https://bugs.freedesktop.org/show_bug.cgi?id=97879
Marek Olšák changed:
What|Removed |Added
Assignee|mesa-dev@lists.freedesktop.
https://bugs.freedesktop.org/show_bug.cgi?id=97879
andrei.demin1...@gmail.com changed:
What|Removed |Added
CC||andrei.demin1...@gmail.com
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Captain Crutches changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
libgra...@gmail.com changed:
What|Removed |Added
CC||libgra...@gmail.com
--
You are
https://bugs.freedesktop.org/show_bug.cgi?id=97879
David Ortner changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
matt...@familycampground.org changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #60 from Iaroslav Andrusyak ---
if it help rocket league in wine(gallium-nine) works fine without hangs
--
You are receiving this mail because:
You are the assignee for the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #59 from Andreas Hartmetz ---
Another random guess: Maybe shader compilation is a problem insofar that it
blocks in a different GL API call than in other drivers, which causes some lock
to be held for much
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #58 from Vladislav Egorov ---
Correction - in fact I only tested radeon+radeonsi pair. I will try
amdgpu+radeonsi later.
--
You are receiving this mail because:
You are the assignee for the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #57 from Vladislav Egorov ---
Simple way to reproduce the bug - launch the game, then go to "Options" menu
and get multi-second (>5s) freeze.
I've tried to launch Rocket League on several GPUs. Graphics
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Clément Guérin changed:
What|Removed |Added
CC||geecko@free.fr
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #56 from Grazvydas Ignotas ---
Is the async I/O thread doing a lot of memory allocations?
If so, perhaps the malloc implementation is slowed down by having large amount
of small allocs/frees from shader compiles
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #55 from Timothee Besset ---
Rocket League uses an async I/O thread to stream in content in the background.
That thread works off of a queue and only does disk reads and decompression (it
doesn't issue any OpenGL
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #54 from Michel Dänzer ---
(In reply to Marek Olšák from comment #52)
> 2) Make a screenshot of the sysprof window and send it to the game developer.
Please save the profile in sysprof and send the saved data
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #53 from Timothee Besset ---
Hello! I have started working on this. I haven't found the root cause yet but I
will update here when I have something.
(For context, I did the initial port work for Psyonix. I just
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #52 from Marek Olšák ---
We don't need a debug build. We just need:
1) One person to run the debug build and use sysprof to capture where the CPU
is spending time during the freeze.
2) Make a screenshot of the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
m...@pepelino.de changed:
What|Removed |Added
CC||m...@pepelino.de
--
You are
https://bugs.freedesktop.org/show_bug.cgi?id=97879
himl...@gmx.de changed:
What|Removed |Added
CC||himl...@gmx.de
--
You are receiving
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #51 from Jani Kärkkäinen ---
Sent a support ticket to Psyonix about this (and the request for a debug
build). Hopefully a random persons support ticket gets to the dev team and they
deem it something that's
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Karol Herbst changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #50 from Marek Olšák ---
It would be useful to have a debug build of the game and run it with a profiler
or debugger to see where it's looping.
--
You are receiving this mail because:
You are the assignee for the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #49 from i...@posteo.net ---
(In reply to Jani Kärkkäinen from comment #48)
> Using AMDGPU-PRO the hangs are non-existent. So there must be SOMETHING in
> the whole mesa-driver stack, that causes the hangs, if not the GL drivers
>
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #48 from Jani Kärkkäinen ---
Using AMDGPU-PRO the hangs are non-existent. So there must be SOMETHING in the
whole mesa-driver stack, that causes the hangs, if not the GL drivers
themselves.
--
You are
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #47 from Marek Olšák ---
The freezes are not caused by shader compilation. I don't know what's causing
them. They are too long (even 10 seconds). A CPU profiler shows the time is not
spent in the driver. It's spent
https://bugs.freedesktop.org/show_bug.cgi?id=97879
John Brooks changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
George Billios changed:
What|Removed |Added
CC||gbill...@gmail.com
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #46 from George Billios ---
This is also valid for Trine 3.
Big delay to start ~5mins
setting MESA_SHADER_CAPTURE_PATH results in about 16k files!!!
specs
i7 860
Fury R9
4.7-staging kernel
mesa-git Mesa
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #45 from Gregor Münch ---
No change with GIT of today. Slowdowns remain the same.
--
You are receiving this mail because:
You are the assignee for the bug.___
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Jani Kärkkäinen changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #44 from Jani Kärkkäinen ---
I'm quite sure I'm getting this as well. I'm however on a HD6850, so that'd be
the r600 driver I believe?
Anything I can do to help pinpoint the culprit?
Some specs:
OpenGL
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #43 from Steven ---
I also experience the issue. If someone can explain or point me to how I can
profile it I can also try to provide some api traces.
I'm running
Mesa 12.0.3
OpenGL renderer string: Gallium
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #42 from Evan Black ---
Can't really contribute much in terms of any of the tracing stuff; just
dropping my specs here as I have similar issues.
