search for: vhost_rx_batch

...inux/if_tap.h> > #include <linux/if_vlan.h> > +#include <linux/skb_array.h> > +#include <linux/skbuff.h> > > #include <net/sock.h> > > @@ -85,6 +87,7 @@ struct vhost_net_ubuf_ref { > struct vhost_virtqueue *vq; > }; > > +#define VHOST_RX_BATCH 64 > struct vhost_net_virtqueue { > struct vhost_virtqueue vq; > size_t vhost_hlen; > @@ -99,6 +102,10 @@ struct vhost_net_virtqueue { > /* Reference counting for outstanding ubufs. > * Protected by vq mutex. Writers must also take device mutex. */ > struct vhost_ne...

...inux/if_tap.h> > #include <linux/if_vlan.h> > +#include <linux/skb_array.h> > +#include <linux/skbuff.h> > > #include <net/sock.h> > > @@ -85,6 +87,7 @@ struct vhost_net_ubuf_ref { > struct vhost_virtqueue *vq; > }; > > +#define VHOST_RX_BATCH 64 > struct vhost_net_virtqueue { > struct vhost_virtqueue vq; > size_t vhost_hlen; > @@ -99,6 +102,10 @@ struct vhost_net_virtqueue { > /* Reference counting for outstanding ubufs. > * Protected by vq mutex. Writers must also take device mutex. */ > struct vhost_ne...

...vlan.h> >> +#include <linux/skb_array.h> >> +#include <linux/skbuff.h> >> >> #include <net/sock.h> >> >> @@ -85,6 +87,7 @@ struct vhost_net_ubuf_ref { >> struct vhost_virtqueue *vq; >> }; >> >> +#define VHOST_RX_BATCH 64 >> struct vhost_net_virtqueue { >> struct vhost_virtqueue vq; >> size_t vhost_hlen; >> @@ -99,6 +102,10 @@ struct vhost_net_virtqueue { >> /* Reference counting for outstanding ubufs. >> * Protected by vq mutex. Writers must also take device mut...

...gt; >> >>> +{ >>> + if (rvq->rh != rvq->rt) >>> + goto out; >>> + >>> + rvq->rh = rvq->rt = 0; >>> + rvq->rt = skb_array_consume_batched_bh(rvq->rx_array, rvq->rxq, >>> + VHOST_RX_BATCH); >> A comment explaining why is is -bh would be helpful. > > Ok. > > Thanks Rethink about this. It looks like -bh is not needed in this case since no consumer run in bh. Thanks

...gt; >> >>> +{ >>> + if (rvq->rh != rvq->rt) >>> + goto out; >>> + >>> + rvq->rh = rvq->rt = 0; >>> + rvq->rt = skb_array_consume_batched_bh(rvq->rx_array, rvq->rxq, >>> + VHOST_RX_BATCH); >> A comment explaining why is is -bh would be helpful. > > Ok. > > Thanks Rethink about this. It looks like -bh is not needed in this case since no consumer run in bh. Thanks

...ret = total_len; goto out; } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 0d84de6..bec4109 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -118,6 +118,7 @@ struct vhost_net_virtqueue { struct ptr_ring *rx_ring; struct vhost_net_buf rxq; struct xdp_buff xdp[VHOST_RX_BATCH]; + struct vring_used_elem heads[VHOST_RX_BATCH]; }; struct vhost_net { @@ -511,7 +512,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, void *buf; int copied; - if (len < nvq->sock_hlen) + if (unlikely(len < nvq->sock_hlen)) return -EFAULT; if (SKB_D...

...won't access the used ring until used idx was advanced for several descriptors and since we advance used ring for every N packets, guest will only need to access used idx for every N packet since it can cache the used idx. To have a better interaction for both batch dequeuing and dpdk batching, VHOST_RX_BATCH was used as the maximum number of descriptors that could be batched. Test were done between two machines with 2.40GHz Intel(R) Xeon(R) CPU E5-2630 connected back to back through ixgbe. Traffic were generated on one remote ixgbe through MoonGen and measure the RX pps through testpmd in guest when d...

...likely(mergeable) ? UIO_MAXIOV : 1); /* On error, stop handling until the next kick. */ if (unlikely(headcount < 0)) @@ -862,12 +878,9 @@ static void handle_rx(struct vhost_net *net) vhost_discard_vq_desc(vq, headcount); goto out; } - nheads += headcount; - if (nheads > VHOST_RX_BATCH) { - vhost_add_used_and_signal_n(&net->dev, vq, vq->heads, - nheads); - nheads = 0; - } + nvq->done_idx += headcount; + if (nvq->done_idx > VHOST_RX_BATCH) + vhost_rx_signal_used(nvq); if (unlikely(vq_log)) vhost_log_write(vq, vq_log, log, vhost_len);...

...@@ #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> +#include <linux/skb_array.h> +#include <linux/skbuff.h> #include <net/sock.h> @@ -85,6 +87,7 @@ struct vhost_net_ubuf_ref { struct vhost_virtqueue *vq; }; +#define VHOST_RX_BATCH 64 struct vhost_net_virtqueue { struct vhost_virtqueue vq; size_t vhost_hlen; @@ -99,6 +102,10 @@ struct vhost_net_virtqueue { /* Reference counting for outstanding ubufs. * Protected by vq mutex. Writers must also take device mutex. */ struct vhost_net_ubuf_ref *ubufs; + struct skb_arr...

