All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Auld <matthew.william.auld@gmail.com>
To: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Intel Graphics Development <intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 10/17] drm/i915: Hide unshrinkable context objects from the shrinker
Date: Fri, 2 Aug 2019 17:01:05 +0100	[thread overview]
Message-ID: <CAM0jSHPqsi6Z4Nos93PRZztAOGMam8qTyU5+teyVNQyiEAjjJA@mail.gmail.com> (raw)
In-Reply-To: <20190730133035.1977-11-chris@chris-wilson.co.uk>

On Tue, 30 Jul 2019 at 14:31, Chris Wilson <chris@chris-wilson.co.uk> wrote:
>
> The shrinker cannot touch objects used by the contexts (logical state
> and ring). Currently we mark those as "pin_global" to let the shrinker
> skip over them, however, if we remove them from the shrinker lists
> entirely, we don't event have to include them in our shrink accounting.
>
> By keeping the unshrinkable objects in our shrinker tracking, we report
> a large number of objects available to be shrunk, and leave the shrinker
> deeply unsatisfied when we fail to reclaim those. The shrinker will
> persist in trying to reclaim the unavailable objects, forcing the system
> into a livelock (not even hitting the dread oomkiller).
>
> v2: Extend unshrinkable protection for perma-pinned scratch and guc
> allocations (Tvrtko)
> v3: Notice that we should be pinned when marking unshrinkable and so the
> link cannot be empty; merge duplicate paths.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2019-08-02 16:01 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-30 13:30 Quick and dirty intel_gt_pm.c rebase Chris Wilson
2019-07-30 13:30 ` [PATCH 01/17] drm/i915/execlists: Always clear pending&inflight requests on reset Chris Wilson
2019-08-01  8:08   ` Andi Shyti
2019-08-01  8:13     ` Chris Wilson
2019-07-30 13:30 ` [PATCH 02/17] drm/i915: Allow sharing the idle-barrier from other kernel requests Chris Wilson
2019-07-30 13:30 ` [PATCH 03/17] drm/i915: Flush extra hard after writing relocations through the GTT Chris Wilson
2019-07-30 13:30 ` [PATCH 04/17] drm/i915: Use drm_i915_private directly from drv_get_drvdata() Chris Wilson
2019-08-05 17:05   ` Andi Shyti
2019-08-05 18:01     ` Chris Wilson
2019-07-30 13:30 ` [PATCH 05/17] drm/i915/gem: Make caps.scheduler static Chris Wilson
2019-08-05 17:08   ` Andi Shyti
2019-08-05 18:07     ` Chris Wilson
2019-07-30 13:30 ` [PATCH 06/17] drm/i915: Move aliasing_ppgtt underneath its i915_ggtt Chris Wilson
2019-07-30 13:58   ` Tvrtko Ursulin
2019-07-30 14:12     ` Chris Wilson
2019-07-30 13:30 ` [PATCH 07/17] drm/i915/gt: Provide a local intel_context.vm Chris Wilson
2019-07-30 13:30 ` [PATCH 08/17] drm/i915: Remove lrc default desc from GEM context Chris Wilson
2019-07-30 22:57   ` Kumar Valsan, Prathap
2019-07-30 13:30 ` [PATCH 09/17] drm/i915: Push the ring creation flags to the backend Chris Wilson
2019-08-05 17:08   ` Andi Shyti
2019-09-02 13:59     ` Tvrtko Ursulin
2019-09-06 18:18       ` Chris Wilson
2019-09-02 14:17   ` Tvrtko Ursulin
2019-07-30 13:30 ` [PATCH 10/17] drm/i915: Hide unshrinkable context objects from the shrinker Chris Wilson
2019-08-02 16:01   ` Matthew Auld [this message]
2019-07-30 13:30 ` [PATCH 11/17] drm/i915/gt: Move the [class][inst] lookup for engines onto the GT Chris Wilson
2019-07-30 13:30 ` [PATCH 12/17] drm/i915: Use intel_engine_lookup_user for probing HAS_BSD etc Chris Wilson
2019-08-05 17:08   ` Andi Shyti
2019-07-30 13:30 ` [PATCH 13/17] drm/i915: Isolate i915_getparam_ioctl() Chris Wilson
2019-08-05 17:09   ` Andi Shyti
2019-07-30 13:30 ` [PATCH 14/17] drm/i915: Only include active engines in the capture state Chris Wilson
2019-07-30 13:30 ` [PATCH 15/17] drm/i915: Flush the freed object list on file close Chris Wilson
2019-08-02 17:00   ` Matthew Auld
2019-08-02 19:46     ` Chris Wilson
2019-07-30 13:30 ` [PATCH 16/17] drm/i915: Make debugfs/per_file_stats scale better Chris Wilson
2019-07-30 13:30 ` [PATCH 17/17] drm/i915/gt: Extract GT runtime power management from intel_pm.c Chris Wilson
2019-07-30 14:00 ` ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/17] drm/i915/execlists: Always clear pending&inflight requests on reset Patchwork
2019-07-30 14:09 ` ✗ Fi.CI.SPARSE: " Patchwork
2019-07-30 14:38 ` ✗ Fi.CI.BAT: failure " 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=CAM0jSHPqsi6Z4Nos93PRZztAOGMam8qTyU5+teyVNQyiEAjjJA@mail.gmail.com \
    --to=matthew.william.auld@gmail.com \
    --cc=chris@chris-wilson.co.uk \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.