search

yshui / picom

A lightweight compositor for X11 with animation support
https://picom.app/
Other
4.18k stars 589 forks source link

A huge performance decrease after v. 10 #967

Open erydit opened 1 year ago

erydit commented 1 year ago

Platform amd Environment

OS: Manjaro Linux x86_64 Kernel: 6.0.11-1-MANJARO DE: Xfce 4.16 WM: Xfwm4 CPU: AMD FX-8350 (8) @ 4.000GHz GPU: AMD ATI Radeon 3000

GPU, drivers, and screen setup

drivers 01:05.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] RS780L [Radeon 3000] Subsystem: Gigabyte Technology Co., Ltd Device d000 Kernel driver in use: radeon Kernel modules: radeon, amdgpu xf86-video-ati 1:19.1.0.r15.g7a6a34af-1 mesa 22.2.4-1
glxinfo -B name of display: :0.0 display: :0 screen: 0 direct rendering: Yes Extended renderer info (GLX_MESA_query_renderer): Vendor: X.Org (0x1002) Device: AMD RS780 (DRM 2.50.0 / 6.0.11-1-MANJARO, LLVM 14.0.6) (0x9616) Version: 22.2.4 Accelerated: yes Video memory: 512MB Unified memory: no Preferred profile: core (0x1) Max core profile version: 3.3 Max compat profile version: 3.0 Max GLES1 profile version: 1.1 Max GLES[23] profile version: 3.0 Memory info (GL_ATI_meminfo): VBO free memory - total: 511 MB, largest block: 511 MB VBO free aux. memory - total: 509 MB, largest block: 509 MB Texture free memory - total: 511 MB, largest block: 511 MB Texture free aux. memory - total: 509 MB, largest block: 509 MB Renderbuffer free memory - total: 511 MB, largest block: 511 MB Renderbuffer free aux. memory - total: 509 MB, largest block: 509 MB Memory info (GL_NVX_gpu_memory_info): Dedicated video memory: 512 MB Total available memory: 1021 MB Currently available dedicated video memory: 511 MB OpenGL vendor string: X.Org OpenGL renderer string: AMD RS780 (DRM 2.50.0 / 6.0.11-1-MANJARO, LLVM 14.0.6) OpenGL core profile version string: 3.3 (Core Profile) Mesa 22.2.4 OpenGL core profile shading language version string: 3.30 OpenGL core profile context flags: (none) OpenGL core profile profile mask: core profile OpenGL version string: 3.0 Mesa 22.2.4 OpenGL shading language version string: 1.30 OpenGL context flags: (none) OpenGL ES profile version string: OpenGL ES 3.0 Mesa 22.2.4 OpenGL ES profile shading language version string: OpenGL ES GLSL ES 3.00

picom version

v10.1

Configuration:

