PowerPC fastpaths for mutex subsystem

Ingo Molnar mingo at elte.hu
Wed Jan 11 21:52:13 EST 2006


* Ingo Molnar <mingo at elte.hu> wrote:

> ok. I'll really need to look at "vmstat" output from these. We could 
> easily make the mutex slowpath behave like ppc64 semaphores, via the 
> attached (untested) patch, but i really think it's the wrong thing to 
> do, because it overloads the system with runnable tasks in an 
> essentially unlimited fashion [== overscheduling] - they'll all 
> contend for the same single mutex.

find the working patch below. (the previous one had a syntax error)

	Ingo

Index: linux/kernel/mutex.c
===================================================================
--- linux.orig/kernel/mutex.c
+++ linux/kernel/mutex.c
@@ -227,6 +227,9 @@ __mutex_unlock_slowpath(atomic_t *lock_c
 		debug_mutex_wake_waiter(lock, waiter);
 
 		wake_up_process(waiter->task);
+
+		/* be (much) more agressive about wakeups: */
+		list_move_tail(&waiter->list, &lock->wait_list);
 	}
 
 	debug_mutex_clear_owner(lock);



More information about the Linuxppc64-dev mailing list