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>