Sounds reasonable to me too. Should we have a single flag that enables tracebacks in both the parser and in the rest of python? IIRC, we print the python backtrace by default when we hit a python exception, and it seems to me that most of the time the backtrace obscures a useful error message rather than providing any help (though of course sometimes it's the other way around).
Steve On Sun, Nov 14, 2010 at 9:37 PM, nathan binkert <[email protected]> wrote: > Seems fine to me. --debug already exists with scons, so that's > perhaps not the best option. I think we want to try to kee our > options separate from SCons. > > Nate > > On Sun, Nov 14, 2010 at 7:41 PM, Gabe Black <[email protected]> wrote: > > Hi everybody. If you don't actively work on ISA descriptions or the > > parser, feel free to ignore this email. I've been working on the parser > > to better integrate the recent PC changes, and it's been useful to turn > > on the backtrace feature of the parser by setting debug=True at the top. > > This is a lot better than having it buried in the script (thanks, Ali) > > but it's still fairly easy to forget to turn it back off when generating > > patches, etc. Would anyone object to plumbing a scons variable through > > scons and into the parser to affect that behavior? I'm not sure whether > > a command line variable or -- style option would be best for scons, but > > I'm leaning heavily towards something like --debug for the parser > > itself. This isn't high priority and I may never bother actually > > implementing it, but I wanted to see if anyone violently apposed for > > some reason, maybe the added complexity and leaking of parser control > > knobs into the wider world of scons. > > > > Gabe > > _______________________________________________ > > m5-dev mailing list > > [email protected] > > http://m5sim.org/mailman/listinfo/m5-dev > > > > > _______________________________________________ > m5-dev mailing list > [email protected] > http://m5sim.org/mailman/listinfo/m5-dev >
_______________________________________________ m5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/m5-dev
