Re: [RFC PATCH] perf report: add sort by file lines

[Lin Ming <ming.m.lin@intel.com>]

On Fri, 2011-04-01 at 21:49 +0800, Peter Zijlstra wrote:
> On Fri, 2011-04-01 at 21:22 +0800, Lin Ming wrote:
> > On Fri, 2011-04-01 at 19:05 +0800, Peter Zijlstra wrote:
> > > On Fri, 2011-04-01 at 19:44 +0900, Masami Hiramatsu wrote:
> > > > E.g. an indirect jump makes it hard to find where it jumps to.
> > > 
> > > Yes indirect jumps are 'interesting', is there anything in the debug
> > > info that will help us out with the possible target sites?
> > > 
> > > Also what generates indirect jumps, switch() stmts? Indirect function
> > > call that get optimized might also be, but hopefully DWARF would tell us
> > > about that and allow us to know the state right after the jump.
> > 
> > I'm not sure.
> > 
> > But I'm thinking another way to trace the register assignment by LBR
> > records.
> > 
> > LBR will introduce overhead, but it can tell us all the branches,
> > including the indirect jump.
> 
> 
> Yeah, but it would be nice to see how far we can get without using extra
> information, we can always try and complement stuff later.

Well, let me start working out a prototype.

Thanks for all the comments from your guys :)