From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: Hernan Vargas <hernan.vargas@intel.com>,
dev@dpdk.org, gakhil@marvell.com, trix@redhat.com
Cc: nicolas.chautru@intel.com, qi.z.zhang@intel.com
Subject: Re: [PATCH v1 03/13] test/bbdev: add timeout for latency tests
Date: Tue, 31 Jan 2023 11:02:15 +0100 [thread overview]
Message-ID: <1639469b-213a-d782-8234-a34cbe688df7@redhat.com> (raw)
In-Reply-To: <20230117165023.20567-4-hernan.vargas@intel.com>
On 1/17/23 17:50, Hernan Vargas wrote:
> Add a timeout to force exit the latency tests in case dequeue never
> happens.
>
> Signed-off-by: Hernan Vargas <hernan.vargas@intel.com>
> ---
> app/test-bbdev/test_bbdev_perf.c | 26 +++++++++++++++++++++-----
> 1 file changed, 21 insertions(+), 5 deletions(-)
>
> diff --git a/app/test-bbdev/test_bbdev_perf.c b/app/test-bbdev/test_bbdev_perf.c
> index 1a8a6b9f82..14fe76eb64 100644
> --- a/app/test-bbdev/test_bbdev_perf.c
> +++ b/app/test-bbdev/test_bbdev_perf.c
> @@ -26,6 +26,7 @@
>
> #define MAX_QUEUES RTE_MAX_LCORE
> #define TEST_REPETITIONS 100
> +#define TIME_OUT_POLL 1e8
> #define WAIT_OFFLOAD_US 1000
>
> #ifdef RTE_BASEBAND_FPGA_LTE_FEC
> @@ -4544,6 +4545,7 @@ latency_test_ldpc_dec(struct rte_mempool *mempool,
>
> for (i = 0, dequeued = 0; dequeued < num_to_process; ++i) {
> uint16_t enq = 0, deq = 0;
> + uint32_t time_out = 0;
> bool first_time = true;
> last_time = 0;
>
> @@ -4595,7 +4597,8 @@ latency_test_ldpc_dec(struct rte_mempool *mempool,
> last_time = rte_rdtsc_precise() - start_time;
> first_time = false;
> }
> - } while (unlikely(burst_sz != deq));
> + time_out++;
> + } while ((burst_sz != deq) && (time_out < TIME_OUT_POLL));
>
> *max_time = RTE_MAX(*max_time, last_time);
> *min_time = RTE_MIN(*min_time, last_time);
> @@ -4604,7 +4607,13 @@ latency_test_ldpc_dec(struct rte_mempool *mempool,
> if (extDdr)
> retrieve_harq_ddr(dev_id, queue_id, ops_enq, burst_sz);
>
> - if (test_vector.op_type != RTE_BBDEV_OP_NONE) {
> + if (burst_sz != deq) {
> + ret = TEST_FAILED;
> + dequeued = num_to_process; /* Force exit */
This should not be necessary, as TEST_ASSERT_SUCCESS() hides a return
statement.
> + struct rte_bbdev_info info;
Don't mix declaration & code.
> + rte_bbdev_info_get(dev_id, &info);
> + TEST_ASSERT_SUCCESS(ret, "Dequeue timeout!");
> + } else if (test_vector.op_type != RTE_BBDEV_OP_NONE) {
> ret = validate_ldpc_dec_op(ops_deq, burst_sz, ref_op,
> vector_mask);
> TEST_ASSERT_SUCCESS(ret, "Validation failed!");
> @@ -4630,6 +4639,7 @@ latency_test_enc(struct rte_mempool *mempool,
>
> for (i = 0, dequeued = 0; dequeued < num_to_process; ++i) {
> uint16_t enq = 0, deq = 0;
> + uint32_t time_out = 0;
> bool first_time = true;
> last_time = 0;
>
> @@ -4665,13 +4675,19 @@ latency_test_enc(struct rte_mempool *mempool,
> last_time += rte_rdtsc_precise() - start_time;
> first_time = false;
> }
> - } while (unlikely(burst_sz != deq));
> + time_out++;
> + } while ((burst_sz != deq) && (time_out < TIME_OUT_POLL));
>
> *max_time = RTE_MAX(*max_time, last_time);
> *min_time = RTE_MIN(*min_time, last_time);
> *total_time += last_time;
> -
> - if (test_vector.op_type != RTE_BBDEV_OP_NONE) {
> + if (burst_sz != deq) {
> + ret = TEST_FAILED;
> + dequeued = num_to_process; /* Force exit */
> + struct rte_bbdev_info info;
> + rte_bbdev_info_get(dev_id, &info);
> + TEST_ASSERT_SUCCESS(ret, "Dequeue timeout!");
Same comments here.
