Displaying 20 results from an estimated 131 matches for "zcopy_used".
2013 Sep 04
2
[PATCH V3 4/6] vhost_net: determine whether or not to use zerocopy at one time
On Mon, Sep 02, 2013 at 04:40:59PM +0800, Jason Wang wrote:
> Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
> upend_idx != done_idx we still set zcopy_used to true and rollback this choice
> later. This could be avoided by determining zerocopy once by checking all
> conditions at one time before.
>
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
> drivers/vhost/net.c | 47 ++++++++++++++++++++---------------------...
2013 Sep 04
2
[PATCH V3 4/6] vhost_net: determine whether or not to use zerocopy at one time
On Mon, Sep 02, 2013 at 04:40:59PM +0800, Jason Wang wrote:
> Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
> upend_idx != done_idx we still set zcopy_used to true and rollback this choice
> later. This could be avoided by determining zerocopy once by checking all
> conditions at one time before.
>
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
> drivers/vhost/net.c | 47 ++++++++++++++++++++---------------------...
2013 Sep 23
2
[PATCH V3 4/6] vhost_net: determine whether or not to use zerocopy at one time
...10:54:44AM +0800, Jason Wang wrote:
> On 09/04/2013 07:59 PM, Michael S. Tsirkin wrote:
> > On Mon, Sep 02, 2013 at 04:40:59PM +0800, Jason Wang wrote:
> >> Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
> >> upend_idx != done_idx we still set zcopy_used to true and rollback this choice
> >> later. This could be avoided by determining zerocopy once by checking all
> >> conditions at one time before.
> >>
> >> Signed-off-by: Jason Wang <jasowang at redhat.com>
> >> ---
> >> drivers/vhost/n...
2013 Sep 23
2
[PATCH V3 4/6] vhost_net: determine whether or not to use zerocopy at one time
...10:54:44AM +0800, Jason Wang wrote:
> On 09/04/2013 07:59 PM, Michael S. Tsirkin wrote:
> > On Mon, Sep 02, 2013 at 04:40:59PM +0800, Jason Wang wrote:
> >> Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
> >> upend_idx != done_idx we still set zcopy_used to true and rollback this choice
> >> later. This could be avoided by determining zerocopy once by checking all
> >> conditions at one time before.
> >>
> >> Signed-off-by: Jason Wang <jasowang at redhat.com>
> >> ---
> >> drivers/vhost/n...
2013 Aug 30
1
[PATCH V2 4/6] vhost_net: determine whether or not to use zerocopy at one time
Hello.
On 08/30/2013 08:29 AM, Jason Wang wrote:
> Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
> upend_idx != done_idx we still set zcopy_used to true and rollback this choice
> later. This could be avoided by determine zerocopy once by checking all
> conditions at one time before.
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
> drivers/vhost/net.c | 46 +++++++++++++++++++---------------------------...
2013 Aug 30
1
[PATCH V2 4/6] vhost_net: determine whether or not to use zerocopy at one time
Hello.
On 08/30/2013 08:29 AM, Jason Wang wrote:
> Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
> upend_idx != done_idx we still set zcopy_used to true and rollback this choice
> later. This could be avoided by determine zerocopy once by checking all
> conditions at one time before.
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
> drivers/vhost/net.c | 46 +++++++++++++++++++---------------------------...
2017 Sep 28
1
[PATCH net-next RFC 5/5] vhost_net: basic tx virtqueue batched processing
> @@ -461,6 +460,7 @@ static void handle_tx(struct vhost_net *net)
> struct socket *sock;
> struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
> bool zcopy, zcopy_used;
> + int i, batched = VHOST_NET_BATCH;
>
> mutex_lock(&vq->mutex);
> sock = vq->private_data;
> @@ -475,6 +475,12 @@ static void handle_tx(struct vhost_net *net)
> hdr_size = nvq->vhost_hlen;
> zcopy = nvq->ubufs;
>
>...
