Agreed on both points. I'll submit a patchset to remove the l2fwd_fork example and its user-guide, so it doesn't appear that DPDK supports this model. If anyone on the ML disagrees, they can respond here or on the patch thread.

-----Original Message-----
From: Stephen Hemminger [mailto:stephen@networkplumber.org]
Sent: Friday, July 27, 2018 11:00 AM
To: Thomas Monjalon <redacted>
Cc: Eads, Gage <redacted>; Burakov, Anatoly
[off-list ref]; dev@dpdk.org; Richardson, Bruce
[off-list ref]; jerin.jacob@caviumnetworks.com; Yigit, Ferruh
[off-list ref]; hemant.agrawal@nxp.com; Ananyev, Konstantin
[off-list ref]; Olivier Matz [off-list ref]
Subject: Re: DPDK and forked processes

On Fri, 27 Jul 2018 17:03:48 +0200
Thomas Monjalon [off-list ref] wrote:

quoted

27/07/2018 15:46, Eads, Gage:

quoted

As this discussion has broad implications for DPDK, is it a good candidate for

a techboard meeting topic?

quoted

We can discuss it in techboard, but usually we prefer discussing
topics whose resolution is not clear.
In this case, I think everybody agree with Anatoly, isn't it?

I would prefer that decisions like this be done by rough consensus on the mailing
list.

As far as applications messing with internals, in reality any application can
change anything. Just don't come crying to DPDK community for help.