Re: [Libunwind-devel] [patch] Fix for fast unwind and tcmalloc not playing well together.

[Lassi Tuura]

Hi Paul,

> Greetings,
> 
> I am now trying to use Lassi's fast trace, and the results are exceptionally
> good: on some of my test cases the overhead of using libunwind (compared
> to frame-based unwinder) went from 9x to 1.2x ;-)
> 
> Lassi, thanks!

Nice, glad to hear it's working for you :-)

> One problem that cropped up: tcmalloc wants to record stack traces on free,
> and this causes a crash when a thread is exiting.
> 
> Glibc calls thread-specific dtors in the order in which the keys were added,
> so the first dtor is the trace_cache_free() one. Then thread-specific
> data for some other key is free()d, which calls into unw_backtrace(),
> which uses dangling cache and munmapped cache->frames.
> 
> Attached patch
> 1. delays destruction of trace cache to the last possible moment, and
> 2. clears tls_cache, so the dangling pointer will not be used.
> 
> Tested on Linux/x86_64 (Ubuntu 10.04); no new failures.

Didn't test this yet, but looks very reasonable to me. I'll spin some tests on
this with our software chain (also with Konstantin's patch for FreeBSD) next 
week.

Regards,
Lassi