Core i5 4690k
R9 285
8 GB Memory
I've tried it both on my SSD and
https://bugs.freedesktop.org/show_bug.cgi?id=97879
hofmann.zach...@gmail.com changed:
What|Removed |Added
CC||hofmann.zach...@gmail.com
--
https://bugs.freedesktop.org/show_bug.cgi?id=97879
John-Michael Mulesa changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #41 from Marek Olšák ---
Yeah, the stalls are pretty small with apitrace. I've just pushed patches that
should improve compile times for the GLSL compiler. Before that, the GLSL
compilation speed always decreased
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #40 from Michel Dänzer ---
(In reply to Stefano Cipriani from comment #39)
> https://drive.google.com/open?id=0B41ZZ4daaP9hTmNDaUl2MHFWQlE
While replaying this trace, I only see pauses of fractions of seconds
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Stefano Cipriani changed:
What|Removed |Added
CC||cip9...@gmail.com
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #39 from Stefano Cipriani ---
Playing against bots with an AMD r9 m265x (cape verde) using DRI_PRIME=1
rendered via Intel HD Graphics 4600 the game it's not playable for about 30+
seconds, bot cars start to one
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #38 from Vedran Miletić ---
(In reply to Micael Bergeron from comment #37)
> The number of shaders is quite astonishing.
>
> Could using the r600 shader compiler LLVM (--enable-r600-llvm-compiler) fix
> this?
>
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Timothee Besset changed:
What|Removed |Added
CC||tt...@ttimo.net
--
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #37 from Micael Bergeron ---
The number of shaders is quite astonishing.
Could using the r600 shader compiler LLVM (--enable-r600-llvm-compiler) fix
this?
As for the future, I think a persistent shader
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #36 from Silvan Jegen ---
(In reply to Marek Olšák from comment #35)
> Well, it's unreal engine 3, so it doesn't surprise me that it compiles
> shaders on demand. All UE3 games are affected in the same way.
>
>
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #35 from Marek Olšák ---
Well, it's unreal engine 3, so it doesn't surprise me that it compiles shaders
on demand. All UE3 games are affected in the same way.
Possible solution 1:
- persistent shader cache on the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #34 from Micael Bergeron ---
Created attachment 127319
--> https://bugs.freedesktop.org/attachment.cgi?id=127319=edit
Shaders output folfer
MESA_SHADER_CAPTURE_PATH output folder.
--
You are receiving
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #33 from Marek Olšák ---
The traces don't work. Let's assume it's an apitrace bug.
Running the traces can be done with: glretrace --benchmark [trace file]
glretrace is part of apitrace.
We can at least profile the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #32 from Micael Bergeron ---
(In reply to Marek Olšák from comment #31)
> Please create apitrace while this environment variable is set:
> MESA_EXTENSION_OVERRIDE="-GL_ARB_buffer_storage
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #31 from Marek Olšák ---
Please create apitrace while this environment variable is set:
MESA_EXTENSION_OVERRIDE="-GL_ARB_buffer_storage -GL_AMD_pinned_memory"
Then check that the apitrace replays correctly. If it
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Vedran Rodic changed:
What|Removed |Added
CC||vro...@gmail.com
--
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #30 from Michel Dänzer ---
(In reply to Eero Tamminen from comment #20)
> Apitrace's own CPU overhead is so high that it's not very good for
> identifying CPU bottlenecks.
That may be true in general, but taking
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #29 from Silvan Jegen ---
(In reply to Micael Bergeron from comment #28)
> I asked Psyonix for the debug symbols bug had no response.
> http://psyonix.com/forum/viewtopic.php?f=36=27894
Maybe you can add a link to
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #28 from Micael Bergeron ---
I can reproduce this every time.
Using amdgpu-pro seems to fix the problem.
I asked Psyonix for the debug symbols bug had no response.
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #27 from Eero Tamminen ---
(In reply to Silvan Jegen from comment #22)
> Created attachment 126796 [details]
> perf report of RocketLeague stalling/freezing
Overview:
-
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #26 from Silvan Jegen ---
I generated the report and uploaded the result.
I may have hit a bug in perf while doing it. "perf report" was blocking on a
pread64 call on /dev/dri/card0 when creating the report. I had
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #25 from Silvan Jegen ---
Created attachment 126813
--> https://bugs.freedesktop.org/attachment.cgi?id=126813=edit
perf report of RocketLeague stalling/freezing, including callgraphs
--
You are receiving this
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #24 from Silvan Jegen ---
(In reply to Michel Dänzer from comment #23)
> Please pass --call-graph to perf record (you may need to play with the
> different methods supported by that to find the one which works best
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #23 from Michel Dänzer ---
Please pass --call-graph to perf record (you may need to play with the
different methods supported by that to find the one which works best for you,
see perf record --help) and perf
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #22 from Silvan Jegen ---
Created attachment 126796
--> https://bugs.freedesktop.org/attachment.cgi?id=126796=edit
perf report of RocketLeague stalling/freezing
--
You are receiving this mail because:
You are
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #21 from Silvan Jegen ---
(In reply to Eero Tamminen from comment #20)
> Best would be to do (e.g. from SSH console):
> # perf record -a
> ^C
>
> During the game freeze.
