From 49594a63147a994d9674b1f479d0107e70fe1cbc Mon Sep 17 00:00:00 2001 From: Gavin Hu Date: Fri, 9 Nov 2018 19:42:47 +0800 Subject: [PATCH] ring/c11: relax ordering for load and store of the head When calling __atomic_compare_exchange_n, use relaxed ordering for the success case, as multiple producers/consumers do not release updates to each other so no need for acquire or release ordering. Because the thread fence in place, ordering for the first iteration can be relaxed. Run the ring perf test on the following testbed: HW: ThunderX2 B0 CPU CN9975 v2.0, 2 sockets, 28core,4 threads/core,2.5GHz OS: Ubuntu 16.04.5 LTS, Kernel: 4.15.0-36-generic DPDK: 18.08, Configuration: arm64-armv8a-linuxapp-gcc gcc: 8.1.0 $sudo ./test/test/test -l 16-19,44-47,72-75,100-103 -n 4 \ --socket-mem=1024 -- -i Without the patch: *** Testing using two physical cores *** SP/SC bulk enq/dequeue (size: 8): 5.75 MP/MC bulk enq/dequeue (size: 8): 10.18 SP/SC bulk enq/dequeue (size: 32): 1.80 MP/MC bulk enq/dequeue (size: 32): 2.34 With the patch: *** Testing using two physical cores *** SP/SC bulk enq/dequeue (size: 8): 5.59 MP/MC bulk enq/dequeue (size: 8): 10.54 SP/SC bulk enq/dequeue (size: 32): 1.73 MP/MC bulk enq/dequeue (size: 32): 2.38 No significant improvement, nor regression was seen, as the optimisation is not at the critical path. Fixes: 39368ebfc6 ("ring: introduce C11 memory model barrier option") Cc: stable@dpdk.org Signed-off-by: Gavin Hu Reviewed-by: Honnappa Nagarahalli Reviewed-by: Steve Capper Reviewed-by: Ola Liljedahl --- lib/librte_ring/rte_ring_c11_mem.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/lib/librte_ring/rte_ring_c11_mem.h b/lib/librte_ring/rte_ring_c11_mem.h index dc49a998fd..0fb73a3371 100644 --- a/lib/librte_ring/rte_ring_c11_mem.h +++ b/lib/librte_ring/rte_ring_c11_mem.h @@ -61,7 +61,7 @@ __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); + *old_head = __atomic_load_n(&r->prod.head, __ATOMIC_RELAXED); do { /* Reset n to the initial burst count */ n = max; @@ -97,7 +97,7 @@ __rte_ring_move_prod_head(struct rte_ring *r, unsigned int is_sp, /* on failure, *old_head is updated */ success = __atomic_compare_exchange_n(&r->prod.head, old_head, *new_head, - 0, __ATOMIC_ACQUIRE, + 0, __ATOMIC_RELAXED, __ATOMIC_RELAXED); } while (unlikely(success == 0)); return n; @@ -137,7 +137,7 @@ __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); + *old_head = __atomic_load_n(&r->cons.head, __ATOMIC_RELAXED); do { /* Restore n as it may change every loop */ n = max; @@ -172,7 +172,7 @@ __rte_ring_move_cons_head(struct rte_ring *r, int is_sc, /* on failure, *old_head will be updated */ success = __atomic_compare_exchange_n(&r->cons.head, old_head, *new_head, - 0, __ATOMIC_ACQUIRE, + 0, __ATOMIC_RELAXED, __ATOMIC_RELAXED); } while (unlikely(success == 0)); return n; -- 2.20.1