aboutsummaryrefslogtreecommitdiffstats
path: root/lib
diff options
context:
space:
mode:
authorDavidlohr Bueso <davidlohr.bueso@hp.com>2013-05-07 18:39:03 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2013-05-07 19:11:51 -0400
commit9607a85b67a9714290a78c1a56630ab1c9fa2c23 (patch)
treeb1f5f8c8a056f39f160bdd08f1f2340d5a700710 /lib
parent2d864e41710f1d2ba406fb62018ab0487152e6f2 (diff)
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 <davidlohr.bueso@hp.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'lib')
-rw-r--r--lib/rwsem.c4
1 files changed, 3 insertions, 1 deletions
diff --git a/lib/rwsem.c b/lib/rwsem.c
index cf0ad2ad19f5..19c5fa95e0b4 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)
223 count = RWSEM_ACTIVE_WRITE_BIAS; 223 count = RWSEM_ACTIVE_WRITE_BIAS;
224 if (!list_is_singular(&sem->wait_list)) 224 if (!list_is_singular(&sem->wait_list))
225 count += RWSEM_WAITING_BIAS; 225 count += RWSEM_WAITING_BIAS;
226 if (cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == 226
227 if (sem->count == RWSEM_WAITING_BIAS &&
228 cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) ==
227 RWSEM_WAITING_BIAS) 229 RWSEM_WAITING_BIAS)
228 break; 230 break;
229 } 231 }