Re: [Libunwind-devel] non-local return scalability bottleneck

[Arun Sharma]

On Thu, Dec 3, 2015 at 9:28 AM, D'Alessandro, Luke K
<address@hidden> wrote:

> HIDDEN int
> dwarf_make_proc_info (struct dwarf_cursor *c)
> {
> #if 0
>     if (c->as->caching_policy == UNW_CACHE_NONE
>         || get_cached_proc_info (c) < 0)
> #endif
>         /* Lookup it up the slow way... */
>         return fetch_proc_info (c, c->ip, 0);
>     return 0;
> }
> ```
>
> So the question becomes, what is standing in the way of a “ 
> get_cached_proc_info” implementation? Is it just a "TODO/patches welcome” or 
> is there something fundamentally difficult going on here?

That code has been around since at least 2004, before my time with
libunwind. It didn't show up in the common use case of unwinding the
stack without a non-local return.

Suspect the comment below is relevant. Perhaps try removing it and see
what happens?

 -Arun

HIDDEN inline int
x86_64_local_resume (unw_addr_space_t as, unw_cursor_t *cursor, void *arg)
{
  [..]
  /* Ensure c->pi is up-to-date.  On x86-64, it's relatively common to
     be missing DWARF unwind info.  We don't want to fail in that
     case, because the frame-chain still would let us do a backtrace
     at least.  */
  dwarf_make_proc_info (&c->dwarf);