rx netdim needs to count the traffic during a complete napi process,
and start updating and comparing samples to make decisions after
the napi ends. Let virtqueue_napi_complete() return true if napi is done,
otherwise vice versa.
Signed-off-by: Heng Qi
Acked-by: Jason Wang
---
drivers/net/virti
We do not currently support tx dim, so respond to -EOPNOTSUPP.
Signed-off-by: Heng Qi
---
v1->v2:
- Use -EOPNOTSUPP instead of specific implementation.
drivers/net/virtio_net.c | 29 ++---
1 file changed, 26 insertions(+), 3 deletions(-)
diff --git a/drivers/net/virtio_
By comparing the traffic information in the complete napi processes,
let the virtio-net driver automatically adjust the coalescing
moderation parameters of each receive queue.
Signed-off-by: Heng Qi
---
v2->v3:
- Some minor modifications.
v1->v2:
- Improved the judgment of dim switch conditions.
Extract commands to set virtqueue coalescing parameters for reuse
by ethtool -Q, vq resize and netdim.
Signed-off-by: Heng Qi
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 106 +++
1 file changed, 64 insertions(+), 42 deletions(-)
diff --git a/drivers/
Now, virtio-net already supports per-queue moderation parameter
setting. Based on this, we use the linux dimlib to support
dynamic coalescing moderation for virtio-net.
Due to some scheduling issues, we only support and test the rx dim.
Some test results:
I. Sockperf UDP
This patch separates the rx and tx global coalescing moderation
commands to support netdim switches in subsequent patches.
Signed-off-by: Heng Qi
Acked-by: Jason Wang
---
drivers/net/virtio_net.c | 31 ---
1 file changed, 28 insertions(+), 3 deletions(-)
diff --git
On Tue, 14 Nov 2023 12:27:20 +0800, Jason Wang wrote:
> On Tue, Nov 14, 2023 at 11:59 AM Xuan Zhuo wrote:
> >
> > On Tue, 14 Nov 2023 11:55:52 +0800, Jason Wang wrote:
> > > On Tue, Nov 14, 2023 at 11:42 AM Xuan Zhuo
> > > wrote:
> > > >
> > > > On Tue, 14 Nov 2023 11:26:42 +0800, Jason Wang
On Tue, Nov 14, 2023 at 11:59 AM Xuan Zhuo wrote:
>
> On Tue, 14 Nov 2023 11:55:52 +0800, Jason Wang wrote:
> > On Tue, Nov 14, 2023 at 11:42 AM Xuan Zhuo
> > wrote:
> > >
> > > On Tue, 14 Nov 2023 11:26:42 +0800, Jason Wang
> > > wrote:
> > > > On Thu, Nov 9, 2023 at 7:06 PM Xuan Zhuo
> >
On Tue, 14 Nov 2023 11:55:52 +0800, Jason Wang wrote:
> On Tue, Nov 14, 2023 at 11:42 AM Xuan Zhuo wrote:
> >
> > On Tue, 14 Nov 2023 11:26:42 +0800, Jason Wang wrote:
> > > On Thu, Nov 9, 2023 at 7:06 PM Xuan Zhuo
> > > wrote:
> > > >
> > > > On Thu, 9 Nov 2023 14:37:38 +0800, Jason Wang
>
On Tue, Nov 14, 2023 at 11:42 AM Xuan Zhuo wrote:
>
> On Tue, 14 Nov 2023 11:26:42 +0800, Jason Wang wrote:
> > On Thu, Nov 9, 2023 at 7:06 PM Xuan Zhuo wrote:
> > >
> > > On Thu, 9 Nov 2023 14:37:38 +0800, Jason Wang wrote:
> > > > On Tue, Nov 7, 2023 at 11:12 AM Xuan Zhuo
> > > > wrote:
> >
On Mon, 13 Nov 2023 17:11:04 +0100, Maciej Fijalkowski
wrote:
> On Tue, Nov 07, 2023 at 11:12:24AM +0800, Xuan Zhuo wrote:
> > The virtnet_xdp_handler() is re-used. But
> >
> > 1. We need to copy data to create skb for XDP_PASS.
> > 2. We need to call xsk_buff_free() to release the buffer.
> > 3.
On Tue, 14 Nov 2023 11:26:42 +0800, Jason Wang wrote:
> On Thu, Nov 9, 2023 at 7:06 PM Xuan Zhuo wrote:
> >
> > On Thu, 9 Nov 2023 14:37:38 +0800, Jason Wang wrote:
> > > On Tue, Nov 7, 2023 at 11:12 AM Xuan Zhuo
> > > wrote:
> > > >
> > > > If the xsk is enabling, the xsk tx will share the se
On Thu, Nov 9, 2023 at 7:06 PM Xuan Zhuo wrote:
>
> On Thu, 9 Nov 2023 14:37:38 +0800, Jason Wang wrote:
> > On Tue, Nov 7, 2023 at 11:12 AM Xuan Zhuo
> > wrote:
> > >
> > > If the xsk is enabling, the xsk tx will share the send queue.
> > > But the xsk requires that the send queue use the prem
On Mon, 13 Nov 2023 17:00:50 +0100, Maciej Fijalkowski
wrote:
> On Fri, Nov 10, 2023 at 10:38:04AM +0800, Xuan Zhuo wrote:
> > On Thu, 9 Nov 2023 17:26:33 +0100, Maciej Fijalkowski
> > wrote:
> > > On Thu, Nov 09, 2023 at 07:11:46PM +0800, Xuan Zhuo wrote:
> > > > On Thu, 9 Nov 2023 03:12:27 -0
On Tue, Nov 07, 2023 at 11:12:24AM +0800, Xuan Zhuo wrote:
> The virtnet_xdp_handler() is re-used. But
>
> 1. We need to copy data to create skb for XDP_PASS.
> 2. We need to call xsk_buff_free() to release the buffer.
> 3. The handle for xdp_buff is difference.
>
> If we pushed this logic into e
On Fri, Nov 10, 2023 at 10:38:04AM +0800, Xuan Zhuo wrote:
> On Thu, 9 Nov 2023 17:26:33 +0100, Maciej Fijalkowski
> wrote:
> > On Thu, Nov 09, 2023 at 07:11:46PM +0800, Xuan Zhuo wrote:
> > > On Thu, 9 Nov 2023 03:12:27 -0500, "Michael S. Tsirkin"
> > > wrote:
> > > > On Tue, Nov 07, 2023 at 1
16 matches
Mail list logo
