DPDK usage discussions
 help / color / mirror / Atom feed
* [dpdk-users] KNI - mbuf-sk_buff converstion
@ 2016-12-21  7:39 Avi Cohen
  2016-12-21  8:28 ` Anupam Kapoor
  0 siblings, 1 reply; 3+ messages in thread
From: Avi Cohen @ 2016-12-21  7:39 UTC (permalink / raw)
  To: users

Hello,
I guess  these conversions mbuff to sk_buff (executed in the KNI kthread context  )  - are zero_copy with respect  to the packet data (headers+payload) - is this correct ?
Thanks avi

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [dpdk-users] KNI - mbuf-sk_buff converstion
  2016-12-21  7:39 [dpdk-users] KNI - mbuf-sk_buff converstion Avi Cohen
@ 2016-12-21  8:28 ` Anupam Kapoor
  2016-12-21 14:01   ` tom.barbette
  0 siblings, 1 reply; 3+ messages in thread
From: Anupam Kapoor @ 2016-12-21  8:28 UTC (permalink / raw)
  To: Avi Cohen; +Cc: users

On Wed, Dec 21, 2016 at 1:09 PM, Avi Cohen <avi.cohen@huawei.com> wrote:

> are zero_copy with respect  to the packet data (headers+payload) - is this
> correc


​umm mbuf's, and skb's are in different address spaces...

--
kind regards
anupam​


In the beginning was the lambda, and the lambda was with Emacs, and Emacs
was the lambda.

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [dpdk-users] KNI - mbuf-sk_buff converstion
  2016-12-21  8:28 ` Anupam Kapoor
@ 2016-12-21 14:01   ` tom.barbette
  0 siblings, 0 replies; 3+ messages in thread
From: tom.barbette @ 2016-12-21 14:01 UTC (permalink / raw)
  To: Anupam Kapoor; +Cc: Avi Cohen, users

The memory space could be mapped when converting an mbuf to skbuff (while as you say it would be much harder the other way), but I don't see it done in the KNI code.

It memcpy the whole packet.

Out of curiosity, are there plan on using mapped skbuff?

Tom Barbette 
PhD Student @ Université de Liège 

Office 1/13 
Bâtiment B37 
Quartier Polytech 
Allée de la découverte, 12 
4000 Liège 

04/366 91 75 
0479/60 94 63 


----- Mail original -----
De: "Anupam Kapoor" <anupam.kapoor@gmail.com>
À: "Avi Cohen" <avi.cohen@huawei.com>
Cc: users@dpdk.org
Envoyé: Mercredi 21 Décembre 2016 09:28:46
Objet: Re: [dpdk-users] KNI - mbuf-sk_buff converstion

On Wed, Dec 21, 2016 at 1:09 PM, Avi Cohen <avi.cohen@huawei.com> wrote:

> are zero_copy with respect  to the packet data (headers+payload) - is this
> correc


​umm mbuf's, and skb's are in different address spaces...

--
kind regards
anupam​


In the beginning was the lambda, and the lambda was with Emacs, and Emacs
was the lambda.

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2016-12-21 14:01 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-12-21  7:39 [dpdk-users] KNI - mbuf-sk_buff converstion Avi Cohen
2016-12-21  8:28 ` Anupam Kapoor
2016-12-21 14:01   ` tom.barbette

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).