summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorGavin Hu <gavin.hu@arm.com>2018-11-02 19:21:28 +0800
committerThomas Monjalon <thomas@monjalon.net>2018-11-05 14:34:27 +0100
commit047adc17245892198be31c54cf6658080df3dc6d (patch)
tree46f8b8b66fe903e31b16ae4cb7af79f087fec069 /lib
parent9ed877062898dd1eb7150bca56ebbd5329e96ee4 (diff)
downloaddpdk-047adc17245892198be31c54cf6658080df3dc6d.zip
dpdk-047adc17245892198be31c54cf6658080df3dc6d.tar.gz
dpdk-047adc17245892198be31c54cf6658080df3dc6d.tar.xz
ring/c11: move atomic load of head above the loop
In __rte_ring_move_prod_head, move the __atomic_load_n up and out of the do {} while loop as upon failure the old_head will be updated, another load is costly and not necessary. This helps a little on the latency,about 1~5%. Test result with the patch(two cores): SP/SC bulk enq/dequeue (size: 8): 5.64 MP/MC bulk enq/dequeue (size: 8): 9.58 SP/SC bulk enq/dequeue (size: 32): 1.98 MP/MC bulk enq/dequeue (size: 32): 2.30 Fixes: 39368ebfc606 ("ring: introduce C11 memory model barrier option") Cc: stable@dpdk.org Signed-off-by: Gavin Hu <gavin.hu@arm.com> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Reviewed-by: Steve Capper <steve.capper@arm.com> Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com> Reviewed-by: Jia He <justin.he@arm.com> Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com> Tested-by: Jerin Jacob <jerin.jacob@caviumnetworks.com> Acked-by: Olivier Matz <olivier.matz@6wind.com>
Diffstat (limited to 'lib')
-rw-r--r--lib/librte_ring/rte_ring_c11_mem.h10
1 files changed, 4 insertions, 6 deletions
diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/rte_ring_c11_mem.h
index 52da95a..7bc74a4 100644
--- a/lib/librte_ring/rte_ring_c11_mem.h
+++ b/lib/librte_ring/rte_ring_c11_mem.h
@@ -61,13 +61,11 @@ __rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
unsigned int max = n;
int success;
+ *old_head = __atomic_load_n(&r->prod.head, __ATOMIC_ACQUIRE);
do {
/* Reset n to the initial burst count */
n = max;
- *old_head = __atomic_load_n(&r->prod.head,
- __ATOMIC_ACQUIRE);
-
/* load-acquire synchronize with store-release of ht->tail
* in update_tail.
*/
@@ -93,6 +91,7 @@ __rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp,
if (is_sp)
r->prod.head = *new_head, success = 1;
else
+ /* on failure, *old_head is updated */
success = __atomic_compare_exchange_n(&r->prod.head,
old_head, *new_head,
0, __ATOMIC_ACQUIRE,
@@ -135,13 +134,11 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
int success;
/* move cons.head atomically */
+ *old_head = __atomic_load_n(&r->cons.head, __ATOMIC_ACQUIRE);
do {
/* Restore n as it may change every loop */
n = max;
- *old_head = __atomic_load_n(&r->cons.head,
- __ATOMIC_ACQUIRE);
-
/* this load-acquire synchronize with store-release of ht->tail
* in update_tail.
*/
@@ -166,6 +163,7 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc,
if (is_sc)
r->cons.head = *new_head, success = 1;
else
+ /* on failure, *old_head will be updated */
success = __atomic_compare_exchange_n(&r->cons.head,
old_head, *new_head,
0, __ATOMIC_ACQUIRE,