Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 08 Nov 2014 22:09:38 +0200
From:      Andriy Gapon <avg@FreeBSD.org>
To:        Alexander Kabaev <kabaev@gmail.com>, Mark Johnston <markj@FreeBSD.org>
Cc:        svn-src-head@FreeBSD.org, svn-src-all@FreeBSD.org, src-committers@FreeBSD.org
Subject:   Re: svn commit: r274200 - head/share/mk
Message-ID:  <545E7882.90209@FreeBSD.org>
In-Reply-To: <20141108120000.3f16feab@kan>
References:  <201411062246.sA6MkeLN018716@svn.freebsd.org> <20141108120000.3f16feab@kan>

next in thread | previous in thread | raw e-mail | index | archive | help
On 08/11/2014 19:00, Alexander Kabaev wrote:
> On Thu, 6 Nov 2014 22:46:40 +0000 (UTC) Mark Johnston <markj@FreeBSD.org>
> wrote:
> 
>> Author: markj Date: Thu Nov  6 22:46:40 2014 New Revision: 274200 URL:
>> https://svnweb.freebsd.org/changeset/base/274200
>> 
>> Log: Automatically build with debug symbols when building with WITH_CTF. 
>> Otherwise there's nothing for ctfconvert to do, and it ends up emitting
>> an error for each object file. Also remove some redundant checks from
>> bsd.prog.mk and bsd.lib.mk.
> <SKIP>
>> 
>> -.if ${MK_CTF} != "no" && ${DEBUG_FLAGS:M-g} != "" +.if ${MK_CTF} !=
>> "no" CTFFLAGS+= -g .endif .else
> 
> I have a question about this and another similar change. Does it have the
> effect of always leaving binaries with debug symbols in id WITH_CTF is in
> effect and do we now rely solely on install stripping binaries at later
> stage to get rid of the debug symbols? IMHO, we should only pass -g to
> ctfconvert if WITH_CTF is set _and_ user requested debug symbols
> explicitly. Your change seems to be breaking that.

Hmm, I do not follow your logic here, sorry.
So, you say that stripping should be ctfconvert's job? Why?

-- 
Andriy Gapon



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?545E7882.90209>