Igt-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: <igt-dev@lists.freedesktop.org>, Tvrtko Ursulin <tursulin@ursulin.net>
Subject: Re: [PATCH i-g-t v3 12/13] lib/igt_drm_clients: Record total cycles
Date: Wed, 8 May 2024 12:07:40 -0700	[thread overview]
Message-ID: <ZjvNfMUqWvTaRWAG@orsosgc001> (raw)
In-Reply-To: <ZjvL9YI1889za0qT@orsosgc001>

On Wed, May 08, 2024 at 12:01:09PM -0700, Umesh Nerlige Ramappa wrote:
>On Fri, May 03, 2024 at 11:46:42PM -0700, Lucas De Marchi wrote:
>>If the fdinfo data indicates there's drm-total-cycles, use it to
>>propagate the engine utilization. Also add an assert in intel_gpu_top
>>since it only knows how to deal with with engine time busyness.
>>
>>Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
>>---
>>lib/igt_drm_clients.c | 13 +++++++++++++
>>lib/igt_drm_clients.h |  5 +++++
>>2 files changed, 18 insertions(+)
>>
>>diff --git a/lib/igt_drm_clients.c b/lib/igt_drm_clients.c
>>index fbbb763f7..105c7d298 100644
>>--- a/lib/igt_drm_clients.c
>>+++ b/lib/igt_drm_clients.c
>>@@ -107,10 +107,13 @@ igt_drm_client_update(struct igt_drm_client *c, unsigned int pid, char *name,
>>	c->total_engine_time = 0;
>>	c->agg_delta_cycles = 0;
>>	c->total_cycles = 0;
>>+	c->agg_delta_total_cycles = 0;
>>+	c->total_total_cycles = 0;
>>
>>	for (i = 0; i <= c->engines->max_engine_id; i++) {
>>		assert(i < ARRAY_SIZE(info->engine_time));
>>		assert(i < ARRAY_SIZE(info->cycles));
>>+		assert(i < ARRAY_SIZE(info->total_cycles));
>
>same comment as before - maybe just ensure array sizes are the same.
>
>>
>>		if (info->utilization_mask & DRM_FDINFO_UTILIZATION_ENGINE_TIME &&
>>		    info->engine_time[i] >= c->utilization[i].last_engine_time) {
>>@@ -131,6 +134,16 @@ igt_drm_client_update(struct igt_drm_client *c, unsigned int pid, char *name,
>>			c->agg_delta_cycles += c->utilization[i].delta_cycles;
>>			c->utilization[i].last_cycles = info->cycles[i];
>>		}
>>+
>>+		if (info->utilization_mask & DRM_FDINFO_UTILIZATION_CYCLES &&
>
>This should be
>
>s/DRM_FDINFO_UTILIZATION_CYCLES/DRM_FDINFO_UTILIZATION_TOTAL_CYCLES/
>
>or a new name if you decide to change things based on below comment.
>
>>+		    info->total_cycles[i] >= c->utilization[i].last_total_cycles) {
>>+			c->utilization_mask |= IGT_DRM_CLIENT_UTILIZATION_TOTAL_CYCLES;
>>+			c->total_total_cycles += info->total_cycles[i];
>>+			c->utilization[i].delta_total_cycles =
>>+				info->total_cycles[i] - c->utilization[i].last_total_cycles;
>>+			c->agg_delta_total_cycles += c->utilization[i].delta_total_cycles;
>>+			c->utilization[i].last_total_cycles = info->total_cycles[i];
>>+		}
>>	}
>>
>>	/* Memory regions */
>>diff --git a/lib/igt_drm_clients.h b/lib/igt_drm_clients.h
>>index 514c09e71..946d709de 100644
>>--- a/lib/igt_drm_clients.h
>>+++ b/lib/igt_drm_clients.h
>>@@ -36,6 +36,7 @@ enum igt_drm_client_status {
>>enum igt_drm_client_utilization_type {
>>	IGT_DRM_CLIENT_UTILIZATION_ENGINE_TIME	= 1U << 0,
>>	IGT_DRM_CLIENT_UTILIZATION_CYCLES	= 1U << 1,
>>+	IGT_DRM_CLIENT_UTILIZATION_TOTAL_CYCLES	= 1U << 2,
>>};
>>
>>struct igt_drm_client_engines {
>>@@ -74,11 +75,15 @@ struct igt_drm_client {
>>	unsigned long agg_delta_engine_time; /* Aggregate of @utilization.delta_engine_time, i.e. engine time on all engines since previous scan. */
>>	unsigned long total_cycles; /* Aggregate of @utilization.agg_delta_cycles, i.e. engine time on all engines since client start. */
>>	unsigned long agg_delta_cycles; /* Aggregate of @utilization.delta_cycles, i.e. engine time on all engines since previous scan. */
>>+	unsigned long total_total_cycles; /* Aggregate of @utilization.agg_delta_total_cycles, i.e. engine time on all engines since client start. */
>
>total_total_cycles :). I can understand that since I am looking at the 
>patches in order, but there might be room for another rename, maybe:
>
>s/c->total_cycles/c->total_engine_cycles/ (since this is how may 
>cycles the client ran on the engine)
>
>s/c->total_total_cycles/c->total_<something>_cycles/ (where 
><something> could be - "available" or "gpu".

