> On 4 Apr 2019, at 05:19, G. Paul Ziemba <pz-vpp-...@ziemba.us> wrote:
>
> We do that by cloning, you can have multiple head buffers with small amount
> if data to accommodate l2/l3 headers and then such buffers have b->next_buffer
> pointing to shared tail buffer(s). Tail buffer(s) just need to have ref_count
> set properly
> to avoid that such buffer is freed prematurely.
> Perhaps more concrete information would clarify things: for code to support
> https://datatracker.ietf.org/doc/draft-hopps-ipsecme-iptfs
> <https://datatracker.ietf.org/doc/draft-hopps-ipsecme-iptfs>, the aggregation
> of multiple small payload frames into a single tunnel frame requires some
> dis-aggregation at the tunnel's receive endpoint.
>
> While it would be possible to make a functional implementation by recopying
> the payload frame pieces to new buffers for transmitting out of the tunnel,
> performance would be poor. The existing cloning mechanism does not appear to
> cover this situation because the cloned packets would need to end at
> different points in the original buffer. Do you have thoughts on a better way
> to do it?
I dont have time to read that draft, but it looks to me that during decryption
you can simply spray plaintext into multiple buffers, no?
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#12698): https://lists.fd.io/g/vpp-dev/message/12698
Mute This Topic: https://lists.fd.io/mt/30784477/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-
