Skip to content

RFC Per client engine busyness

Tvrtko Ursulin intel-gfx 1 version In review

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 RFC Latest8 patches 14 repliesIn review

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/8drm/i915: Switch context id allocation directoy to xarraydrivers/gpu/drm/i915/gem/i915_gem_context.c drivers/gpu/drm/i915/gem/selftests/mock_context.c drivers/gpu/drm/i915/i915_drv.h+25 -351 reply
2/8drm/i915: Reference count struct drm_i915_file_privatedrivers/gpu/drm/i915/gem/i915_gem_context.c drivers/gpu/drm/i915/i915_drv.c drivers/gpu/drm/i915/i915_drv.h +1 more+17 -72 replies
3/8drm/i915: Expose list of clients in sysfsdrivers/gpu/drm/i915/i915_drv.h drivers/gpu/drm/i915/i915_gem.c drivers/gpu/drm/i915/i915_sysfs.c+155 -63 replies
4/8drm/i915: Update client name on context createdrivers/gpu/drm/i915/gem/i915_gem_context.c drivers/gpu/drm/i915/i915_drv.h drivers/gpu/drm/i915/i915_gem.c+39 -70 replies
5/8drm/i915: Track per-context engine busynessdrivers/gpu/drm/i915/gt/intel_context.c drivers/gpu/drm/i915/gt/intel_context.h drivers/gpu/drm/i915/gt/intel_context_types.h +2 more+100 -82 replies
6/8drm/i915: Track all user contexts per clientdrivers/gpu/drm/i915/gem/i915_gem_context.c drivers/gpu/drm/i915/gem/i915_gem_context_types.h drivers/gpu/drm/i915/i915_drv.h +1 more+53 -30 replies
7/8drm/i915: Contexts can use struct pid stored in the clientdrivers/gpu/drm/i915/gem/i915_gem_context.c drivers/gpu/drm/i915/gem/i915_gem_context_types.h drivers/gpu/drm/i915/i915_debugfs.c +1 more+11 -252 replies
8/8drm/i915: Expose per-engine client busynessdrivers/gpu/drm/i915/i915_drv.h drivers/gpu/drm/i915/i915_gem.c+97 -14 replies

Reviews trailers per patch

2 of 8 patches have a Reviewed-by or Acked-by.

PatchChris Wilson
1/8R-b
2/8R-b
3/8
4/8
5/8
6/8
7/8
8/8

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.

Read the v1 thread

Cover letter [Intel-gfx] [RFC 0/8] Per client engine busyness

From: Tvrtko Ursulin <[email protected]>

Another re-spin of the per-client engine busyness series. Highlights from this version:

* Now tracks GPU time for clients who exit with GPU work left running.
* No more global toggle - it is now constantly on.

Internally we track time spent on engines for each struct intel_context. This can serve as a building block for several features from the want list:
smarter scheduler decisions, getrusage(2)-like per-GEM-context functionality wanted by some customers, cgroups controller, dynamic SSEU tuning,...

Externally, in sysfs, we expose time spent on GPU per client and per engine class.

Sysfs interface enables us to implement a "top-like" tool for GPU tasks. Or with a "screenshot":
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
intel-gpu-top - 906/ 955 MHz; 0% RC6; 5.30 Watts; 933 irqs/s

IMC reads: 4414 MiB/s
IMC writes: 3805 MiB/s

ENGINE BUSY MI_SEMA MI_WAIT
Render/3D/0 93.46% |████████████████████████████████▋ | 0% 0%
Blitter/0 0.00% | | 0% 0%
Video/0 0.00% | | 0% 0%
VideoEnhance/0 0.00% | | 0% 0%

PID NAME Render/3D Blitter Video VideoEnhance

 2733       neverball |██████▌     ||            ||            ||            |
 2047            Xorg |███▊        ||            ||            ||            |
 2737        glxgears |█▍          ||            ||            ||            |
 2128           xfwm4 |            ||            ||            ||            |
 2047            Xorg |            ||            ||            ||            |

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Implementation wise we add a a bunch of files in sysfs like:

	# cd /sys/class/drm/card0/clients/
	# tree
	.
	├── 7
	│   ├── busy
	│   │   ├── 0
	│   │   ├── 1
	│   │   ├── 2
	│   │   └── 3
	│   ├── name
	│   └── pid
	├── 8
	│   ├── busy
	│   │   ├── 0
	│   │   ├── 1
	│   │   ├── 2
	│   │   └── 3
	│   ├── name
	│   └── pid
	├── 9
	│   ├── busy
	│   │   ├── 0
	│   │   ├── 1
	│   │   ├── 2
	│   │   └── 3
	│   ├── name
	│   └── pid
	└── enable_stats

Files in 'busy' directories are numbered using the engine class ABI values and they contain accumulated nanoseconds each client spent on engines of a respective class.

I will post the corresponding patch to intel_gpu_top for reference as well.

Tvrtko Ursulin (8):
drm/i915: Switch context id allocation directoy to xarray drm/i915: Reference count struct drm_i915_file_private drm/i915: Expose list of clients in sysfs drm/i915: Update client name on context create drm/i915: Track per-context engine busyness drm/i915: Track all user contexts per client drm/i915: Contexts can use struct pid stored in the client drm/i915: Expose per-engine client busyness

 drivers/gpu/drm/i915/gem/i915_gem_context.c   | 113 ++++++---
 .../gpu/drm/i915/gem/i915_gem_context_types.h |  16 +-
 .../gpu/drm/i915/gem/selftests/mock_context.c |   3 +-
 drivers/gpu/drm/i915/gt/intel_context.c       |  20 ++
 drivers/gpu/drm/i915/gt/intel_context.h       |  11 +
 drivers/gpu/drm/i915/gt/intel_context_types.h |   9 +
 drivers/gpu/drm/i915/gt/intel_engine_cs.c     |  16 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c           |  52 +++-
 drivers/gpu/drm/i915/i915_debugfs.c           |   7 +-
 drivers/gpu/drm/i915/i915_drv.c               |   4 -
 drivers/gpu/drm/i915/i915_drv.h               |  66 ++++-
 drivers/gpu/drm/i915/i915_gem.c               | 236 +++++++++++++++++-
 drivers/gpu/drm/i915/i915_gpu_error.c         |   6 +-
 drivers/gpu/drm/i915/i915_sysfs.c             |   8 +
 14 files changed, 486 insertions(+), 81 deletions(-)
Signature · 6 lines
2.20.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx