ring: add optional yield to avoid spin forever

Add a sched_yield() syscall if the thread spins for too long,
waiting other thread to finish its operations on the ring.
That gives pre-empted thread a chance to proceed and finish
with ring enqueue/dequeue operation.
The purpose is to reduce contention on the ring.
By ring_perf_test, it doesn't shows additional perf penalty.

Signed-off-by: Cunming Liang <cunming.liang@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

diff --git a/config/common_bsdapp b/config/common_bsdapp
index 56c537202d03483c2ce108f6f85a7bacfa6bd850..f93151af919f20cc5ca1a7b9351b0da92ead6ba8 100644 (file)
--- a/config/common_bsdapp
+++ b/config/common_bsdapp
@@ -248,6 +248,7 @@ CONFIG_RTE_PMD_PACKET_PREFETCH=y
 CONFIG_RTE_LIBRTE_RING=y
 CONFIG_RTE_LIBRTE_RING_DEBUG=n
 CONFIG_RTE_RING_SPLIT_PROD_CONS=n
+CONFIG_RTE_RING_PAUSE_REP_COUNT=0
 
 #
 # Compile librte_mempool

diff --git a/config/common_linuxapp b/config/common_linuxapp
index fc294250c233ba65bb22af6b338b1b8933f3f754..c138a0cc123cdafd934d61a999ea323251f2f89f 100644 (file)
--- a/config/common_linuxapp
+++ b/config/common_linuxapp
@@ -256,6 +256,7 @@ CONFIG_RTE_PMD_PACKET_PREFETCH=y
 CONFIG_RTE_LIBRTE_RING=y
 CONFIG_RTE_LIBRTE_RING_DEBUG=n
 CONFIG_RTE_RING_SPLIT_PROD_CONS=n
+CONFIG_RTE_RING_PAUSE_REP_COUNT=0
 
 #
 # Compile librte_mempool

diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h
index 39bacdd6ae200d2deb4582cfaf0509288dd169d8..bdf69b7790dee68418970f28069090151349702e 100644 (file)
--- a/lib/librte_ring/rte_ring.h
+++ b/lib/librte_ring/rte_ring.h
@@ -127,6 +127,11 @@ struct rte_ring_debug_stats {
 #define RTE_RING_NAMESIZE 32 /**< The maximum length of a ring name. */
 #define RTE_RING_MZ_PREFIX "RG_"
 
+#ifndef RTE_RING_PAUSE_REP_COUNT
+#define RTE_RING_PAUSE_REP_COUNT 0 /**< Yield after pause num of times, no yield
+                                    *   if RTE_RING_PAUSE_REP not defined. */
+#endif
+
 /**
  * An RTE ring structure.
  *
@@ -410,7 +415,7 @@ __rte_ring_mp_do_enqueue(struct rte_ring *r, void * const *obj_table,
        uint32_t cons_tail, free_entries;
        const unsigned max = n;
        int success;
-       unsigned i;
+       unsigned i, rep = 0;
        uint32_t mask = r->prod.mask;
        int ret;
 
@@ -468,9 +473,18 @@ __rte_ring_mp_do_enqueue(struct rte_ring *r, void * const *obj_table,
         * If there are other enqueues in progress that preceded us,
         * we need to wait for them to complete
         */
-       while (unlikely(r->prod.tail != prod_head))
+       while (unlikely(r->prod.tail != prod_head)) {
                rte_pause();
 
+               /* Set RTE_RING_PAUSE_REP_COUNT to avoid spin too long waiting
+                * for other thread finish. It gives pre-empted thread a chance
+                * to proceed and finish with ring dequeue operation. */
+               if (RTE_RING_PAUSE_REP_COUNT &&
+                   ++rep == RTE_RING_PAUSE_REP_COUNT) {
+                       rep = 0;
+                       sched_yield();
+               }
+       }
        r->prod.tail = prod_next;
        return ret;
 }
@@ -589,7 +603,7 @@ __rte_ring_mc_do_dequeue(struct rte_ring *r, void **obj_table,
        uint32_t cons_next, entries;
        const unsigned max = n;
        int success;
-       unsigned i;
+       unsigned i, rep = 0;
        uint32_t mask = r->prod.mask;
 
        /* move cons.head atomically */
@@ -634,9 +648,18 @@ __rte_ring_mc_do_dequeue(struct rte_ring *r, void **obj_table,
         * If there are other dequeues in progress that preceded us,
         * we need to wait for them to complete
         */
-       while (unlikely(r->cons.tail != cons_head))
+       while (unlikely(r->cons.tail != cons_head)) {
                rte_pause();
 
+               /* Set RTE_RING_PAUSE_REP_COUNT to avoid spin too long waiting
+                * for other thread finish. It gives pre-empted thread a chance
+                * to proceed and finish with ring dequeue operation. */
+               if (RTE_RING_PAUSE_REP_COUNT &&
+                   ++rep == RTE_RING_PAUSE_REP_COUNT) {
+                       rep = 0;
+                       sched_yield();
+               }
+       }
        __RING_STAT_ADD(r, deq_success, n);
        r->cons.tail = cons_next;