From: bugzilla-daemon@freedesktop.org
To: dri-devel@lists.freedesktop.org
Subject: [Bug 110781] Radeon: heavy r300 performance drop regression between 11.x and 19.x
Date: Wed, 29 May 2019 15:49:02 +0000 [thread overview]
Message-ID: <bug-110781-502-POTlwEXOzk@http.bugs.freedesktop.org/> (raw)
In-Reply-To: <bug-110781-502@http.bugs.freedesktop.org/>
[-- Attachment #1.1: Type: text/plain, Size: 1865 bytes --]
https://bugs.freedesktop.org/show_bug.cgi?id=110781
--- Comment #5 from Richard Thier <u9vata@gmail.com> ---
Still fast with mesa 17.2.8 and X.Org X Server 1.19.5
The problem is somewhere between 17.x and 19.x mesa versions (and corresponding
xorg).
Also I have made an strace when it is good in one older system to see number of
CREATE and CLOSE ioctl calls (also the number of CS ioctl calls) are a
magnitude smaller than in case of 19.x!
For example 10-20 seconds of glxgears running leads to 9-10 calls to
DRM_IOCTL_RADEON_GEM_CREATE on mesa 17.2.8 while it leads to 708 (!!!) number
of same calls in the same time period on mesa 19.x! This is surely a quite big
of a difference!
The similar pattern in 17.x is never creating a new gem object:
...
ioctl(6, DRM_IOCTL_RADEON_GEM_WAIT_IDLE, 0xbfcf9f04) = 0 <0.000055>
ioctl(6, DRM_IOCTL_RADEON_GEM_BUSY, 0xbfcf9d44) = 0 <0.000022>
ioctl(6, DRM_IOCTL_RADEON_CS, 0xb307d03c) = 0 <0.000089>
ioctl(6, DRM_IOCTL_RADEON_GEM_WAIT_IDLE, 0xbfcf9f04) = 0 <0.000053>
ioctl(6, DRM_IOCTL_RADEON_GEM_BUSY, 0xbfcf9d44) = 0 <0.000023>
ioctl(6, DRM_IOCTL_RADEON_CS, 0xb30910d0) = 0 <0.000095>
ioctl(6, DRM_IOCTL_RADEON_GEM_WAIT_IDLE, 0xbfcf9f04) = 0 <0.000054>
ioctl(6, DRM_IOCTL_RADEON_GEM_BUSY, 0xbfcf9d44) = 0 <0.000023>
ioctl(6, DRM_IOCTL_RADEON_CS, 0xb307d03c) = 0 <0.000090>
...
Sometimes when the *_BUSY ioctl call returns -1, it issues a CREATE, but
otherwise not.
I think GEM is some kind of memory handler for the GPU (just like "ttm" in the
perf output) and I think something have messed up with memory handling schemes
for Mobility Radeon 200M (r300) at some mesa update between 17.x and 19.x.
Will try to bisect a closer version as 17.2.8 is from 2017.12.22 in time...
--
You are receiving this mail because:
You are the assignee for the bug.
[-- Attachment #1.2: Type: text/html, Size: 2748 bytes --]
[-- Attachment #2: Type: text/plain, Size: 159 bytes --]
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
next prev parent reply other threads:[~2019-05-29 15:49 UTC|newest]
Thread overview: 71+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-28 11:51 [Bug 110781] Radeon: heavy r300 performance drop regression between 11.x and 19.x bugzilla-daemon
2019-05-28 11:54 ` bugzilla-daemon
2019-05-28 16:19 ` bugzilla-daemon
2019-05-29 10:16 ` bugzilla-daemon
2019-05-29 10:32 ` bugzilla-daemon
2019-05-29 10:35 ` bugzilla-daemon
2019-05-29 15:49 ` bugzilla-daemon [this message]
2019-05-29 23:17 ` bugzilla-daemon
2019-05-30 12:23 ` bugzilla-daemon
2019-05-31 8:21 ` bugzilla-daemon
2019-06-02 20:42 ` bugzilla-daemon
2019-06-03 8:47 ` bugzilla-daemon
2019-06-03 10:11 ` bugzilla-daemon
2019-06-03 10:49 ` bugzilla-daemon
2019-06-03 12:35 ` bugzilla-daemon
2019-06-03 12:50 ` bugzilla-daemon
2019-06-03 12:50 ` bugzilla-daemon
2019-06-03 13:36 ` bugzilla-daemon
2019-06-03 18:52 ` bugzilla-daemon
2019-06-03 20:19 ` bugzilla-daemon
2019-06-03 20:51 ` bugzilla-daemon
2019-06-04 4:22 ` bugzilla-daemon
2019-06-04 5:50 ` bugzilla-daemon
2019-06-04 6:30 ` bugzilla-daemon
2019-06-04 6:48 ` bugzilla-daemon
2019-06-04 6:53 ` bugzilla-daemon
2019-06-04 7:56 ` bugzilla-daemon
2019-06-04 8:24 ` bugzilla-daemon
2019-06-04 9:43 ` bugzilla-daemon
2019-06-04 10:02 ` bugzilla-daemon
2019-06-04 10:23 ` bugzilla-daemon
2019-06-04 10:27 ` bugzilla-daemon
2019-06-04 10:33 ` bugzilla-daemon
2019-06-04 10:37 ` bugzilla-daemon
2019-06-04 12:43 ` bugzilla-daemon
2019-06-04 23:09 ` bugzilla-daemon
2019-06-05 9:52 ` bugzilla-daemon
2019-06-05 15:10 ` bugzilla-daemon
2019-06-05 16:14 ` bugzilla-daemon
2019-06-05 20:35 ` bugzilla-daemon
2019-06-05 20:50 ` bugzilla-daemon
2019-06-05 21:13 ` bugzilla-daemon
2019-06-05 22:47 ` bugzilla-daemon
2019-06-06 3:02 ` bugzilla-daemon
2019-06-06 17:46 ` bugzilla-daemon
2019-06-06 19:50 ` bugzilla-daemon
2019-06-07 1:48 ` bugzilla-daemon
2019-06-07 6:36 ` bugzilla-daemon
2019-06-07 8:05 ` bugzilla-daemon
2019-06-07 8:22 ` bugzilla-daemon
2019-06-07 8:38 ` bugzilla-daemon
2019-06-07 8:49 ` bugzilla-daemon
2019-06-07 14:43 ` bugzilla-daemon
2019-06-07 14:56 ` bugzilla-daemon
2019-06-07 15:10 ` bugzilla-daemon
2019-06-07 15:20 ` bugzilla-daemon
2019-06-07 15:25 ` bugzilla-daemon
2019-06-07 16:23 ` bugzilla-daemon
2019-06-07 19:23 ` bugzilla-daemon
2019-06-07 20:12 ` bugzilla-daemon
2019-06-08 3:28 ` bugzilla-daemon
2019-06-08 6:51 ` bugzilla-daemon
2019-06-08 16:43 ` bugzilla-daemon
2019-06-10 22:34 ` bugzilla-daemon
2019-06-11 11:23 ` bugzilla-daemon
2019-06-11 17:12 ` bugzilla-daemon
2019-06-11 17:33 ` bugzilla-daemon
2019-06-11 18:24 ` bugzilla-daemon
2019-06-11 23:14 ` bugzilla-daemon
2019-06-12 0:46 ` bugzilla-daemon
2019-06-24 8:44 ` bugzilla-daemon
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-110781-502-POTlwEXOzk@http.bugs.freedesktop.org/ \
--to=bugzilla-daemon@freedesktop.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 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).