intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Ben Widawsky <ben@bwidawsk.net>
To: intel-gfx@lists.freedesktop.org
Cc: Ben Widawsky <ben@bwidawsk.net>,
	"Lecluse, Philippe" <Philippe.Lecluse@intel.com>
Subject: [PATCH 00/15] [RFC] Forced throttling/scheduling
Date: Fri, 18 Nov 2011 18:24:17 -0800	[thread overview]
Message-ID: <1321669472-8045-1-git-send-email-ben@bwidawsk.net> (raw)

This code is currently living on my personal git repo:
git://people.freedesktop.org/~bwidawsk/drm-intel forced_throttling

Since these are RFC, I haven't spent too much time cleaning things up.
Feel free to comment on typos, comments you feel are missing, etc. I
also haven't spent any time running the standard kernel tests, kmemleak
and such - I intend to do so while these are reviewed here.

There are two main "scheduler" types implemented in this patch. What I
refer to as a fairness scheduler, and a batch scheduler. The fairness
scheduler is currently implemented on batch granularity but that is not
guaranteed going forward. The batch scheduler is a way to set batch
limits per pid. Refer to the relevant patch for more details.

It is my opinion that the fairness scheduler isn't terribly interesting
except to prevent badly written, or malicious apps. For example, a 3d
app which queues up a ton of work but never calls glxSwapBuffer.

The batch scheduler is also somewhat uninteresting as the values it uses
require proper tuning and will vary from system to system, and even then
depending on what's currently running. But like the fairness one, this
too has its applications.

Most comments and feedback are welcome.


Ben Widawsky (13):
  drm/i915: relative_constants_mode race fix
  drm/i915: drop lock support for  i915_wait_request
  drm/i915: remove mm structure from file_priv
  drm/i915: Keep track of drm_file in file_priv
  drm/i915: Keep track of request counts
  drm/i915: fairness
  drm/i915: Keep track of open i915 clients
  drm/i915: debugfs entry for i915 clients
  drm/i915: debugfs entries for scheduler params
  drm/i915: infrastructure to support scheduler types
  drm/i915: get/set scheduler type from debugfs
  drm/i915: Implement batch scheduler
  drm/i915: Add handling for batch parameters in debugfs

Daniel Vetter (2):
  drm/i915: refactor debugfs open function
  drm/i915: refactor debugfs create functions

 drivers/gpu/drm/i915/i915_debugfs.c        |  343 +++++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_dma.c            |   18 ++-
 drivers/gpu/drm/i915/i915_drv.c            |    5 +
 drivers/gpu/drm/i915/i915_drv.h            |   41 +++-
 drivers/gpu/drm/i915/i915_gem.c            |   90 ++++++--
 drivers/gpu/drm/i915/i915_gem_execbuffer.c |  194 +++++++++++++---
 drivers/gpu/drm/i915/intel_overlay.c       |    4 +-
 7 files changed, 568 insertions(+), 127 deletions(-)

-- 
1.7.7.3

             reply	other threads:[~2011-11-19  2:24 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-11-19  2:24 Ben Widawsky [this message]
2011-11-19  2:24 ` [PATCH 01/15] drm/i915: refactor debugfs open function Ben Widawsky
2011-11-20 18:50   ` Kenneth Graunke
2011-11-19  2:24 ` [PATCH 02/15] drm/i915: refactor debugfs create functions Ben Widawsky
2011-11-19  2:24 ` [PATCH 03/15] drm/i915: relative_constants_mode race fix Ben Widawsky
2011-11-23 22:30   ` Ben Widawsky
2011-11-19  2:24 ` [PATCH 04/15] drm/i915: drop lock support for i915_wait_request Ben Widawsky
2011-11-19  2:24 ` [PATCH 05/15] drm/i915: remove mm structure from file_priv Ben Widawsky
2011-11-19  2:24 ` [PATCH 06/15] drm/i915: Keep track of drm_file in file_priv Ben Widawsky
2011-11-19  2:24 ` [PATCH 07/15] drm/i915: Keep track of request counts Ben Widawsky
2011-11-19  2:24 ` [PATCH 08/15] drm/i915: fairness Ben Widawsky
2011-11-19  2:24 ` [PATCH 09/15] drm/i915: Keep track of open i915 clients Ben Widawsky
2011-11-19  2:24 ` [PATCH 10/15] drm/i915: debugfs entry for " Ben Widawsky
2011-11-19  2:24 ` [PATCH 11/15] drm/i915: debugfs entries for scheduler params Ben Widawsky
2011-11-19  2:24 ` [PATCH 12/15] drm/i915: infrastructure to support scheduler types Ben Widawsky
2011-11-19  2:24 ` [PATCH 13/15] drm/i915: get/set scheduler type from debugfs Ben Widawsky
2011-11-19  2:24 ` [PATCH 14/15] drm/i915: Implement batch scheduler Ben Widawsky
2011-11-19  2:24 ` [PATCH 15/15] drm/i915: Add handling for batch parameters in debugfs Ben Widawsky
2011-11-29 14:30 ` [PATCH 00/15] [RFC] Forced throttling/scheduling Eugeni Dodonov
2012-04-02 18:28 ` Ben Widawsky

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=1321669472-8045-1-git-send-email-ben@bwidawsk.net \
    --to=ben@bwidawsk.net \
    --cc=Philippe.Lecluse@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    /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).