[parisc-linux] User space locks -- what's wrong

[John David Anglin]

> > #   slow_pthread_self   The synchronization code should try to avoid
> > #                       pthread_self calls by caching thread IDs in a hashtable
> >
> > There's also 'enable_hash_synchronization_default'.
> 
> Reading the thread register is a single mfctl, I don't know if that is
> considered slow?

Looks like it's the later parameter that affects lock caching:

# Should we use hashtable-based synchronization?
# Currently works only for Linux X86/ia64
# Typically faster and more space-efficient
AC_ARG_ENABLE(hash-synchronization,
  AS_HELP_STRING([--enable-hash-synchronization],
		   [use global hash table for monitor locks]))

I'll try turning this off.

Dave
-- 
J. David Anglin                                  dave.anglin at nrc-cnrc.gc.ca
National Research Council of Canada              (613) 990-0752 (FAX: 952-6602)