[dpdk-dev] [PATCH v5 1/4] test/lpm: fix cycle calculation in rcu qsbr perf
Medvedkin, Vladimir
vladimir.medvedkin at intel.com
Wed Nov 4 20:34:48 CET 2020
On 04/11/2020 18:58, Dharmik Thakkar wrote:
> Fix incorrect calculations for LPM adds, LPM deletes,
> and average cycles in RCU QSBR perf tests
>
> Since, rcu qsbr tests run for 'RCU_ITERATIONS' and not
> 'ITERATIONS', replace 'ITERATIONS' with 'RCU_ITERATIONS'
> for calculating adds, deletes, and cycles.
>
> Also, for multi-writer perf test, each writer only writes
> half of NUM_LDEPTH_ROUTE_ENTRIES.
> For 2 writers, total adds (or deletes) should be
> (RCU_ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES) instead of
> (2 * RCU_ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES).
>
> Since, for both the single and multi writer tests, total adds/deletes
> is equal to (RCU_ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES),
> this has been replaced with a macro 'TOTAL_WRITES' and furthermore,
> 'g_writes' has been removed since it is always a fixed value
> equal to TOTAL_WRITES.
>
> Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
> Cc: honnappa.nagarahalli at arm.com
> Cc: stable at dpdk.org
>
> Signed-off-by: Dharmik Thakkar <dharmik.thakkar at arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang at arm.com>
> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli at arm.com>
> ---
> app/test/test_lpm_perf.c | 45 ++++++++++++++--------------------------
> 1 file changed, 16 insertions(+), 29 deletions(-)
>
> diff --git a/app/test/test_lpm_perf.c b/app/test/test_lpm_perf.c
> index c5a238b9d1e8..45164b23214b 100644
> --- a/app/test/test_lpm_perf.c
> +++ b/app/test/test_lpm_perf.c
> @@ -23,7 +23,6 @@ static struct rte_rcu_qsbr *rv;
> static volatile uint8_t writer_done;
> static volatile uint32_t thr_id;
> static uint64_t gwrite_cycles;
> -static uint64_t gwrites;
> /* LPM APIs are not thread safe, use mutex to provide thread safety */
> static pthread_mutex_t lpm_mutex = PTHREAD_MUTEX_INITIALIZER;
>
> @@ -60,6 +59,8 @@ static uint32_t num_ldepth_route_entries;
> #define NUM_ROUTE_ENTRIES num_route_entries
> #define NUM_LDEPTH_ROUTE_ENTRIES num_ldepth_route_entries
>
> +#define TOTAL_WRITES (RCU_ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES)
> +
> enum {
> IP_CLASS_A,
> IP_CLASS_B,
> @@ -432,7 +433,6 @@ test_lpm_rcu_qsbr_writer(void *arg)
> uint8_t core_id = (uint8_t)((uintptr_t)arg);
> uint32_t next_hop_add = 0xAA;
>
> - RTE_SET_USED(arg);
> /* 2 writer threads are used */
> if (core_id % 2 == 0) {
> si = 0;
> @@ -472,9 +472,6 @@ test_lpm_rcu_qsbr_writer(void *arg)
> total_cycles = rte_rdtsc_precise() - begin;
>
> __atomic_fetch_add(&gwrite_cycles, total_cycles, __ATOMIC_RELAXED);
> - __atomic_fetch_add(&gwrites,
> - 2 * NUM_LDEPTH_ROUTE_ENTRIES * RCU_ITERATIONS,
> - __ATOMIC_RELAXED);
>
> return 0;
> }
> @@ -528,7 +525,6 @@ test_lpm_rcu_perf_multi_writer(void)
>
> writer_done = 0;
> __atomic_store_n(&gwrite_cycles, 0, __ATOMIC_RELAXED);
> - __atomic_store_n(&gwrites, 0, __ATOMIC_RELAXED);
>
> __atomic_store_n(&thr_id, 0, __ATOMIC_SEQ_CST);
>
