[dpdk-dev] [PATCH v3 4/6] test/spinlock: amortize the cost of getting time

[Gavin Hu]

Instead of getting timestamps per iteration, amortize its overhead
can help getting more precise benchmarking results.

Signed-off-by: Gavin Hu <gavin...@arm.com>
Reviewed-by: Joyce Kong <joyce.k...@arm.com>
---
 test/test/test_spinlock.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/test/test/test_spinlock.c b/test/test/test_spinlock.c
index 648474833..e9839b979 100644
--- a/test/test/test_spinlock.c
+++ b/test/test/test_spinlock.c
@@ -96,9 +96,9 @@ test_spinlock_recursive_per_core(__attribute__((unused)) void 
*arg)
 }
 
 static rte_spinlock_t lk = RTE_SPINLOCK_INITIALIZER;
-static uint64_t lock_count[RTE_MAX_LCORE] = {0};
+static uint64_t time_count[RTE_MAX_LCORE] = {0};
 
-#define TIME_MS 100
+#define MAX_LOOP 10000
 
 static int
 load_loop_fn(void *func_param)
@@ -114,15 +114,14 @@ load_loop_fn(void *func_param)
                while (rte_atomic32_read(&synchro) == 0);
 
        begin = rte_rdtsc_precise();
-       while (time_diff < hz * TIME_MS / 1000) {
+       while (lcount < MAX_LOOP) {
                if (use_lock)
                        rte_spinlock_lock(&lk);
-               lcount++;
                if (use_lock)
                        rte_spinlock_unlock(&lk);
-               time_diff = rte_rdtsc_precise() - begin;
        }
-       lock_count[lcore] = lcount;
+       time_diff = rte_rdtsc_precise() - begin;
+       time_count[lcore] = time_diff * 1000000 / hz;
        return 0;
 }
 
@@ -136,14 +135,16 @@ test_spinlock_perf(void)
 
        printf("\nTest with no lock on single core...\n");
        load_loop_fn(&lock);
-       printf("Core [%u] count = %"PRIu64"\n", lcore, lock_count[lcore]);
-       memset(lock_count, 0, sizeof(lock_count));
+       printf("Core [%u] Cost Time = %"PRIu64" us\n", lcore,
+                                               time_count[lcore]);
+       memset(time_count, 0, sizeof(time_count));
 
        printf("\nTest with lock on single core...\n");
        lock = 1;
        load_loop_fn(&lock);
-       printf("Core [%u] count = %"PRIu64"\n", lcore, lock_count[lcore]);
-       memset(lock_count, 0, sizeof(lock_count));
+       printf("Core [%u] Cost Time = %"PRIu64" us\n", lcore,
+                                               time_count[lcore]);
+       memset(time_count, 0, sizeof(time_count));
 
        printf("\nTest with lock on %u cores...\n", rte_lcore_count());
 
@@ -158,11 +159,12 @@ test_spinlock_perf(void)
        rte_eal_mp_wait_lcore();
 
        RTE_LCORE_FOREACH(i) {
-               printf("Core [%u] count = %"PRIu64"\n", i, lock_count[i]);
-               total += lock_count[i];
+               printf("Core [%u] Cost Time = %"PRIu64" us\n", i,
+                                               time_count[i]);
+               total += time_count[i];
        }
 
-       printf("Total count = %"PRIu64"\n", total);
+       printf("Total Cost Time = %"PRIu64" us\n", total);
 
        return 0;
 }
-- 
2.11.0