AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

locking/qspinlock: Use a simple write to grab the lock

Browse Source 
Currently, atomic_cmpxchg() is used to get the lock. However, this
is not really necessary if there is more than one task in the queue
and the queue head don't need to reset the tail code. For that case,
a simple write to set the lock bit is enough as the queue head will
be the only one eligible to get the lock as long as it checks that
both the lock and pending bits are not set. The current pending bit
waiting code will ensure that the bit will not be set as soon as the
tail code in the lock is set.

With that change, the are some slight improvement in the performance
of the queued spinlock in the 5M loop micro-benchmark run on a 4-socket
Westere-EX machine as shown in the tables below.

		[Standalone/Embedded - same node]
  # of tasks	Before patch	After patch	%Change
  ----------	-----------	----------	-------
       3	 2324/2321	2248/2265	 -3%/-2%
       4	 2890/2896	2819/2831	 -2%/-2%
       5	 3611/3595	3522/3512	 -2%/-2%
       6	 4281/4276	4173/4160	 -3%/-3%
       7	 5018/5001	4875/4861	 -3%/-3%
       8	 5759/5750	5563/5568	 -3%/-3%

		[Standalone/Embedded - different nodes]
  # of tasks	Before patch	After patch	%Change
  ----------	-----------	----------	-------
       3	12242/12237	12087/12093	 -1%/-1%
       4	10688/10696	10507/10521	 -2%/-2%

It was also found that this change produced a much bigger performance
improvement in the newer IvyBridge-EX chip and was essentially to close
the performance gap between the ticket spinlock and queued spinlock.

The disk workload of the AIM7 benchmark was run on a 4-socket
Westmere-EX machine with both ext4 and xfs RAM disks at 3000 users
on a 3.14 based kernel. The results of the test runs were:

                AIM7 XFS Disk Test
  kernel                 JPM    Real Time   Sys Time    Usr Time
  -----                  ---    ---------   --------    --------
  ticketlock            5678233    3.17       96.61       5.81
  qspinlock             5750799    3.13       94.83       5.97

                AIM7 EXT4 Disk Test
  kernel                 JPM    Real Time   Sys Time    Usr Time
  -----                  ---    ---------   --------    --------
  ticketlock            1114551   16.15      509.72       7.11
  qspinlock             2184466    8.24      232.99       6.01

The ext4 filesystem run had a much higher spinlock contention than
the xfs filesystem run.

The "ebizzy -m" test was also run with the following results:

  kernel               records/s  Real Time   Sys Time    Usr Time
  -----                ---------  ---------   --------    --------
  ticketlock             2075       10.00      216.35       3.49
  qspinlock              3023       10.00      198.20       4.80

Signed-off-by: Waiman Long <Waiman.Long@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel J Blueman <daniel@numascale.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Douglas Hatch <doug.hatch@hp.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paolo Bonzini <paolo.bonzini@gmail.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: virtualization@lists.linux-foundation.org
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1429901803-29771-7-git-send-email-Waiman.Long@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
Waiman Long 2015-04-24 14:56:35 -04:00 committed by Ingo Molnar
parent 69f9cae909
commit 2c83e8e949
1 changed files with 55 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
kernel/locking/qspinlock.c
View File

@ -105,24 +105,37 @@ static inline struct mcs_spinlock *decode_tail(u32 tail)
* By using the whole 2nd least significant byte for the pending bit, we * By using the whole 2nd least significant byte for the pending bit, we
* can allow better optimization of the lock acquisition for the pending * can allow better optimization of the lock acquisition for the pending
* bit holder. * bit holder.
*
* This internal structure is also used by the set_locked function which
* is not restricted to _Q_PENDING_BITS == 8.
*/ */
#if _Q_PENDING_BITS == 8
struct __qspinlock { struct __qspinlock {
union { union {
atomic_t val; atomic_t val;
struct {
#ifdef __LITTLE_ENDIAN #ifdef __LITTLE_ENDIAN
u16 locked_pending; struct {
u16 tail; u8 locked;
#else u8 pending;
u16 tail;
u16 locked_pending;
#endif
}; };
struct {
u16 locked_pending;
u16 tail;
};
#else
struct {
u16 tail;
u16 locked_pending;
};
struct {
u8 reserved[2];
u8 pending;
u8 locked;
};
#endif
}; };
}; };
#if _Q_PENDING_BITS == 8
/** /**
* clear_pending_set_locked - take ownership and clear the pending bit. * clear_pending_set_locked - take ownership and clear the pending bit.
* @lock: Pointer to queued spinlock structure * @lock: Pointer to queued spinlock structure
@ -194,6 +207,19 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
} }
#endif /* _Q_PENDING_BITS == 8 */ #endif /* _Q_PENDING_BITS == 8 */
/**
* set_locked - Set the lock bit and own the lock
* @lock: Pointer to queued spinlock structure
*
* *,*,0 -> *,0,1
*/
static __always_inline void set_locked(struct qspinlock *lock)
{
struct __qspinlock *l = (void *)lock;
WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
}
/** /**
* queued_spin_lock_slowpath - acquire the queued spinlock * queued_spin_lock_slowpath - acquire the queued spinlock
* @lock: Pointer to queued spinlock structure * @lock: Pointer to queued spinlock structure
@ -329,8 +355,14 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
* go away. * go away.
* *
* *,x,y -> *,0,0 * *,x,y -> *,0,0
*
* this wait loop must use a load-acquire such that we match the
* store-release that clears the locked bit and create lock
* sequentiality; this is because the set_locked() function below
* does not imply a full barrier.
*
*/ */
while ((val = atomic_read(&lock->val)) & _Q_LOCKED_PENDING_MASK) while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_PENDING_MASK)
cpu_relax(); cpu_relax();
/* /*
@ -338,15 +370,19 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
* *
* n,0,0 -> 0,0,1 : lock, uncontended * n,0,0 -> 0,0,1 : lock, uncontended
* *,0,0 -> *,0,1 : lock, contended * *,0,0 -> *,0,1 : lock, contended
*
* If the queue head is the only one in the queue (lock value == tail),
* clear the tail code and grab the lock. Otherwise, we only need
* to grab the lock.
*/ */
for (;;) { for (;;) {
new = _Q_LOCKED_VAL; if (val != tail) {
if (val != tail) set_locked(lock);
new |= val;
old = atomic_cmpxchg(&lock->val, val, new);
if (old == val)
break; break;
}
old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
if (old == val)
goto release; /* No contention */
val = old; val = old;
} }
@ -354,12 +390,10 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
/* /*
* contended path; wait for next, release. * contended path; wait for next, release.
*/ */
if (new != _Q_LOCKED_VAL) { while (!(next = READ_ONCE(node->next)))
while (!(next = READ_ONCE(node->next))) cpu_relax();
cpu_relax();
arch_mcs_spin_unlock_contended(&next->locked); arch_mcs_spin_unlock_contended(&next->locked);
}
release: release:
/* /*