> @@ -548,14 +544,11 @@ test_lpm_rcu_perf_multi_writer(void)
> if (rte_eal_wait_lcore(enabled_core_ids[i]) < 0)
> goto error;
>
> - printf("Total LPM Adds: %d\n",
> - 2 * ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> - printf("Total LPM Deletes: %d\n",
> - 2 * ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> + printf("Total LPM Adds: %d\n", TOTAL_WRITES);
> + printf("Total LPM Deletes: %d\n", TOTAL_WRITES);
> printf("Average LPM Add/Del: %"PRIu64" cycles\n",
> - __atomic_load_n(&gwrite_cycles, __ATOMIC_RELAXED) /
> - __atomic_load_n(&gwrites, __ATOMIC_RELAXED)
> - );
> + __atomic_load_n(&gwrite_cycles, __ATOMIC_RELAXED)
> + / TOTAL_WRITES);
>
> /* Wait and check return value from reader threads */
> writer_done = 1;
> @@ -581,7 +574,6 @@ test_lpm_rcu_perf_multi_writer(void)
>
> writer_done = 0;
> __atomic_store_n(&gwrite_cycles, 0, __ATOMIC_RELAXED);
> - __atomic_store_n(&gwrites, 0, __ATOMIC_RELAXED);
> __atomic_store_n(&thr_id, 0, __ATOMIC_SEQ_CST);
>
> /* Launch reader threads */
> @@ -600,14 +592,11 @@ test_lpm_rcu_perf_multi_writer(void)
> if (rte_eal_wait_lcore(enabled_core_ids[i]) < 0)
> goto error;
>
> - printf("Total LPM Adds: %d\n",
> - 2 * ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> - printf("Total LPM Deletes: %d\n",
> - 2 * ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> + printf("Total LPM Adds: %d\n", TOTAL_WRITES);
> + printf("Total LPM Deletes: %d\n", TOTAL_WRITES);
> printf("Average LPM Add/Del: %"PRIu64" cycles\n",
> - __atomic_load_n(&gwrite_cycles, __ATOMIC_RELAXED) /
> - __atomic_load_n(&gwrites, __ATOMIC_RELAXED)
> - );
> + __atomic_load_n(&gwrite_cycles, __ATOMIC_RELAXED)
> + / TOTAL_WRITES);
>
> writer_done = 1;
> /* Wait and check return value from reader threads */
> @@ -711,11 +700,10 @@ test_lpm_rcu_perf(void)
> }
> total_cycles = rte_rdtsc_precise() - begin;
>
> - printf("Total LPM Adds: %d\n", ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> - printf("Total LPM Deletes: %d\n",
> - ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> + printf("Total LPM Adds: %d\n", TOTAL_WRITES);
> + printf("Total LPM Deletes: %d\n", TOTAL_WRITES);
> printf("Average LPM Add/Del: %g cycles\n",
> - (double)total_cycles / (NUM_LDEPTH_ROUTE_ENTRIES * ITERATIONS));
> + (double)total_cycles / TOTAL_WRITES);
>
> writer_done = 1;
> /* Wait and check return value from reader threads */
> @@ -771,11 +759,10 @@ test_lpm_rcu_perf(void)
> }
> total_cycles = rte_rdtsc_precise() - begin;
>
> - printf("Total LPM Adds: %d\n", ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> - printf("Total LPM Deletes: %d\n",
> - ITERATIONS * NUM_LDEPTH_ROUTE_ENTRIES);
> + printf("Total LPM Adds: %d\n", TOTAL_WRITES);
> + printf("Total LPM Deletes: %d\n", TOTAL_WRITES);
> printf("Average LPM Add/Del: %g cycles\n",
> - (double)total_cycles / (NUM_LDEPTH_ROUTE_ENTRIES * ITERATIONS));
> + (double)total_cycles / TOTAL_WRITES);
>
> writer_done = 1;
> /* Wait and check return value from reader threads */
>
Acked-by: Vladimir Medvedkin <vladimir.medvedkin at intel.com>
--
Regards,
Vladimir
More information about the dev
mailing list