2017 Sep 28
1
[PATCH net-next RFC 5/5] vhost_net: basic tx virtqueue batched processing
> @@ -461,6 +460,7 @@ static void handle_tx(struct vhost_net *net)
> struct socket *sock;
> struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
> bool zcopy, zcopy_used;
> + int i, batched = VHOST_NET_BATCH;
>
> mutex_lock(&vq->mutex);
> sock = vq->private_data;
> @@ -475,6 +475,12 @@ static void handle_tx(struct vhost_net *net)
> hdr_size = nvq->vhost_hlen;
> zcopy = nvq->ubufs;
>
>...
2013 Aug 30
0
[PATCH V2 4/6] vhost_net: determine whether or not to use zerocopy at one time
Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
upend_idx != done_idx we still set zcopy_used to true and rollback this choice
later. This could be avoided by determine zerocopy once by checking all
conditions at one time before.
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
drivers/vhost/net.c | 46 +++++++++++++++++++---------------------------
1 files changed, 19 inser...
2013 Sep 02
0
[PATCH V3 4/6] vhost_net: determine whether or not to use zerocopy at one time
Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
upend_idx != done_idx we still set zcopy_used to true and rollback this choice
later. This could be avoided by determining zerocopy once by checking all
conditions at one time before.
Signed-off-by: Jason Wang <jasowang at redhat.com>
---
drivers/vhost/net.c | 47 ++++++++++++++++++++---------------------------
1 files changed, 20 in...
2017 Sep 22
0
[PATCH net-next RFC 5/5] vhost_net: basic tx virtqueue batched processing
..., *heads = vq->heads;
unsigned out, in;
- int head;
+ int avails, head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
@@ -461,6 +460,7 @@ static void handle_tx(struct vhost_net *net)
struct socket *sock;
struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
bool zcopy, zcopy_used;
+ int i, batched = VHOST_NET_BATCH;
mutex_lock(&vq->mutex);
sock = vq->private_data;
@@ -475,6 +475,12 @@ static void handle_tx(struct vhost_net *net)
hdr_size = nvq->vhost_hlen;
zcopy = nvq->ubufs;
+ /* Disable zerocopy batched fetching for simplicity */
+ if (zcopy) {...
2013 Sep 05
0
[PATCH V3 4/6] vhost_net: determine whether or not to use zerocopy at one time
On 09/04/2013 07:59 PM, Michael S. Tsirkin wrote:
> On Mon, Sep 02, 2013 at 04:40:59PM +0800, Jason Wang wrote:
>> Currently, even if the packet length is smaller than VHOST_GOODCOPY_LEN, if
>> upend_idx != done_idx we still set zcopy_used to true and rollback this choice
>> later. This could be avoided by determining zerocopy once by checking all
>> conditions at one time before.
>>
>> Signed-off-by: Jason Wang <jasowang at redhat.com>
>> ---
>> drivers/vhost/net.c | 47 ++++++++++++++++++...
2018 May 21
0
[RFC PATCH net-next 04/12] vhost_net: split out datacopy logic
...)
{
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
struct vhost_virtqueue *vq = &nvq->vq;
@@ -512,7 +598,7 @@ static void handle_tx(struct vhost_net *net)
size_t hdr_size;
struct socket *sock;
struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
- bool zcopy, zcopy_used;
+ bool zcopy_used;
int sent_pkts = 0;
mutex_lock(&vq->mutex);
@@ -527,13 +613,10 @@ static void handle_tx(struct vhost_net *net)
vhost_net_disable_vq(net, vq);
hdr_size = nvq->vhost_hlen;
- zcopy = nvq->ubufs;
for (;;) {
/* Release DMAs done buffers first */
- if (...
2013 Sep 02
8
[PATCH V3 0/6] vhost code cleanup and minor enhancement
This series tries to unify and simplify vhost codes especially for
zerocopy. With this series, 5% - 10% improvement for per cpu throughput were
seen during netperf guest sending test.
