Eric W. Biederman wrote:
 

I'm conflicted about the dwarf unwinder.  I was off doing other things
at the time so I missed the pain, but I do have a distinct recollection of
the back traces on x86_64 being distinctly worse the on i386.  Lately
I haven't seen that so it may be I was misinterpreting what I was
seeing, and the compiler optimizations were what gave me such weird
back traces.  

Well, if you compile x86_64 with frame pointers it helps a bit because
the compiler doesn't tail merge function calls. But the stack backtrace
ignores the frame pointers even if they're present, unlike i386 which
will use them.