On second thoughts, I believe <something>_cycles is likely derived from 
drm-total-cycles, so you have named it accordingly. I am okay with this 
as is.

With just the if condition fixed above, this should be

Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>

Umesh
>
>Regards,
>Umesh
>
>>+	unsigned long agg_delta_total_cycles; /* Aggregate of @utilization.delta_total_cycles, i.e. engine time on all engines since previous scan. */
>>	struct igt_drm_client_utilization {
>>		unsigned long delta_engine_time; /* Engine time data, relative to previous scan. */
>>		unsigned long delta_cycles; /* Engine cycles data, relative to previous scan. */
>>+		unsigned long delta_total_cycles; /* Engine total cycles data, relative to previous scan. */
>>		uint64_t last_engine_time; /* Engine time data as parsed from fdinfo. */
>>		uint64_t last_cycles; /* Engine cycles data as parsed from fdinfo. */
>>+		uint64_t last_total_cycles; /* Engine total cycles data as parsed from fdinfo. */
>>	} *utilization; /* Array of engine utilization */
>>
>>	struct drm_client_meminfo *memory; /* Array of region memory utilisation as parsed from fdinfo. */
>>-- 
>>2.43.0
>>

  reply	other threads:[~2024-05-08 19:08 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-04  6:46 [PATCH i-g-t v3 00/12] gputop: Add support for xe Lucas De Marchi
2024-05-04  6:46 ` [PATCH i-g-t v3 01/13] lib/igt_drm_fdinfo: Extract ignore_space() Lucas De Marchi
2024-05-06 20:21   ` Umesh Nerlige Ramappa
2024-05-04  6:46 ` [PATCH i-g-t v3 02/13] lib/igt_drm_fdinfo: Allow any number of spaces before unit Lucas De Marchi
2024-05-06 20:28   ` Umesh Nerlige Ramappa
2024-05-06 20:32     ` Umesh Nerlige Ramappa
2024-05-06 20:38       ` Lucas De Marchi
2024-05-04  6:46 ` [PATCH i-g-t v3 03/13] fixup! " Lucas De Marchi
2024-05-06 20:33   ` Umesh Nerlige Ramappa
2024-05-04  6:46 ` [PATCH i-g-t v3 04/13] lib/igt_drm_fdinfo: Stop passing key twice Lucas De Marchi
2024-05-04  6:46 ` [PATCH i-g-t v3 05/13] lib/igt_drm_fdinfo: Remove prefix arg from parse functions Lucas De Marchi
2024-05-04  6:46 ` [PATCH i-g-t v3 06/13] lib/igt_drm_fdinfo: Parse drm-cycles Lucas De Marchi
2024-05-07  1:11   ` Umesh Nerlige Ramappa
2024-05-04  6:46 ` [PATCH i-g-t v3 07/13] lib/igt_drm_fdinfo: Start tracking available engine keys Lucas De Marchi
2024-05-07  1:14   ` Umesh Nerlige Ramappa
2024-05-04  6:46 ` [PATCH i-g-t v3 08/13] treewide: Rename engine busyness variables Lucas De Marchi
2024-05-08 18:45   ` Umesh Nerlige Ramappa
2024-05-21 13:47     ` Lucas De Marchi
2024-05-04  6:46 ` [PATCH i-g-t v3 09/13] lib/igt_drm_clients: Move engine fields to substruct Lucas De Marchi
2024-05-08 18:45   ` Umesh Nerlige Ramappa
2024-05-04  6:46 ` [PATCH i-g-t v3 10/13] lib/igt_drm_clients: Record drm-cycles Lucas De Marchi
2024-05-08 18:48   ` Umesh Nerlige Ramappa
2024-05-04  6:46 ` [PATCH i-g-t v3 11/13] lib/igt_drm_fdinfo: Parse drm-total-cycles Lucas De Marchi
2024-05-08 18:49   ` Umesh Nerlige Ramappa
2024-05-04  6:46 ` [PATCH i-g-t v3 12/13] lib/igt_drm_clients: Record total cycles Lucas De Marchi
2024-05-08 19:01   ` Umesh Nerlige Ramappa
2024-05-08 19:07     ` Umesh Nerlige Ramappa [this message]
2024-05-04  6:46 ` [PATCH i-g-t v3 13/13] gputop: Add support to drm-cycles/drm-total-cycles Lucas De Marchi
2024-05-08 19:11   ` Umesh Nerlige Ramappa
2024-05-04  7:31 ` ✓ Fi.CI.BAT: success for gputop: Add support for xe (rev4) Patchwork
2024-05-04  7:36 ` ✓ CI.xeBAT: " Patchwork
2024-05-04  8:33 ` ✗ CI.xeFULL: failure " Patchwork
2024-05-04 12:50 ` ✗ Fi.CI.IGT: " Patchwork
2024-05-06 10:37 ` [PATCH i-g-t v3 00/12] gputop: Add support for xe Tvrtko Ursulin
2024-05-06 20:40   ` Lucas De Marchi
2024-05-08 16:25 ` (subset) " Lucas De Marchi

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=ZjvNfMUqWvTaRWAG@orsosgc001 \
    --to=umesh.nerlige.ramappa@intel.com \
    --cc=igt-dev@lists.freedesktop.org \
    --cc=lucas.demarchi@intel.com \
    --cc=tursulin@ursulin.net \
    /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