> + } else if (test_vector.op_type != RTE_BBDEV_OP_NONE) {
> ret = validate_enc_op(ops_deq, burst_sz, ref_op);
> TEST_ASSERT_SUCCESS(ret, "Validation failed!");
> }
next prev parent reply other threads:[~2023-01-31 10:02 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-17 16:50 [PATCH v1 00/13] test/bbdev: changes for 23.03 Hernan Vargas
2023-01-17 16:50 ` [PATCH v1 01/13] test/bbdev: fix seg fault for non supported HARQ len Hernan Vargas
2023-01-31 9:20 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 02/13] test/bbdev: refactor TB throughput report Hernan Vargas
2023-01-31 9:48 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 03/13] test/bbdev: add timeout for latency tests Hernan Vargas
2023-01-31 10:02 ` Maxime Coquelin [this message]
2023-01-17 16:50 ` [PATCH v1 04/13] test/bbdev: early termination not explicit set Hernan Vargas
2023-01-31 10:04 ` Maxime Coquelin
2023-02-10 17:15 ` Vargas, Hernan
2023-02-20 15:38 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 05/13] test/bbdev: report device status in bbdev-test Hernan Vargas
2023-01-31 10:05 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 06/13] test/bbdev: log capture from queue stop Hernan Vargas
2023-01-31 10:07 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 07/13] test/bbdev: add support for BLER for 4G Hernan Vargas
2023-01-31 10:20 ` Maxime Coquelin
2023-02-13 20:59 ` Vargas, Hernan
2023-02-20 15:43 ` Maxime Coquelin
2023-02-22 21:55 ` Vargas, Hernan
2023-02-23 8:26 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 08/13] test/bbdev: extend support for large TB Hernan Vargas
2023-01-31 11:29 ` Maxime Coquelin
2023-02-13 20:20 ` Vargas, Hernan
2023-02-20 15:40 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 09/13] test/bbdev: bbdev-test cannot compare some scenarios Hernan Vargas
2023-01-31 12:15 ` Maxime Coquelin
2023-02-13 19:40 ` Chautru, Nicolas
2023-01-17 16:50 ` [PATCH v1 10/13] test/bbdev: adjustment for soft output Hernan Vargas
2023-01-31 12:25 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 11/13] test/bbdev: expose warning counters Hernan Vargas
2023-01-31 12:26 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 12/13] test/bbdev: remove check for invalid opaque data Hernan Vargas
2023-01-31 12:33 ` Maxime Coquelin
2023-01-17 16:50 ` [PATCH v1 13/13] test/bbdev: remove iteration count check Hernan Vargas
2023-01-31 12:35 ` Maxime Coquelin
2023-02-08 20:38 ` Vargas, Hernan
2023-02-09 9:10 ` Maxime Coquelin
2023-02-09 16:59 ` Chautru, Nicolas
2023-02-10 14:01 ` Maxime Coquelin
2023-02-10 18:11 ` Chautru, Nicolas
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1639469b-213a-d782-8234-a34cbe688df7@redhat.com \
--to=maxime.coquelin@redhat.com \
--cc=dev@dpdk.org \
--cc=gakhil@marvell.com \
--cc=hernan.vargas@intel.com \
--cc=nicolas.chautru@intel.com \
--cc=qi.z.zhang@intel.com \
--cc=trix@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).