From 9607a85b67a9714290a78c1a56630ab1c9fa2c23 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 7 May 2013 15:39:03 -0700 Subject: rwsem: check counter to avoid cmpxchg calls This patch tries to reduce the amount of cmpxchg calls in the writer failed path by checking the counter value first before issuing the instruction. If ->count is not set to RWSEM_WAITING_BIAS then there is no point wasting a cmpxchg call. Furthermore, Michel states "I suppose it helps due to the case where someone else steals the lock while we're trying to acquire sem->wait_lock." Two very different workloads and machines were used to see how this patch improves throughput: pgbench on a quad-core laptop and aim7 on a large 8 socket box with 80 cores. Some results comparing Michel's fast-path write lock stealing (tps-rwsem) on a quad-core laptop running pgbench: | db_size | clients | tps-rwsem | tps-patch | +---------+----------+----------------+--------------+ | 160 MB | 1 | 6906 | 9153 | + 32.5 | 160 MB | 2 | 15931 | 22487 | + 41.1% | 160 MB | 4 | 33021 | 32503 | | 160 MB | 8 | 34626 | 34695 | | 160 MB | 16 | 33098 | 34003 | | 160 MB | 20 | 31343 | 31440 | | 160 MB | 30 | 28961 | 28987 | | 160 MB | 40 | 26902 | 26970 | | 160 MB | 50 | 25760 | 25810 | ------------------------------------------------------ | 1.6 GB | 1 | 7729 | 7537 | | 1.6 GB | 2 | 19009 | 23508 | + 23.7% | 1.6 GB | 4 | 33185 | 32666 | | 1.6 GB | 8 | 34550 | 34318 | | 1.6 GB | 16 | 33079 | 32689 | | 1.6 GB | 20 | 31494 | 31702 | | 1.6 GB | 30 | 28535 | 28755 | | 1.6 GB | 40 | 27054 | 27017 | | 1.6 GB | 50 | 25591 | 25560 | ------------------------------------------------------ | 7.6 GB | 1 | 6224 | 7469 | + 20.0% | 7.6 GB | 2 | 13611 | 12778 | | 7.6 GB | 4 | 33108 | 32927 | | 7.6 GB | 8 | 34712 | 34878 | | 7.6 GB | 16 | 32895 | 33003 | | 7.6 GB | 20 | 31689 | 31974 | | 7.6 GB | 30 | 29003 | 28806 | | 7.6 GB | 40 | 26683 | 26976 | | 7.6 GB | 50 | 25925 | 25652 | ------------------------------------------------------ For the aim7 worloads, they overall improved on top of Michel's patchset. For full graphs on how the rwsem series plus this patch behaves on a large 8 socket machine against a vanilla kernel: http://stgolabs.net/rwsem-aim7-results.tar.gz Signed-off-by: Davidlohr Bueso Signed-off-by: Linus Torvalds diff --git a/lib/rwsem.c b/lib/rwsem.c index cf0ad2a..19c5fa9 100644 --- a/lib/rwsem.c +++ b/lib/rwsem.c @@ -223,7 +223,9 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) count = RWSEM_ACTIVE_WRITE_BIAS; if (!list_is_singular(&sem->wait_list)) count += RWSEM_WAITING_BIAS; - if (cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == + + if (sem->count == RWSEM_WAITING_BIAS && + cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == RWSEM_WAITING_BIAS) break; } -- cgit v0.10.2