...st_net: introduce helper to initialize tx iov iter vhost_net: introduce vhost_exceeds_weight() vhost_net: introduce get_tx_bufs() vhost_net: introduce tx_can_batch() vhost_net: split out datacopy logic vhost_net: rename vhost_rx_signal_used() to vhost_net_signal_used() vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH vhost_net: batch update used ring for datacopy TX drivers/vhost/net.c | 249 +++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 179 insertions(+), 70 deletions(-) -- 2.7.4

...st_net: introduce helper to initialize tx iov iter vhost_net: introduce vhost_exceeds_weight() vhost_net: introduce get_tx_bufs() vhost_net: introduce tx_can_batch() vhost_net: split out datacopy logic vhost_net: rename vhost_rx_signal_used() to vhost_net_signal_used() vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH vhost_net: batch update used ring for datacopy TX drivers/vhost/net.c | 249 +++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 179 insertions(+), 70 deletions(-) -- 2.7.4

...; + if (rvq->rh != rvq->rt) >>>>> + goto out; >>>>> + >>>>> + rvq->rh = rvq->rt = 0; >>>>> + rvq->rt = skb_array_consume_batched_bh(rvq->rx_array, rvq->rxq, >>>>> + VHOST_RX_BATCH); >>>> A comment explaining why is is -bh would be helpful. >>> Ok. >>> >>> Thanks >> Rethink about this. It looks like -bh is not needed in this case since >> no consumer run in bh. > In that case do we need other variants of "ptr_ring_con...

...; + if (rvq->rh != rvq->rt) >>>>> + goto out; >>>>> + >>>>> + rvq->rh = rvq->rt = 0; >>>>> + rvq->rt = skb_array_consume_batched_bh(rvq->rx_array, rvq->rxq, >>>>> + VHOST_RX_BATCH); >>>> A comment explaining why is is -bh would be helpful. >>> Ok. >>> >>> Thanks >> Rethink about this. It looks like -bh is not needed in this case since >> no consumer run in bh. > In that case do we need other variants of "ptr_ring_con...

...used in guest for better numbers. Thanks > >> Please review. >> >> Jason Wang (5): >> vhost: split out ring head fetching logic >> vhost: introduce helper to prefetch desc index >> vhost: introduce vhost_add_used_idx() >> vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH >> vhost_net: basic tx virtqueue batched processing >> >> drivers/vhost/net.c | 221 ++++++++++++++++++++++++++++---------------------- >> drivers/vhost/vhost.c | 165 +++++++++++++++++++++++++++++++------ >> drivers/vhost/vhost.h | 9 ++ &...

...used in guest for better numbers. Thanks > >> Please review. >> >> Jason Wang (5): >> vhost: split out ring head fetching logic >> vhost: introduce helper to prefetch desc index >> vhost: introduce vhost_add_used_idx() >> vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH >> vhost_net: basic tx virtqueue batched processing >> >> drivers/vhost/net.c | 221 ++++++++++++++++++++++++++++---------------------- >> drivers/vhost/vhost.c | 165 +++++++++++++++++++++++++++++++------ >> drivers/vhost/vhost.h | 9 ++ &...

Hi all: This series tries to implement rx batching for vhost-net. This is done by batching the dequeuing from skb_array which was exported by underlayer socket and pass the sbk back through msg_control to finish userspace copying. Tests shows at most 19% improvment on rx pps. Please review. Thanks Jason Wang (8): ptr_ring: introduce batch dequeuing skb_array: introduce batch dequeuing

Hi all: This series tries to implement rx batching for vhost-net. This is done by batching the dequeuing from skb_array which was exported by underlayer socket and pass the sbk back through msg_control to finish userspace copying. Tests shows at most 19% improvment on rx pps. Please review. Thanks Jason Wang (8): ptr_ring: introduce batch dequeuing skb_array: introduce batch dequeuing

Hi all: We do not support XDP batching for TUN since it can only receive one packet a time from vhost_net. This series tries to remove this limitation by: - introduce a TUN specific msg_control that can hold a pointer to an array of XDP buffs - try copy and build XDP buff in vhost_net - store XDP buffs in an array and submit them once for every N packets from vhost_net - since TUN can only

...ds to speed up used ring updating and improve the cache utilization. Test shows about ~22% improvement in tx pss. Please review. Jason Wang (5): vhost: split out ring head fetching logic vhost: introduce helper to prefetch desc index vhost: introduce vhost_add_used_idx() vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH vhost_net: basic tx virtqueue batched processing drivers/vhost/net.c | 221 ++++++++++++++++++++++++++++---------------------- drivers/vhost/vhost.c | 165 +++++++++++++++++++++++++++++++------ drivers/vhost/vhost.h | 9 ++ 3 files changed, 270 insertions(+), 125 deletion...

...ds to speed up used ring updating and improve the cache utilization. Test shows about ~22% improvement in tx pss. Please review. Jason Wang (5): vhost: split out ring head fetching logic vhost: introduce helper to prefetch desc index vhost: introduce vhost_add_used_idx() vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH vhost_net: basic tx virtqueue batched processing drivers/vhost/net.c | 221 ++++++++++++++++++++++++++++---------------------- drivers/vhost/vhost.c | 165 +++++++++++++++++++++++++++++++------ drivers/vhost/vhost.h | 9 ++ 3 files changed, 270 insertions(+), 125 deletion...