I have a dual screen setup and ran
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #20 from Eero Tamminen ---
Apitrace's own CPU overhead is so high that it's not very good for identifying
CPU bottlenecks.
Best would be to do (e.g. from SSH console):
# perf record -a
^C
During the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Alexander Tsoy changed:
What|Removed |Added
CC||alexan...@tsoy.me
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #19 from Tobias Droste ---
And I added screenshots of the profile for a few seconds where the game is
running fine.
I figured that it might be interesting where the difference between good and
bad is.
--
You are
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #18 from Tobias Droste ---
Created attachment 126773
--> https://bugs.freedesktop.org/attachment.cgi?id=126773=edit
Profile of a few seconds in the middle of the game (only radeonsi)
--
You are receiving this mail
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #17 from Tobias Droste ---
Created attachment 126772
--> https://bugs.freedesktop.org/attachment.cgi?id=126772=edit
Profile of a few seconds in the middle of the game (all components)
--
You are receiving this
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #16 from Tobias Droste ---
I tried to do some profiling but with callgrind it's impossible because after
half an hour I'm not even in the game creation menu.
I tried zoom as an alternative (never used it before) and
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #14 from Tobias Droste ---
Created attachment 126770
--> https://bugs.freedesktop.org/attachment.cgi?id=126770=edit
Profile of the the first few seconds of a game (all components)
--
You are receiving this mail
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #15 from Tobias Droste ---
Created attachment 126771
--> https://bugs.freedesktop.org/attachment.cgi?id=126771=edit
Profile of the the first few seconds of a game (only radeonsi)
--
You are receiving this mail
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #13 from hofmann.zach...@gmail.com ---
I can also confirm this problem with Radeon R7 250 (radeonsi), Mesa 12.0.2,
LLVM 3.8.1 and kernel version 4.6.0.
--
You are receiving this mail because:
You are the assignee for the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #12 from Michel Dänzer ---
(In reply to Andreas Hartmetz from comment #4)
> Assuming the problem was shader compilation, what could be done about it,
> though? Optimizing shader compilation by a factor of 10 seems
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #11 from Gregor Münch ---
Experiencing same problem with Radeon HD 7970 Mesa Git radeonsi, LLVM Git,
Linux 4.8 rc6.
The Hangs are always there when:
-start of the match 5-7sec
-multiple times within the 1st
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #10 from Silvan Jegen ---
(In reply to Michel Dänzer from comment #3)
> (In reply to Silvan Jegen from comment #2)
> > Just to clarify: the trace also includes loading of the game itself (which
> > takes a long
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #9 from Tobias Droste ---
Ah should have mentioned it:
This is with radeon+radeonsi (no amdpgu) so it's probably not the kernel.
--
You are receiving this mail because:
You are the assignee for the
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #8 from Tobias Droste ---
On the first screenshot you can clearly see the FPS going down to 0 multiple
times.
Though looking at the graph only the first 2 drops could be explained by shader
compiles if I interpret
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #7 from Tobias Droste ---
Created attachment 126717
--> https://bugs.freedesktop.org/attachment.cgi?id=126717=edit
Screenshot with GALLIUM_HUD of the first 2min30s of the game (good)
--
You are receiving this mail
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #6 from Tobias Droste ---
Created attachment 126716
--> https://bugs.freedesktop.org/attachment.cgi?id=126716=edit
Screenshot with GALLIUM_HUD of the first 1min30s of the game (good)
--
You are receiving this mail
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #5 from Tobias Droste ---
Created attachment 126715
--> https://bugs.freedesktop.org/attachment.cgi?id=126715=edit
Screenshot with GALLIUM_HUD of the first 10s of the game (bad)
--
You are receiving this mail
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #4 from Andreas Hartmetz ---
I have the same problem. Assuming the problem was shader compilation, what
could be done about it, though? Optimizing shader compilation by a factor of 10
seems unrealistic, a disk
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #3 from Michel Dänzer ---
(In reply to Silvan Jegen from comment #2)
> Just to clarify: the trace also includes loading of the game itself (which
> takes a long time too) as well as in-game menu navigation.
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Frederic Romagne changed:
What|Removed |Added
CC|
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Vedran Miletić changed:
What|Removed |Added
CC||ved...@miletic.net
https://bugs.freedesktop.org/show_bug.cgi?id=97879
--- Comment #2 from Silvan Jegen ---
(In reply to Michel Dänzer from comment #1)
> Looks like most of the cycles at the start of the apitrace are spent in the
> GLSL compiler frontend, in particular in do_common_optimization.
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Michel Dänzer changed:
What|Removed |Added
Component|Drivers/Gallium/radeonsi|glsl-compiler
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Kenneth Graunke changed:
What|Removed |Added
QA Contact|mesa-dev@lists.freedesktop.
https://bugs.freedesktop.org/show_bug.cgi?id=97879
Bug ID: 97879
Summary: [amdgpu] Rocket League: long hangs (several seconds)
when loading assets (models/textures/shaders?)
Product: Mesa
Version: 12.0
Hardware: x86-64
83 matches
Mail list logo