mutex: adaptive spinnning, performance tweaks

Spin more agressively. This is less fair but also markedly faster.

The numbers:

 * dbench 50 (higher is better):
  spin        1282MB/s
  v10         548MB/s
  v10 no wait 1868MB/s

 * 4k creates (numbers in files/second higher is better):
  spin        avg 200.60 median 193.20 std 19.71 high 305.93 low 186.82
  v10         avg 180.94 median 175.28 std 13.91 high 229.31 low 168.73
  v10 no wait avg 232.18 median 222.38 std 22.91 high 314.66 low 209.12

 * File stats (numbers in seconds, lower is better):
  spin        2.27s
  v10         5.1s
  v10 no wait 1.6s

( The source changes are smaller than they look, I just moved the
  need_resched checks in __mutex_lock_common after the cmpxchg. )

Signed-off-by: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/mutex.c b/kernel/mutex.c
index ff42e97..5d79781 100644 (file)
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -171,12 +171,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                struct thread_info *owner;
 
                /*
-                * If there are pending waiters, join them.
-                */
-               if (!list_empty(&lock->wait_list))
-                       break;
-
-               /*
                 * If there's an owner, wait for it to either
                 * release the lock or go to sleep.
                 */
@@ -184,6 +178,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                if (owner && !mutex_spin_on_owner(lock, owner))
                        break;
 
+               if (atomic_cmpxchg(&lock->count, 1, 0) == 1) {
+                       lock_acquired(&lock->dep_map, ip);
+                       mutex_set_owner(lock);
+                       preempt_enable();
+                       return 0;
+               }
+
                /*
                 * When there's no owner, we might have preempted between the
                 * owner acquiring the lock and setting the owner field. If
@@ -193,13 +194,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
                if (!owner && (need_resched() || rt_task(task)))
                        break;
 
-               if (atomic_cmpxchg(&lock->count, 1, 0) == 1) {
-                       lock_acquired(&lock->dep_map, ip);
-                       mutex_set_owner(lock);
-                       preempt_enable();
-                       return 0;
-               }
-
                /*
                 * The cpu_relax() call is a compiler barrier which forces
                 * everything in this loop to be re-loaded. We don't need