Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1611766 > unrolled thread

Re: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array

Started byJason Wang <jasowang@redhat.com>
First post2017-03-29 12:00 +0200
Last post2017-03-29 23:50 +0200
Articles 4 — 3 participants

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.


Contents

  Re: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array Jason Wang <jasowang@redhat.com> - 2017-03-29 12:00 +0200
    Re: [PATCH net-next 7/8] vhost_net: try batch dequing from skb  array Pankaj Gupta <pagupta@redhat.com> - 2017-03-29 12:50 +0200
      Re: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array Jason Wang <jasowang@redhat.com> - 2017-03-29 13:00 +0200
        Re: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array "Michael S. Tsirkin" <mst@redhat.com> - 2017-03-29 23:50 +0200

#1611766 — Re: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array

FromJason Wang <jasowang@redhat.com>
Date2017-03-29 12:00 +0200
SubjectRe: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array
Message-ID<tqiyu-55o-17@gated-at.bofh.it>

On 2017年03月23日 13:34, Jason Wang wrote:
>
>
>>
>>> +{
>>> +    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

[toc] | [next] | [standalone]


#1611807 — Re: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array

FromPankaj Gupta <pagupta@redhat.com>
Date2017-03-29 12:50 +0200
SubjectRe: [PATCH net-next 7/8] vhost_net: try batch dequing from skb array
Message-ID<tqjkR-5EX-1@gated-at.bofh.it>
In reply to#1611766
Hi Jason,

> 
> On 2017年03月23日 13:34, Jason Wang wrote:
> >
> >
> >>
> >>> +{
> >>> +    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_consume_batched_*()" functions.
Are we planning to use them in future? 

> 
> Thanks
> 

[toc] | [prev] | [next] | [standalone]


#1611823

FromJason Wang <jasowang@redhat.com>
Date2017-03-29 13:00 +0200
Message-ID<tqjux-5Ii-9@gated-at.bofh.it>
In reply to#1611807

On 2017年03月29日 18:46, Pankaj Gupta wrote:
> Hi Jason,
>
>> On 2017年03月23日 13:34, Jason Wang wrote:
>>>
>>>>> +{
>>>>> +    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_consume_batched_*()" functions.
> Are we planning to use them in future?

I think we'd better keep them, since it serves as helpers. You can see 
that not all the helpers in ptr_ring has real users, but they were 
prepared for the future use.

Thanks

>
>> Thanks
>>

[toc] | [prev] | [next] | [standalone]


#1612400

From"Michael S. Tsirkin" <mst@redhat.com>
Date2017-03-29 23:50 +0200
Message-ID<tqtDA-4sl-13@gated-at.bofh.it>
In reply to#1611823
On Wed, Mar 29, 2017 at 06:53:27PM +0800, Jason Wang wrote:
> 
> 
> On 2017年03月29日 18:46, Pankaj Gupta wrote:
> > Hi Jason,
> > 
> > > On 2017年03月23日 13:34, Jason Wang wrote:
> > > > 
> > > > > > +{
> > > > > > +    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_consume_batched_*()" functions.
> > Are we planning to use them in future?
> 
> I think we'd better keep them, since it serves as helpers. You can see that
> not all the helpers in ptr_ring has real users, but they were prepared for
> the future use.
> 
> Thanks

Makes sense for basic building blocks but I'm not sure we
need to do it for all APIs.


> > 
> > > Thanks
> > > 

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web