From: Emil Velikov <emil.l.velikov@gmail.com>
To: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Intel Graphics Development <intel-gfx@lists.freedesktop.org>,
ML dri-devel <dri-devel@lists.freedesktop.org>
Subject: Re: [PATCH 00/12] drm: Put drm_display_mode on diet
Date: Thu, 20 Feb 2020 13:21:03 +0000 [thread overview]
Message-ID: <CACvgo50pCb4OafEs9tLm7YEPqHc+BtDAvagRnwjXtZeQDNwUwg@mail.gmail.com> (raw)
In-Reply-To: <20200219203544.31013-1-ville.syrjala@linux.intel.com>
On Wed, 19 Feb 2020 at 20:35, Ville Syrjala
<ville.syrjala@linux.intel.com> wrote:
>
> From: Ville Syrjälä <ville.syrjala@linux.intel.com>
>
> struct drm_display_mode is extremely fat. Put it on diet.
>
> Some stats for the whole series:
>
> 64bit sizeof(struct drm_display_mode):
> 200 -> 136 bytes (-32%)
>
> 64bit bloat-o-meter -c drm.ko:
> add/remove: 1/0 grow/shrink: 29/47 up/down: 893/-1544 (-651)
> Function old new delta
> ...
> Total: Before=189430, After=188779, chg -0.34%
> add/remove: 0/0 grow/shrink: 0/0 up/down: 0/0 (0)
> Data old new delta
> Total: Before=11667, After=11667, chg +0.00%
> add/remove: 0/0 grow/shrink: 0/5 up/down: 0/-16896 (-16896)
> RO Data old new delta
> edid_4k_modes 1000 680 -320
> edid_est_modes 3400 2312 -1088
> edid_cea_modes_193 5400 3672 -1728
> drm_dmt_modes 17600 11968 -5632
> edid_cea_modes_1 25400 17272 -8128
> Total: Before=71239, After=54343, chg -23.72%
>
>
> 64bit bloat-o-meter drm.ko:
> add/remove: 1/0 grow/shrink: 29/52 up/down: 893/-18440 (-17547)
> ...
> Total: Before=272336, After=254789, chg -6.44%
>
>
> 32bit sizeof(struct drm_display_mode):
> 184 -> 120 bytes (-34%)
>
> 32bit bloat-o-meter -c drm.ko
> add/remove: 1/0 grow/shrink: 19/21 up/down: 743/-1368 (-625)
> Function old new delta
> ...
> Total: Before=172359, After=171734, chg -0.36%
> add/remove: 0/0 grow/shrink: 0/0 up/down: 0/0 (0)
> Data old new delta
> Total: Before=4227, After=4227, chg +0.00%
> add/remove: 0/0 grow/shrink: 0/5 up/down: 0/-16896 (-16896)
> RO Data old new delta
> edid_4k_modes 920 600 -320
> edid_est_modes 3128 2040 -1088
> edid_cea_modes_193 4968 3240 -1728
> drm_dmt_modes 16192 10560 -5632
> edid_cea_modes_1 23368 15240 -8128
> Total: Before=59230, After=42334, chg -28.53%
>
> 32bit bloat-o-meter drm.ko:
> add/remove: 1/0 grow/shrink: 19/26 up/down: 743/-18264 (-17521)
> ...
> Total: Before=235816, After=218295, chg -7.43%
>
>
> Some ideas for further reduction:
> - Convert mode->name to a pointer (saves 24/28 bytes in the
> struct but would often require a heap alloc for the name (though
> typical mode name is <10 bytes so still overall win perhaps)
> - Get rid of mode->name entirely? I guess setcrtc & co. is the only
> place where we have to preserve the user provided name, elsewhere
> could pehaps just generate on demand? Not sure how tricky this
> would get.
The series does some great work, with future work reaching the cache
line for 64bit.
Doing much more than that might be an overkill IMHO.
In particular, if we change DRM_DISPLAY_MODE_LEN to 24 we get there,
avoiding the heap alloc/calc on demand fun.
While also ensuring the name is sufficiently large for the next decade or so.
From drm_mode_set_name():
snprintf(mode->name, DRM_DISPLAY_MODE_LEN, "%dx%d%s",
mode->hdisplay, mode->vdisplay, interlaced ? "i" : "");
We change the h/v display from (10^15)-1 to (10^11)-1 which seems reasonable.
Note: haven't checked if name includes the terminating \0, so take
numbers with a grain of salt.