Plase review.
Changes from V2:
- Typo fixes and code style fix
- Add performance gain in the commit log of patch 2/6
- Retest the update the result in patch 6/6
Changes from V1:
- Fix the zerocopy enabling check
2013 Sep 02
8
[PATCH V3 0/6] vhost code cleanup and minor enhancement
This series tries to unify and simplify vhost codes especially for
zerocopy. With this series, 5% - 10% improvement for per cpu throughput were
seen during netperf guest sending test.
Plase review.
Changes from V2:
- Typo fixes and code style fix
- Add performance gain in the commit log of patch 2/6
- Retest the update the result in patch 6/6
Changes from V1:
- Fix the zerocopy enabling check
2017 Sep 26
2
[PATCH net-next RFC 5/5] vhost_net: basic tx virtqueue batched processing
...> - int head;
> + int avails, head;
> struct msghdr msg = {
> .msg_name = NULL,
> .msg_namelen = 0,
> @@ -461,6 +460,7 @@ static void handle_tx(struct vhost_net *net)
> struct socket *sock;
> struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
> bool zcopy, zcopy_used;
> + int i, batched = VHOST_NET_BATCH;
>
> mutex_lock(&vq->mutex);
> sock = vq->private_data;
> @@ -475,6 +475,12 @@ static void handle_tx(struct vhost_net *net)
> hdr_size = nvq->vhost_hlen;
> zcopy = nvq->ubufs;
>
> + /* Disable zerocopy batc...
2017 Sep 26
2
[PATCH net-next RFC 5/5] vhost_net: basic tx virtqueue batched processing
...> - int head;
> + int avails, head;
> struct msghdr msg = {
> .msg_name = NULL,
> .msg_namelen = 0,
> @@ -461,6 +460,7 @@ static void handle_tx(struct vhost_net *net)
> struct socket *sock;
> struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
> bool zcopy, zcopy_used;
> + int i, batched = VHOST_NET_BATCH;
>
> mutex_lock(&vq->mutex);
> sock = vq->private_data;
> @@ -475,6 +475,12 @@ static void handle_tx(struct vhost_net *net)
> hdr_size = nvq->vhost_hlen;
> zcopy = nvq->ubufs;
>
> + /* Disable zerocopy batc...
2017 Sep 01
2
[PATCH net-next] virtio-net: invoke zerocopy callback on xmit path if no tx napi
...hich I cannot yet explain.
>>
>> Running two threads in a guest, each with a udp socket, each
>> sending up to 100 datagrams, or until EAGAIN, every msec.
>>
>> Sender A sends 1B datagrams.
>> Sender B sends VHOST_GOODCOPY_LEN, which is enough
>> to trigger zcopy_used in vhost net.
>>
>> A local receive process on the host receives both flows. To avoid
>> a deep copy when looping the packet onto the receive path,
>> changed skb_orphan_frags_rx to always return false (gross hack).
>>
>> The flow with the larger packets is redir...
2017 Sep 01
2
[PATCH net-next] virtio-net: invoke zerocopy callback on xmit path if no tx napi
...hich I cannot yet explain.
>>
>> Running two threads in a guest, each with a udp socket, each
>> sending up to 100 datagrams, or until EAGAIN, every msec.
>>
>> Sender A sends 1B datagrams.
>> Sender B sends VHOST_GOODCOPY_LEN, which is enough
>> to trigger zcopy_used in vhost net.
>>
>> A local receive process on the host receives both flows. To avoid
>> a deep copy when looping the packet onto the receive path,
>> changed skb_orphan_frags_rx to always return false (gross hack).
>>
>> The flow with the larger packets is redir...
2017 Sep 22
17
[PATCH net-next RFC 0/5] batched tx processing in vhost_net
Hi:
This series tries to implement basic tx batched processing. This is
done by prefetching descriptor indices and update used ring in a
batch. This intends 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