Daniel Eischen wrote:
On Mon, 29 Oct 2007, Kris Kennaway wrote:
kris 2007-10-29 21:01:47 UTC
FreeBSD src repository
Modified files:
lib/libthr/thread thr_mutex.c
lib/libkse/thread thr_mutex.c
include pthread.h
Log:
Add a new "non-portable" mutex type, PTHREAD_MUTEX_ADAPTIVE_NP. This
is also implemented in glibc and is used by a number of existing
applications (mysql, firefox, etc).
This mutex type is a default mutex with the additional property that
it spins briefly when attempting to acquire a contested lock, doing
trylock operations in userland before entering the kernel to block if
eventually unsuccessful.
The expectation is that applications requesting this mutex type know
that the mutex is likely to be only held for very brief periods, so it
is faster to spin in userland and probably succeed in acquiring the
mutex, than to enter the kernel and sleep, only to be woken up almost
immediately. This can help significantly in certain cases when
pthread mutexes are heavily contended and held for brief durations
(such as mysql).
Spin up to 200 times before entering the kernel, which represents only
a few us on modern CPUs. No performance degradation was observed with
this value and it is sufficient to avoid a large performance drop in
mysql performance in the heavily contended pthread mutex case.
The libkse implementation is a NOP.
The libkse implementation already spins for a bit. The default
number of spins is 500.
OK, cool.
I'm not sure that another mutex type is warranted, the default
mutex implementation should be adaptive I think.
The point being that certain existing applications already know about
this mutex name and will use it automatically when it exists.
I am a bit wary of making this the default type though. The algorithm
is a pessimization when the conditions described above are not true.
Kris
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/cvs-all
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
