search for: virtqueue_napi_complet

...b.ntt.co.jp> --- drivers/net/virtio_net.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 19a985e..c0db48d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -261,9 +261,12 @@ static void virtqueue_napi_complete(struct napi_struct *napi, int opaque; opaque = virtqueue_enable_cb_prepare(vq); - if (napi_complete_done(napi, processed) && - unlikely(virtqueue_poll(vq, opaque))) - virtqueue_napi_schedule(napi, vq); + if (napi_complete_done(napi, processed)) { + if (unlikely(virtqueue_poll(v...

...b.ntt.co.jp> --- drivers/net/virtio_net.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 19a985e..c0db48d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -261,9 +261,12 @@ static void virtqueue_napi_complete(struct napi_struct *napi, int opaque; opaque = virtqueue_enable_cb_prepare(vq); - if (napi_complete_done(napi, processed) && - unlikely(virtqueue_poll(vq, opaque))) - virtqueue_napi_schedule(napi, vq); + if (napi_complete_done(napi, processed)) { + if (unlikely(virtqueue_poll(v...

...api_struct *napi, int budget) > struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); > > __netif_tx_lock(txq, raw_smp_processor_id()); > - free_old_xmit_skbs(sq); > + free_old_xmit_skbs(sq, txq, true); > __netif_tx_unlock(txq); > > virtqueue_napi_complete(napi, sq->vq, 0); > @@ -1505,13 +1509,15 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) > struct send_queue *sq = &vi->sq[qnum]; > int err; > struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); > - bool kick = !skb->xmit_mo...

...api_struct *napi, int budget) > struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); > > __netif_tx_lock(txq, raw_smp_processor_id()); > - free_old_xmit_skbs(sq); > + free_old_xmit_skbs(sq, txq, true); > __netif_tx_unlock(txq); > > virtqueue_napi_complete(napi, sq->vq, 0); > @@ -1505,13 +1509,15 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) > struct send_queue *sq = &vi->sq[qnum]; > int err; > struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum); > - bool kick = !skb->xmit_mo...

From: Willem de Bruijn <willemb at google.com> Add napi for virtio-net transmit completion processing. Based on previous patchsets by Jason Wang: [RFC V7 PATCH 0/7] enable tx interrupts for virtio-net http://lkml.iu.edu/hypermail/linux/kernel/1505.3/00245.html Changes: RFC -> v1: - dropped vhost interrupt moderation patch: not needed and likely expensive at light

From: Willem de Bruijn <willemb at google.com> Add napi for virtio-net transmit completion processing. Based on previous patchsets by Jason Wang: [RFC V7 PATCH 0/7] enable tx interrupts for virtio-net http://lkml.iu.edu/hypermail/linux/kernel/1505.3/00245.html Changes: RFC -> v1: - dropped vhost interrupt moderation patch: not needed and likely expensive at light

...N + ETH_DATA_LEN) > @@ -86,6 +87,8 @@ struct send_queue { > > /* Name of the send queue: output.$index */ > char name[40]; > + > + struct napi_struct napi; > }; > > /* Internal representation of a receive virtqueue */ > @@ -262,12 +265,16 @@ static void virtqueue_napi_complete(struct napi_struct *napi, > static void skb_xmit_done(struct virtqueue *vq) > { > struct virtnet_info *vi = vq->vdev->priv; > + struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; > > /* Suppress further interrupts. */ > virtqueue_disable_cb(vq);...

From: Willem de Bruijn <willemb at google.com> Add napi for virtio-net transmit completion processing. Changes: v1 -> v2: - disable by default - disable unless affinity_hint_set because cache misses add up to a third higher cycle cost, e.g., in TCP_RR tests. This is not limited to the patch that enables tx completion cleaning in rx napi. - use trylock to

From: Willem de Bruijn <willemb at google.com> Add napi for virtio-net transmit completion processing. Changes: v1 -> v2: - disable by default - disable unless affinity_hint_set because cache misses add up to a third higher cycle cost, e.g., in TCP_RR tests. This is not limited to the patch that enables tx completion cleaning in rx napi. - use trylock to

...T_DRIVER_VERSION "1.0.0" +static const u32 ethtool_coalesce_napi_mask = (1UL << 10); + static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, @@ -1444,7 +1446,10 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) virtqueue_napi_complete(napi, sq->vq, 0); - if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) + /* Check napi.weight to avoid tx stall since it could be set + * to zero by ethtool after skb_xmit_done(). + */ + if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS || !sq->napi.weight) netif_tx_wake_queue(txq);...

