Igt-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Laguna, Lukasz" <lukasz.laguna@intel.com>
To: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>,
	<igt-dev@lists.freedesktop.org>
Cc: <adam.miszczak@linux.intel.com>, <jakub1.kolakowski@intel.com>
Subject: Re: [PATCH i-g-t 1/8] tests/intel/xe_sriov_scheduling: Use timestamp helper
Date: Tue, 9 Jun 2026 16:48:43 +0200	[thread overview]
Message-ID: <7289576f-52df-434d-96fc-571faa23756d@intel.com> (raw)
In-Reply-To: <20260527205644.2801165-2-marcin.bernatowicz@linux.intel.com>


On 5/27/2026 22:56, Marcin Bernatowicz wrote:
> Replace open-coded timestamp collection with current_timestamp_ns().
>
> Signed-off-by: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
> Cc: Adam Miszczak <adam.miszczak@linux.intel.com>
> Cc: Jakub Kolakowski <jakub1.kolakowski@intel.com>
> Cc: Lukasz Laguna <lukasz.laguna@intel.com>

Reviewed-by: Lukasz Laguna <lukasz.laguna@intel.com>

> ---
>   tests/intel/xe_sriov_scheduling.c | 26 +++++++++++++-------------
>   1 file changed, 13 insertions(+), 13 deletions(-)
>
> diff --git a/tests/intel/xe_sriov_scheduling.c b/tests/intel/xe_sriov_scheduling.c
> index 4228eea2d..509d6fd00 100644
> --- a/tests/intel/xe_sriov_scheduling.c
> +++ b/tests/intel/xe_sriov_scheduling.c
> @@ -85,6 +85,15 @@ struct subm_set {
>   	pthread_barrier_t barrier;
>   };
>   
> +static uint64_t current_timestamp_ns(void)
> +{
> +	struct timespec tv;
> +
> +	igt_gettime(&tv);
> +
> +	return tv.tv_sec * (uint64_t)NSEC_PER_SEC + (uint64_t)tv.tv_nsec;
> +}
> +
>   static void subm_init(struct subm *s, int fd, int vf_num, uint64_t addr,
>   		      struct drm_xe_engine_class_instance hwe,
>   		      unsigned int inflight)
> @@ -164,8 +173,6 @@ static void subm_wait_slot(struct subm *s, unsigned int slot, uint64_t abs_timeo
>   
>   static void subm_exec_slot(struct subm *s, unsigned int slot)
>   {
> -	struct timespec tv;
> -
>   	syncobj_reset(s->fd, &s->done_fence[slot], 1);
>   	memset(&s->sync[0], 0, sizeof(s->sync));
>   	s->sync[0].type = DRM_XE_SYNC_TYPE_SYNCOBJ;
> @@ -174,8 +181,7 @@ static void subm_exec_slot(struct subm *s, unsigned int slot)
>   	s->exec.num_syncs = 1;
>   	s->exec.syncs = to_user_pointer(&s->sync[0]);
>   	s->exec.address = s->addr[slot];
> -	igt_gettime(&tv);
> -	s->submit_ts[slot] = (uint64_t)tv.tv_sec * (uint64_t)NSEC_PER_SEC + (uint64_t)tv.tv_nsec;
> +	s->submit_ts[slot] = current_timestamp_ns();
>   	xe_exec(s->fd, &s->exec);
>   }
>   
> @@ -200,12 +206,9 @@ static void subm_exec_loop(struct subm *s, struct subm_stats *stats,
>   {
>   	const unsigned int inflight = s->slots;
>   	unsigned int submitted = 0;
> -	struct timespec tv;
>   	unsigned int i;
>   
> -	igt_gettime(&tv);
> -	stats->start_timestamp =
> -		tv.tv_sec * (uint64_t)NSEC_PER_SEC + tv.tv_nsec;
> +	stats->start_timestamp = current_timestamp_ns();
>   	igt_debug("[%s] start_timestamp: %f\n", s->id, stats->start_timestamp * 1e-9);
>   
>   	/* Prefill */
> @@ -222,9 +225,7 @@ static void subm_exec_loop(struct subm *s, struct subm_stats *stats,
>   		unsigned int slot = i % inflight;
>   
>   		subm_wait_slot(s, slot, INT64_MAX);
> -		igt_gettime(&tv);
> -		stats->complete_ts[i] = (uint64_t)tv.tv_sec * (uint64_t)NSEC_PER_SEC +
> -					(uint64_t)tv.tv_nsec;
> +		stats->complete_ts[i] = current_timestamp_ns();
>   		igt_stats_push(&stats->samples, stats->complete_ts[i] - s->submit_ts[slot]);
>   
>   		if (!subm_is_work_complete(s, slot)) {
> @@ -246,8 +247,7 @@ static void subm_exec_loop(struct subm *s, struct subm_stats *stats,
>   		}
>   	}
>   
> -	igt_gettime(&tv);
> -	stats->end_timestamp = tv.tv_sec * (uint64_t)NSEC_PER_SEC + tv.tv_nsec;
> +	stats->end_timestamp = current_timestamp_ns();
>   	igt_debug("[%s] end_timestamp: %f\n", s->id, stats->end_timestamp * 1e-9);
>   }
>   

