d/numam-dpdk
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

vhost: batch used descs chains write-back with packed ring

Browse Source 
Instead of writing back descriptors chains in order, let's
write the first chain flags last in order to improve batching.

Also, move the write barrier in logging cache sync, so that it
is done only when logging is enabled. It means there is now
one more barrier for split ring when logging is enabled.

With Kernel's pktgen benchmark, ~3% performance gain is measured.

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
This commit is contained in:
Maxime Coquelin 2018-12-20 17:47:55 +01:00 committed by Ferruh Yigit
parent 517ad3e018
commit b473ec1131
2 changed files with 18 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lib/librte_vhost/vhost.h
View File

@ -457,12 +457,9 @@ vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
!dev->log_base))
return;
log_base = (unsigned long *)(uintptr_t)dev->log_base;
rte_smp_wmb();
/*
* It is expected a write memory barrier has been issued
* before this function is called.
*/
log_base = (unsigned long *)(uintptr_t)dev->log_base;
for (i = 0; i < vq->log_cache_nb_elem; i++) {
struct log_cache_entry *elem = vq->log_cache + i;

19
lib/librte_vhost/virtio_net.c
View File

@ -97,6 +97,8 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
{
int i;
uint16_t used_idx = vq->last_used_idx;
uint16_t head_idx = vq->last_used_idx;
uint16_t head_flags = 0;
/* Split loop in two to save memory barriers */
for (i = 0; i < vq->shadow_used_idx; i++) {
@ -126,12 +128,17 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
flags &= ~VRING_DESC_F_AVAIL;
}
vq->desc_packed[vq->last_used_idx].flags = flags;
if (i > 0) {
vq->desc_packed[vq->last_used_idx].flags = flags;
vhost_log_cache_used_vring(dev, vq,
vhost_log_cache_used_vring(dev, vq,
vq->last_used_idx *
sizeof(struct vring_packed_desc),
sizeof(struct vring_packed_desc));
} else {
head_idx = vq->last_used_idx;
head_flags = flags;
}
vq->last_used_idx += vq->shadow_used_packed[i].count;
if (vq->last_used_idx >= vq->size) {
@ -140,7 +147,13 @@ flush_shadow_used_ring_packed(struct virtio_net *dev,
}
}
rte_smp_wmb();
vq->desc_packed[head_idx].flags = head_flags;
vhost_log_cache_used_vring(dev, vq,
head_idx *
sizeof(struct vring_packed_desc),
sizeof(struct vring_packed_desc));
vq->shadow_used_idx = 0;
vhost_log_cache_sync(dev, vq);
}