All of lore.kernel.org
 help / color / mirror / Atom feed
From: bugzilla-daemon@kernel.org
To: dri-devel@lists.freedesktop.org
Subject: [Bug 221106] New: [TTM] Buffer eviction failed - associated with screen freezes with QXL/Spice
Date: Thu, 19 Feb 2026 20:46:49 +0000	[thread overview]
Message-ID: <bug-221106-2300@https.bugzilla.kernel.org/> (raw)

https://bugzilla.kernel.org/show_bug.cgi?id=221106

            Bug ID: 221106
           Summary: [TTM] Buffer eviction failed - associated with screen
                    freezes with QXL/Spice
           Product: Drivers
           Version: 2.5
          Hardware: All
                OS: Linux
            Status: NEW
          Severity: normal
          Priority: P3
         Component: Video(DRI - non Intel)
          Assignee: drivers_video-dri@kernel-bugs.osdl.org
          Reporter: devzero@web.de
        Regression: No

Hello, 

i opened up a bugticket at https://bugzilla.proxmox.com/show_bug.cgi?id=7320 ,
which was closed with the notice, that nobody would probably fix QXL driver
issues anymore. 

as we can see, spice qxl is much better quality then virtio:
https://lindi.iki.fi/lindi/qxl/spice_qxl_vs_virtio.webm, so i don't want to
give up that early. 

from my suspicion, i'm not sure if this is only a qxl driver issue but not a
memory management / fragmentation issue around TTM, too - as we have these
messages whenever there are freezes:

[  407.915718] [TTM] Buffer eviction failed
[  690.692852] hrtimer: interrupt took 5425371 ns
[  997.482081] [TTM] Buffer eviction failed
[ 1021.034156] [TTM] Buffer eviction failed
[ 2027.215362] input: spice vdagent tablet as /devices/virtual/input/input9
[ 2481.259265] NOTICE: Automounting of tracing to debugfs is deprecated and
will be removed in 2030
[ 3439.716485] [TTM] Buffer eviction failed

i see a lot of development has been with TTM component, too.

in proxmox, i increased virtual qxl/spice graphics card memory from the default
of 16mb to 32mb and things running much more stable/reliable/smoothly with
that, i could not yet trigger longer freezes like with 16mb, so the question
is, what happens here and why - and could perhapssomeone with deeper knowledge
have a look on what's happening here and what's causing the buffer eviction
failures. the happen in sync with the gui freezes. 

thank you

-- 
You may reply to this email to add a comment.

You are receiving this mail because:
You are watching the assignee of the bug.

                 reply	other threads:[~2026-02-19 20:46 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=bug-221106-2300@https.bugzilla.kernel.org/ \
    --to=bugzilla-daemon@kernel.org \
    --cc=dri-devel@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.