...T_DRIVER_VERSION "1.0.0" +static const u32 ethtool_coalesce_napi_mask = (1UL << 10); + static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, @@ -1444,7 +1446,10 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) virtqueue_napi_complete(napi, sq->vq, 0); - if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) + /* Check napi.weight to avoid tx stall since it could be set + * to zero by ethtool after skb_xmit_done(). + */ + if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS || !sq->napi.weight) netif_tx_wake_queue(txq);...

...overhead, esp for UDP. > @@ -86,6 +87,8 @@ struct send_queue { > > /* Name of the send queue: output.$index */ > char name[40]; > + > + struct napi_struct napi; > }; > > /* Internal representation of a receive virtqueue */ > @@ -262,12 +265,16 @@ static void virtqueue_napi_complete(struct napi_struct *napi, > static void skb_xmit_done(struct virtqueue *vq) > { > struct virtnet_info *vi = vq->vdev->priv; > + struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; > > /* Suppress further interrupts. */ > virtqueue_disable_cb(vq); >...

...config. */ #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) @@ -86,6 +87,8 @@ struct send_queue { /* Name of the send queue: output.$index */ char name[40]; + + struct napi_struct napi; }; /* Internal representation of a receive virtqueue */ @@ -262,12 +265,16 @@ static void virtqueue_napi_complete(struct napi_struct *napi, static void skb_xmit_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; + struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; /* Suppress further interrupts. */ virtqueue_disable_cb(vq); - /* We were probably waiting for more...

...t;> struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); >>> __netif_tx_lock(txq, raw_smp_processor_id()); >>> - free_old_xmit_skbs(sq); >>> + free_old_xmit_skbs(sq, txq, true); >>> __netif_tx_unlock(txq); >>> virtqueue_napi_complete(napi, sq->vq, 0); >>> @@ -1505,13 +1509,15 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) >>> struct send_queue *sq = &vi->sq[qnum]; >>> int err; >>> struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);...

...t;> struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); >>> __netif_tx_lock(txq, raw_smp_processor_id()); >>> - free_old_xmit_skbs(sq); >>> + free_old_xmit_skbs(sq, txq, true); >>> __netif_tx_unlock(txq); >>> virtqueue_napi_complete(napi, sq->vq, 0); >>> @@ -1505,13 +1509,15 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) >>> struct send_queue *sq = &vi->sq[qnum]; >>> int err; >>> struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);...

Now that we have brought the virtio overhead way down with a fast packed ring implementation, we seem to be actually observing TCP drops indicative of bufferbloat. So let's try to enable TSQ. Note: it isn't clear that the default pacing is great for the virt usecase. It's worth trying to play with sk_pacing_shift_update to see what happens. For this reason, and for a more important

...config. */ #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) @@ -86,6 +87,8 @@ struct send_queue { /* Name of the send queue: output.$index */ char name[40]; + + struct napi_struct napi; }; /* Internal representation of a receive virtqueue */ @@ -262,12 +265,16 @@ static void virtqueue_napi_complete(struct napi_struct *napi, static void skb_xmit_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; + struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; /* Suppress further interrupts. */ virtqueue_disable_cb(vq); - /* We were probably waiting for more...

...config. */ #define GOOD_PACKET_LEN (ETH_HLEN + VLAN_HLEN + ETH_DATA_LEN) @@ -86,6 +87,8 @@ struct send_queue { /* Name of the send queue: output.$index */ char name[40]; + + struct napi_struct napi; }; /* Internal representation of a receive virtqueue */ @@ -262,12 +265,16 @@ static void virtqueue_napi_complete(struct napi_struct *napi, static void skb_xmit_done(struct virtqueue *vq) { struct virtnet_info *vi = vq->vdev->priv; + struct napi_struct *napi = &vi->sq[vq2txq(vq)].napi; /* Suppress further interrupts. */ virtqueue_disable_cb(vq); - /* We were probably waiting for more...

From: Willem de Bruijn <willemb at google.com> Add napi for virtio-net transmit completion processing. Changes: v2 -> v3: - convert __netif_tx_trylock to __netif_tx_lock on tx napi poll ensure that the handler always cleans, to avoid deadlock - unconditionally clean in start_xmit avoid adding an unnecessary "if (use_napi)" branch - remove

From: Willem de Bruijn <willemb at google.com> Add napi for virtio-net transmit completion processing. Changes: v2 -> v3: - convert __netif_tx_trylock to __netif_tx_lock on tx napi poll ensure that the handler always cleans, to avoid deadlock - unconditionally clean in start_xmit avoid adding an unnecessary "if (use_napi)" branch - remove