locking/qrwlock: Don't contend with readers when setting _QW_WAITING
The current cmpxchg() loop in setting the _QW_WAITING flag for writers in queue_write_lock_slowpath() will contend with incoming readers causing possibly extra cmpxchg() operations that are wasteful. This patch changes the code to do a byte cmpxchg() to eliminate contention with new readers. A multithreaded microbenchmark running 5M read_lock/write_lock loop on a 8-socket 80-core Westmere-EX machine running 4.0 based kernel with the qspinlock patch have the following execution times (in ms) with and without the patch: With R:W ratio = 5:1 Threads w/o patch with patch % change ------- --------- ---------- -------- 2 990 895 -9.6% 3 2136 1912 -10.5% 4 3166 2830 -10.6% 5 3953 3629 -8.2% 6 4628 4405 -4.8% 7 5344 5197 -2.8% 8 6065 6004 -1.0% 9 6826 6811 -0.2% 10 7599 7599 0.0% 15 9757 9766 +0.1% 20 13767 13817 +0.4% With small number of contending threads, this patch can improve locking performance by up to 10%. With more contending threads, however, the gain diminishes. 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: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1433863153-30722-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
92ae18371c
commit
405963b6a5
|
@ -22,6 +22,26 @@
|
|||
#include <linux/hardirq.h>
|
||||
#include <asm/qrwlock.h>
|
||||
|
||||
/*
|
||||
* This internal data structure is used for optimizing access to some of
|
||||
* the subfields within the atomic_t cnts.
|
||||
*/
|
||||
struct __qrwlock {
|
||||
union {
|
||||
atomic_t cnts;
|
||||
struct {
|
||||
#ifdef __LITTLE_ENDIAN
|
||||
u8 wmode; /* Writer mode */
|
||||
u8 rcnts[3]; /* Reader counts */
|
||||
#else
|
||||
u8 rcnts[3]; /* Reader counts */
|
||||
u8 wmode; /* Writer mode */
|
||||
#endif
|
||||
};
|
||||
};
|
||||
arch_spinlock_t lock;
|
||||
};
|
||||
|
||||
/**
|
||||
* rspin_until_writer_unlock - inc reader count & spin until writer is gone
|
||||
* @lock : Pointer to queue rwlock structure
|
||||
|
@ -107,10 +127,10 @@ void queue_write_lock_slowpath(struct qrwlock *lock)
|
|||
* or wait for a previous writer to go away.
|
||||
*/
|
||||
for (;;) {
|
||||
cnts = atomic_read(&lock->cnts);
|
||||
if (!(cnts & _QW_WMASK) &&
|
||||
(atomic_cmpxchg(&lock->cnts, cnts,
|
||||
cnts | _QW_WAITING) == cnts))
|
||||
struct __qrwlock *l = (struct __qrwlock *)lock;
|
||||
|
||||
if (!READ_ONCE(l->wmode) &&
|
||||
(cmpxchg(&l->wmode, 0, _QW_WAITING) == 0))
|
||||
break;
|
||||
|
||||
cpu_relax_lowlatency();
|
||||
|
|
Loading…
Reference in New Issue