  parent reply	other threads:[~2026-06-09 14:49 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-27 20:56 [PATCH i-g-t 0/8] tests/intel/xe_sriov_scheduling: improve scheduling coverage Marcin Bernatowicz
2026-05-27 20:56 ` [PATCH i-g-t 1/8] tests/intel/xe_sriov_scheduling: Use timestamp helper Marcin Bernatowicz
2026-05-28 10:43   ` Kamil Konieczny
2026-06-09 14:48   ` Laguna, Lukasz [this message]
2026-05-27 20:56 ` [PATCH i-g-t 2/8] tests/intel/xe_sriov_scheduling: Add scheduling priority support Marcin Bernatowicz
2026-06-09 14:51   ` Laguna, Lukasz
2026-05-27 20:56 ` [PATCH i-g-t 3/8] tests/intel/xe_sriov_scheduling: Make sysfs_get_job_timeout_ms take const eci Marcin Bernatowicz
2026-06-09 14:52   ` Laguna, Lukasz
2026-05-27 20:56 ` [PATCH i-g-t 4/8] tests/intel/xe_sriov_scheduling: Add PMU-based verification helpers Marcin Bernatowicz
2026-06-09 14:53   ` Laguna, Lukasz
2026-05-27 20:56 ` [PATCH i-g-t 5/8] tests/intel/xe_sriov_scheduling: Raise min exec quantum to 2ms Marcin Bernatowicz
2026-06-09 14:54   ` Laguna, Lukasz
2026-05-27 20:56 ` [PATCH i-g-t 6/8] tests/intel/xe_sriov_scheduling: Refactor throughput_ratio and nonpreempt-engine-resets test Marcin Bernatowicz
2026-06-09 14:58   ` Laguna, Lukasz
2026-05-27 20:56 ` [PATCH i-g-t 7/8] tests/intel/xe_sriov_scheduling: Remove unused log_sample_values helper Marcin Bernatowicz
2026-06-09 14:58   ` Laguna, Lukasz
2026-05-27 20:56 ` [PATCH i-g-t 8/8] tests/intel/xe_sriov_scheduling: Add default fair scheduling test Marcin Bernatowicz
2026-06-09 14:58   ` Laguna, Lukasz
2026-05-28  0:01 ` ✓ Xe.CI.BAT: success for tests/intel/xe_sriov_scheduling: improve scheduling coverage Patchwork
2026-05-28  0:04 ` ✗ i915.CI.BAT: failure " Patchwork
2026-05-28 12:15 ` ✓ Xe.CI.FULL: success " Patchwork

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=7289576f-52df-434d-96fc-571faa23756d@intel.com \
    --to=lukasz.laguna@intel.com \
    --cc=adam.miszczak@linux.intel.com \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=jakub1.kolakowski@intel.com \
    --cc=marcin.bernatowicz@linux.intel.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