deischen at freebsd.org
Mon May 9 12:54:35 PDT 2005
On Tue, 10 May 2005, Peter Jeremy wrote:
> On Mon, 2005-May-09 11:00:18 -0400, Ewan Todd wrote:
> >I have what I think is a serious performance issue with fbsd 5.3
> >release. I've read about threading issues, and it seems to me that
> >that is what I'm looking at, but I'm not confident enough to rule out
> >that it might be a hardware issue, a kernel configuration issue, or
> >something to do with the python port.
> There does appear to be a problem in FreeBSD. Python is built with
> threading enabled by default, the threading libraries play with the
> signal mask and there have been extensive changes there. My
The threading libraries don't play with the signal mask. In fact,
libpthread has userland versions of sigprocmask() et. al. and won't
even make the syscall() unless the threads are system scope. There
is a special thread in libpthread that handles signals which does
use the system sigprocmask(), but unless the application is
making heavy use of signals in general, it shouldn't matter.
> suggestions on things you could check are:
> 1) Rebuild python with threading disabled (add '-DWITHOUT_THREADS' to the
> 'make' command line and see if that makes any difference
> 2) Re-write the sample program in a non-threaded language - eg C or perl
> and see if the high system time goes away.
> Unfortunately, I can't think of a solution at present.
You can also set LIBPTHREAD_SYSTEM_SCOPE in the environment to
force libpthread to use system scope threads. It uses process
scope threads by default.
More information about the freebsd-stable