-Emil
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2020-02-20 13:21 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-19 20:35 [PATCH 00/12] drm: Put drm_display_mode on diet Ville Syrjala
2020-02-19 20:35 ` [PATCH 01/12] drm: Nuke mode->hsync Ville Syrjala
2020-02-20 10:55 ` [Intel-gfx] " Emil Velikov
2020-02-21 16:04 ` Ville Syrjälä
2020-02-21 16:55 ` Emil Velikov
2020-02-19 20:35 ` [PATCH 02/12] drm/exynos: Use mode->clock instead of reverse calculating it from the vrefresh Ville Syrjala
2020-02-20 10:56 ` Emil Velikov
2020-02-25 0:49 ` Inki Dae
2020-02-19 20:35 ` [PATCH 03/12] drm/i915: Introduce some local intel_dp variables Ville Syrjala
2020-02-20 11:13 ` [Intel-gfx] " Emil Velikov
2020-02-19 20:35 ` [PATCH 04/12] drm: Nuke mode->vrefresh Ville Syrjala
2020-02-20 12:00 ` Emil Velikov
2020-02-22 12:32 ` Sam Ravnborg
2020-02-24 13:14 ` Ville Syrjälä
2020-02-24 14:14 ` Andrzej Hajda
2020-02-25 11:21 ` Ville Syrjälä
2020-02-25 15:19 ` Andrzej Hajda
2020-02-25 15:45 ` Ville Syrjälä
2020-02-25 19:27 ` Ville Syrjälä
2020-02-25 21:52 ` Linus Walleij
2020-02-19 20:35 ` [PATCH 05/12] drm/msm/dpu: Stop copying around mode->private_flags Ville Syrjala
2020-02-20 11:24 ` Emil Velikov
2020-02-20 15:33 ` Ville Syrjälä
2020-02-20 18:14 ` Daniel Vetter
2020-02-19 20:35 ` [PATCH 06/12] drm: Shrink {width,height}_mm to u16 Ville Syrjala
2020-02-20 12:48 ` [Intel-gfx] " Emil Velikov
2020-02-19 20:35 ` [PATCH 07/12] drm: Shrink mode->type to u8 Ville Syrjala
2020-02-20 18:17 ` [Intel-gfx] " Daniel Vetter
2020-02-19 20:35 ` [PATCH 08/12] drm: Make mode->flags u32 Ville Syrjala
2020-02-19 20:35 ` [PATCH 09/12] drm: Shrink drm_display_mode timings Ville Syrjala
2020-02-20 18:19 ` [Intel-gfx] " Daniel Vetter
2020-02-20 18:47 ` Ville Syrjälä
2020-02-21 16:13 ` Sam Ravnborg
2020-02-21 17:27 ` Sam Ravnborg
2020-02-24 13:06 ` Ville Syrjälä
2020-02-19 20:35 ` [PATCH 10/12] drm: Flatten drm_mode_vrefresh() Ville Syrjala
2020-02-19 20:35 ` [PATCH 11/12] drm: Shrink mode->private_flags Ville Syrjala
2020-02-21 16:15 ` Sam Ravnborg
2020-02-24 13:23 ` Ville Syrjälä
2020-02-19 20:35 ` [PATCH 12/12] drm: pahole struct drm_display_mode Ville Syrjala
2020-02-20 12:53 ` Emil Velikov
2020-02-19 21:18 ` [PATCH 00/12] drm: Put drm_display_mode on diet Ville Syrjälä
2020-02-20 13:21 ` Emil Velikov [this message]
2020-02-20 14:27 ` Ville Syrjälä
2020-02-20 15:34 ` [Intel-gfx] " Ville Syrjälä
2020-02-21 11:32 ` Jani Nikula
2020-02-21 11:43 ` Ville Syrjälä
2020-02-21 14:42 ` Daniel Vetter
2020-02-21 15:40 ` Ville Syrjälä
2020-02-21 16:09 ` Ville Syrjälä
2020-02-21 17:16 ` Daniel Vetter
2020-02-21 17:49 ` Ville Syrjälä
2020-02-20 17:01 ` Emil Velikov
2020-02-21 15:09 ` Linus Walleij
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=CACvgo50pCb4OafEs9tLm7YEPqHc+BtDAvagRnwjXtZeQDNwUwg@mail.gmail.com \
--to=emil.l.velikov@gmail.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=ville.syrjala@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;
as well as URLs for NNTP newsgroup(s).