test/rwlock: benchmark on all available cores

Add performance test on all available cores to benchmark
the scaling up performance of rw_lock.

Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org
Suggested-by: Gavin Hu <gavin.hu@arm.com>
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

diff --git a/app/test/test_rwlock.c b/app/test/test_rwlock.c
index 224f0de..1d3774e 100644 (file)
--- a/app/test/test_rwlock.c
+++ b/app/test/test_rwlock.c
@@ -36,6 +36,7 @@
 
 static rte_rwlock_t sl;
 static rte_rwlock_t sl_tab[RTE_MAX_LCORE];
+static rte_atomic32_t synchro;
 
 enum {
        LC_TYPE_RDLOCK,
@@ -83,6 +84,77 @@ test_rwlock_per_core(__attribute__((unused)) void *arg)
        return 0;
 }
 
+static rte_rwlock_t lk = RTE_RWLOCK_INITIALIZER;
+static volatile uint64_t rwlock_data;
+static uint64_t lock_count[RTE_MAX_LCORE] = {0};
+
+#define TIME_MS 100
+#define TEST_RWLOCK_DEBUG 0
+
+static int
+load_loop_fn(__attribute__((unused)) void *arg)
+{
+       uint64_t time_diff = 0, begin;
+       uint64_t hz = rte_get_timer_hz();
+       uint64_t lcount = 0;
+       const unsigned int lcore = rte_lcore_id();
+
+       /* wait synchro for slaves */
+       if (lcore != rte_get_master_lcore())
+               while (rte_atomic32_read(&synchro) == 0)
+                       ;
+
+       begin = rte_rdtsc_precise();
+       while (time_diff < hz * TIME_MS / 1000) {
+               rte_rwlock_write_lock(&lk);
+               ++rwlock_data;
+               rte_rwlock_write_unlock(&lk);
+
+               rte_rwlock_read_lock(&lk);
+               if (TEST_RWLOCK_DEBUG && !(lcount % 100))
+                       printf("Core [%u] rwlock_data = %"PRIu64"\n",
+                               lcore, rwlock_data);
+               rte_rwlock_read_unlock(&lk);
+
+               lcount++;
+               /* delay to make lock duty cycle slightly realistic */
+               rte_pause();
+               time_diff = rte_rdtsc_precise() - begin;
+       }
+
+       lock_count[lcore] = lcount;
+       return 0;
+}
+
+static int
+test_rwlock_perf(void)
+{
+       unsigned int i;
+       uint64_t total = 0;
+
+       printf("\nRwlock Perf Test on %u cores...\n", rte_lcore_count());
+
+       /* clear synchro and start slaves */
+       rte_atomic32_set(&synchro, 0);
+       if (rte_eal_mp_remote_launch(load_loop_fn, NULL, SKIP_MASTER) < 0)
+               return -1;
+
+       /* start synchro and launch test on master */
+       rte_atomic32_set(&synchro, 1);
+       load_loop_fn(NULL);
+
+       rte_eal_mp_wait_lcore();
+
+       RTE_LCORE_FOREACH(i) {
+               printf("Core [%u] count = %"PRIu64"\n", i, lock_count[i]);
+               total += lock_count[i];
+       }
+
+       printf("Total count = %"PRIu64"\n", total);
+
+       return 0;
+}
+
 /*
  * - There is a global rwlock and a table of rwlocks (one per lcore).
  *
@@ -132,6 +204,9 @@ rwlock_test1(void)
 
        rte_eal_mp_wait_lcore();
 
+       if (test_rwlock_perf() < 0)
+               return -1;
+
        return 0;
 }