Mon, May 20, 2024 at 02:48:15PM CEST, j...@resnulli.us wrote:
>Fri, May 10, 2024 at 09:11:16AM CEST, hen...@linux.alibaba.com wrote:
>>On Thu, 9 May 2024 13:46:15 +0200, Jiri Pirko wrote:
>>> From: Jiri Pirko
>>>
>>> Add support for Byte Queue Limits (BQL).
>>
>>Historically both Jason and Mich
On Wed, 5 Jun 2024 13:30:51 +0200, Jiri Pirko wrote:
> Mon, May 20, 2024 at 02:48:15PM CEST, j...@resnulli.us wrote:
> >Fri, May 10, 2024 at 09:11:16AM CEST, hen...@linux.alibaba.com wrote:
> >>On Thu, 9 May 2024 13:46:15 +0200, Jiri Pirko wrote:
> >>> From: Jiri Pirko
> >>>
> >>> Add support
If the device does not respond to a request for a long time,
then control vq polling elevates CPU utilization, a problem that
exacerbates with more command requests.
Enabling control vq's irq is advantageous for the guest, and
this still doesn't support concurrent requests.
This code is basically
Ctrlq in polling mode may cause the virtual machine to hang and
occupy additional CPU resources. Enabling the irq for ctrlq
alleviates this problem and allows commands to be requested
concurrently.
Changelog
=
v1->v2:
- Refactor the patch 1 and rephase the commit log.
Heng Qi (2):
vir
Currently, the control queue (ctrlq) handles commands synchronously,
leading to increased delays for dim commands during multi-queue
VM configuration and directly impacting dim performance.
To address this, we are shifting to asynchronous processing of
ctrlq's dim commands.
Signed-off-by: Heng Qi
On Tue, 2024-06-04 at 18:17 +0200, Alexander Potapenko wrote:
> On Tue, Jun 4, 2024 at 6:07 PM Ilya Leoshkevich
> wrote:
> >
> > On Thu, 2023-08-10 at 20:30 +0800, Xuan Zhuo wrote:
> > > If the vq is the premapped mode, use the sg_dma_address()
> > > directly.
> > >
> > > Signed-off-by: Xuan Zhu
On Wed, Jun 5, 2024 at 7:51 PM Heng Qi wrote:
>
> On Wed, 5 Jun 2024 13:30:51 +0200, Jiri Pirko wrote:
> > Mon, May 20, 2024 at 02:48:15PM CEST, j...@resnulli.us wrote:
> > >Fri, May 10, 2024 at 09:11:16AM CEST, hen...@linux.alibaba.com wrote:
> > >>On Thu, 9 May 2024 13:46:15 +0200, Jiri Pirko
On Wed, Jun 5, 2024 at 10:56 PM Heng Qi wrote:
>
> Currently, the control queue (ctrlq) handles commands synchronously,
> leading to increased delays for dim commands during multi-queue
> VM configuration and directly impacting dim performance.
>
> To address this, we are shifting to asynchronous
Hello Jason,
On Thu, Jun 6, 2024 at 8:21 AM Jason Wang wrote:
>
> On Wed, Jun 5, 2024 at 7:51 PM Heng Qi wrote:
> >
> > On Wed, 5 Jun 2024 13:30:51 +0200, Jiri Pirko wrote:
> > > Mon, May 20, 2024 at 02:48:15PM CEST, j...@resnulli.us wrote:
> > > >Fri, May 10, 2024 at 09:11:16AM CEST, hen...@li
On Thu, 6 Jun 2024 08:27:35 +0800, Jason Wang wrote:
> On Wed, Jun 5, 2024 at 10:56 PM Heng Qi wrote:
> >
> > Currently, the control queue (ctrlq) handles commands synchronously,
> > leading to increased delays for dim commands during multi-queue
> > VM configuration and directly impacting dim pe
On Tue, 04 Jun 2024 18:07:44 +0200, Ilya Leoshkevich wrote:
> On Thu, 2023-08-10 at 20:30 +0800, Xuan Zhuo wrote:
> > If the vq is the premapped mode, use the sg_dma_address() directly.
> >
> > Signed-off-by: Xuan Zhuo
> > ---
> > drivers/virtio/virtio_ring.c | 19 +--
> > 1 file
On Thu, Jun 6, 2024 at 10:59 AM Jason Xing wrote:
>
> Hello Jason,
>
> On Thu, Jun 6, 2024 at 8:21 AM Jason Wang wrote:
> >
> > On Wed, Jun 5, 2024 at 7:51 PM Heng Qi wrote:
> > >
> > > On Wed, 5 Jun 2024 13:30:51 +0200, Jiri Pirko wrote:
> > > > Mon, May 20, 2024 at 02:48:15PM CEST, j...@resnu
On Thu, Jun 06, 2024 at 12:25:15PM +0800, Jason Wang wrote:
> > If the codes of orphan mode don't have an impact when you enable
> > napi_tx mode, please keep it if you can.
>
> For example, it complicates BQL implementation.
>
> Thanks
I very much doubt sending interrupts to a VM can
*on all be
Ctrlq in polling mode may cause the virtual machine to hang and
occupy additional CPU resources. Enabling the irq for ctrlq
alleviates this problem and allows commands to be requested
concurrently.
Changelog
=
v2->v3:
- Use the completion for dim cmds.
v1->v2:
- Refactor the patch 1 a
If the device does not respond to a request for a long time,
then control vq polling elevates CPU utilization, a problem that
exacerbates with more command requests.
Enabling control vq's irq is advantageous for the guest, and
this still doesn't support concurrent requests.
Suggested-by: Jason Wa
In a later patch, the driver may send requests concurrently, in
which case each command will have its own control buffer, so we
refactor virtnet_send_command_reply() to pass the control buffer
explicitly as a parameter.
Signed-off-by: Heng Qi
---
drivers/net/virtio_net.c | 22 ---
Previously, control vq only allowed a single request to be sent,
so using virtnet_info as a global token was fine. To support
concurrent requests, the driver needs to use a command-level token
to distinguish between requests that have been sent.
Signed-off-by: Heng Qi
---
drivers/net/virtio_net.
Currently, control vq handles commands synchronously,
leading to increased delays for dim commands during multi-queue
VM configuration and directly impacting dim performance.
To address this, we are shifting to asynchronous processing of
ctrlq's dim commands.
Signed-off-by: Heng Qi
---
drivers/
18 matches
Mail list logo
