn
Amortize the cost of virtual interrupts by doing both rx and tx work
on reception of a receive interrupt. Together VIRTIO_F_EVENT_IDX and
vhost interrupt moderation, this suppresses most explicit tx
completion interrupts for bidirectional workloads.
Signed-off-by: Willem de Bruijn
---
drivers/net/virtio_net.c | 19 +++
1 file changed, 19 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9a9031640179..21c575127d50 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1031,6 +1031,23 @@ static int virtnet_receive(struct receive_queue *rq, int
budget)
return received;
}
+static unsigned int free_old_xmit_skbs(struct send_queue *sq, int budget);
+
+static void virtnet_poll_cleantx(struct receive_queue *rq)
+{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ unsigned int index = vq2rxq(rq->vq);
+ struct send_queue *sq = &vi->sq[index];
+ struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
+
+ __netif_tx_lock(txq, smp_processor_id());
+ free_old_xmit_skbs(sq, sq->napi.weight);
+ __netif_tx_unlock(txq);
Should we check tx napi weight here? Or this was treated as an
independent optimization?
+
+ if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
+ netif_wake_subqueue(vi->dev, vq2txq(sq->vq));
+}
+
static int virtnet_poll(struct napi_struct *napi, int budget)
{
struct receive_queue *rq =
@@ -1039,6 +1056,8 @@ static int virtnet_poll(struct napi_struct *napi, int
budget)
received = virtnet_receive(rq, budget);
+ virtnet_poll_cleantx(rq);
+
Better to do the before virtnet_receive() consider refill may allocate
memory for rx buffers.
Btw, if this is proved to be more efficient. In the future we may
consider to:
1) use a single interrupt for both rx and tx
2) use a single napi to handle both rx and tx
Thanks
/* Out of packets? */
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
[PATCH net-next RFC 4/4] virtio-net: clean tx descriptors from rx napi
From: Willem de Bruijn
Amortize the cost of virtual interrupts by doing both rx and tx work
on reception of a receive interrupt. Together VIRTIO_F_EVENT_IDX and
vhost interrupt moderation, this suppresses most explicit tx
completion interrupts for bidirectional workloads.
Signed-off-by: Willem de Bruijn
---
drivers/net/virtio_net.c | 19 +++
1 file changed, 19 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9a9031640179..21c575127d50 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1031,6 +1031,23 @@ static int virtnet_receive(struct receive_queue *rq, int
budget)
return received;
}
+static unsigned int free_old_xmit_skbs(struct send_queue *sq, int budget);
+
+static void virtnet_poll_cleantx(struct receive_queue *rq)
+{
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ unsigned int index = vq2rxq(rq->vq);
+ struct send_queue *sq = &vi->sq[index];
+ struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index);
+
+ __netif_tx_lock(txq, smp_processor_id());
+ free_old_xmit_skbs(sq, sq->napi.weight);
+ __netif_tx_unlock(txq);
+
+ if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
+ netif_wake_subqueue(vi->dev, vq2txq(sq->vq));
+}
+
static int virtnet_poll(struct napi_struct *napi, int budget)
{
struct receive_queue *rq =
@@ -1039,6 +1056,8 @@ static int virtnet_poll(struct napi_struct *napi, int
budget)
received = virtnet_receive(rq, budget);
+ virtnet_poll_cleantx(rq);
+
/* Out of packets? */
if (received < budget)
virtqueue_napi_complete(napi, rq->vq, received);
--
2.12.0.rc1.440.g5b76565f74-goog
