Re: [PATCH v3 2/2] config: disable CONFIG_RTE_SCHED_VECTOR for arm

From: Thomas Monjalon <thomas.monjalon@6wind.com>
To: Jan Viktorin <viktorin@rehivetech.com>
Cc: dev@dpdk.org
Subject: Re: [PATCH v3 2/2] config: disable CONFIG_RTE_SCHED_VECTOR for arm
Date: Mon, 30 Nov 2015 15:13:53 +0100	[thread overview]
Message-ID: <3362350.VxlxT3kjya@xps13> (raw)
In-Reply-To: <20151130150421.43d50e59@pcviktorin.fit.vutbr.cz>

2015-11-30 15:04, Jan Viktorin:
> On Mon, 30 Nov 2015 14:59:45 +0100
> Thomas Monjalon <thomas.monjalon@6wind.com> wrote:
> 
> > 2015-11-30 14:27, Jan Viktorin:
> > > I believe (and have already expressed this idea) that this is not a
> > > problem of architecture ports but it is a problem of the build system.
> > > Love me or hate me, in my opinion the build system is broken :). The
> > > build system should be able to solve this.
> > > 
> > > I've created privately an integration of kconfig into DPDK, however, it
> > > is far from being usable and I did not have time to make at least an
> > > RFC patch. If there is an attitude in the community to include such
> > > thing in the future versions, I'd like to make some more effort in this
> > > area.  
> > 
> > If we were integrating kconfig, we should consider kconfig-frontends
> > (http://ymorin.is-a-geek.org/projects/kconfig-frontends).
> 
> True, this seems to be the easiest way. I've already used it
> successfully.
> 
> > But I'm not sure it is the way to go. You are welcome to open the debate
> > in a dedicated thread by explaining the benefits compared to a configuration
> > script.
> 
> OK. I will consider this. Probably, after the community call... (Or
> before?)

Please take your time.
We will better ready to discuss it when the "make install" issue will be
solved.

> > I think most of the options could be automatically guessed given the target
> > CPU, kernel, libc and compiler. It looks like a scripting task, not a
> > manual configuration (as kconfig provides). But maybe we can mix kconfig
> > and some automatic defaults.
> > 
> 
> Well, scripting... If you have issues like "feature X" does not work
> on "platform A" then you need to express this. If you try to script
> such dependency, I am afraid you always end up with a system of the same
> or equivalent complexity as the kconfig already has :). We'll see...

I'm not speaking about complexity here, but just features.
With kconfig, options and dependencies are well described but the defaults
are fixed. With a script, you can have some dynamically generated defaults.

Please expose the needs and features clearly in another thread. Thanks