Configuration file \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Shadows \# \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Enabled client-side shadows on windows. Note desktop windows \# (windows with '_NET_WM_WINDOW_TYPE_DESKTOP') never get shadow, \# unless explicitly requested using the wintypes option. \# \# shadow = false shadow = true; \# The blur radius for shadows, in pixels. (defaults to 12) \# shadow-radius = 12 shadow-radius = 7; \# The opacity of shadows. (0.0 - 1.0, defaults to 0.75) \# shadow-opacity = .75 \# The left offset for shadows, in pixels. (defaults to -15) \# shadow-offset-x = -15 shadow-offset-x = -7; \# The top offset for shadows, in pixels. (defaults to -15) \# shadow-offset-y = -15 shadow-offset-y = -7; \# Avoid drawing shadows on dock/panel windows. This option is deprecated, \# you should use the *wintypes* option in your config file instead. \# \# no-dock-shadow = false \# Don't draw shadows on drag-and-drop windows. This option is deprecated, \# you should use the *wintypes* option in your config file instead. \# \# no-dnd-shadow = false \# Red color value of shadow (0.0 - 1.0, defaults to 0). \# shadow-red = 0 \# Green color value of shadow (0.0 - 1.0, defaults to 0). \# shadow-green = 0 \# Blue color value of shadow (0.0 - 1.0, defaults to 0). \# shadow-blue = 0 \# Do not paint shadows on shaped windows. Note shaped windows \# here means windows setting its shape through X Shape extension. \# Those using ARGB background is beyond our control. \# Deprecated, use \# shadow-exclude = 'bounding_shaped' \# or \# shadow-exclude = 'bounding_shaped && !rounded_corners' \# instead. \# \# shadow-ignore-shaped = '' \# Specify a list of conditions of windows that should have no shadow. \# \# examples: \# shadow-exclude = "n:e:Notification"; \# \# shadow-exclude = [] shadow-exclude = [ "name = 'Notification'", "class_g = 'Conky'", "class_g ?= 'Notify-osd'", "class_g = 'Cairo-clock'", "_GTK_FRAME_EXTENTS@:c", "bounding_shaped && !rounded_corners", "_NET_WM_WINDOW_TYPE:a *= '_KDE_NET_WM_WINDOW_TYPE_OVERRIDE'", "class_g = 'firefox' && window_type *= 'dropdown_menu'", "class_g = 'firefox' && argb", ]; \# Specify a X geometry that describes the region in which shadow should not \# be painted in, such as a dock window region. Use \# shadow-exclude-reg = "x10+0+0" \# for example, if the 10 pixels on the bottom of the screen should not have shadows painted on. \# \# shadow-exclude-reg = "" \# Crop shadow of a window fully on a particular Xinerama screen to the screen. \# xinerama-shadow-crop = false \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Fading \# \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Fade windows in/out when opening/closing and when opacity changes, \# unless no-fading-openclose is used. \# fading = false fading = true \# Opacity change between steps while fading in. (0.01 - 1.0, defaults to 0.028) \# fade-in-step = 0.028 fade-in-step = 0.5; \# Opacity change between steps while fading out. (0.01 - 1.0, defaults to 0.03) \# fade-out-step = 0.03 fade-out-step = 0.5; \# The time between steps in fade step, in milliseconds. (> 0, defaults to 10) \# fade-delta = 8 \# Specify a list of conditions of windows that should not be faded. \# fade-exclude = [] \# Do not fade on window open/close. \# no-fading-openclose = false \# Do not fade destroyed ARGB windows with WM frame. Workaround of bugs in Openbox, Fluxbox, etc. \# no-fading-destroyed-argb = false \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Transparency / Opacity \# \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Opacity of inactive windows. (0.1 - 1.0, defaults to 1.0) \# inactive-opacity = 1 \# inactive-opacity = 0.1; \# Opacity of window titlebars and borders. (0.1 - 1.0, disabled by default) \# frame-opacity = 1.0 \# frame-opacity = 0.1; \# Default opacity for dropdown menus and popup menus. (0.0 - 1.0, defaults to 1.0) \# menu-opacity = 0.1; \# Let inactive opacity set by -i override the '_NET_WM_OPACITY' values of windows. \# inactive-opacity-override = true \# inactive-opacity-override = false; \# Default opacity for active windows. (0.0 - 1.0, defaults to 1.0) \# active-opacity = 1.0 \# Dim inactive windows. (0.0 - 1.0, defaults to 0.0) \# inactive-dim = 0.0 \# Specify a list of conditions of windows that should always be considered focused. \# focus-exclude = [] focus-exclude = [ "class_g = 'Cairo-clock'" ]; \# Use fixed inactive dim value, instead of adjusting according to window opacity. \# inactive-dim-fixed = 1.0 \# Specify a list of opacity rules, in the format `PERCENT:PATTERN`, \# like `50:name *= "Firefox"`. picom-trans is recommended over this. \# Note we don't make any guarantee about possible conflicts with other \# programs that set '_NET_WM_WINDOW_OPACITY' on frame or client windows. \# example: \# opacity-rule = [ "80:class_g = 'URxvt'" ]; \# \# opacity-rule = [] \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Background-Blurring \# \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Parameters for background blurring, see the *BLUR* section for more information. \# blur-method = \# blur-size = 12 \# \# blur-deviation = false \# Blur background of semi-transparent / ARGB windows. \# Bad in performance, with driver-dependent behavior. \# The name of the switch may change without prior notifications. \# \# blur-background = true \# Blur background of windows when the window frame is not opaque. \# Implies: \# blur-background \# Bad in performance, with driver-dependent behavior. The name may change. \# \# blur-background-frame = false \# Use fixed blur strength rather than adjusting according to window opacity. \# blur-background-fixed = false \# Specify the blur convolution kernel, with the following format: \# example: \# blur-kern = "5,5,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1"; \# \# blur-kern = '' blur-kern = "3x3box"; \# Exclude conditions for background blur. \# blur-background-exclude = [] blur-background-exclude = [ "window_type = 'dock'", "window_type = 'desktop'", "_GTK_FRAME_EXTENTS@:c" ]; \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# General Settings \# \#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\#\# \# Daemonize process. Fork to background after initialization. Causes issues with certain (badly-written) drivers. daemon = true \# Specify the backend to use: `xrender`, `glx`, or `xr_glx_hybrid`. \# `xrender` is the default one. \# backend = "xrender" backend = "glx" \# Enable/disable VSync. \# vsync = false vsync = true \# Enable remote control via D-Bus. See the *D-BUS API* section below for more details. \# dbus = false \# Try to detect WM windows (a non-override-redirect window with no \# child that has 'WM_STATE') and mark them as active. \# \# mark-wmwin-focused = false mark-wmwin-focused = true; \# Mark override-redirect windows that doesn't have a child window with 'WM_STATE' focused. \# mark-ovredir-focused = false mark-ovredir-focused = true; \# Try to detect windows with rounded corners and don't consider them \# shaped windows. The accuracy is not very high, unfortunately. \# \# detect-rounded-corners = false detect-rounded-corners = true; \# Detect '_NET_WM_OPACITY' on client windows, useful for window managers \# not passing '_NET_WM_OPACITY' of client windows to frame windows. \# \# detect-client-opacity = false detect-client-opacity = true; \# Specify refresh rate of the screen. If not specified or 0, picom will \# try detecting this with X RandR extension. \# \# refresh-rate = 60 refresh-rate = 60 \# Limit picom to repaint at most once every 1 / 'refresh_rate' second to \# boost performance. This should not be used with \# vsync drm/opengl/opengl-oml \# as they essentially does sw-opti's job already, \# unless you wish to specify a lower refresh rate than the actual value. \# \# sw-opti = \# Use EWMH '_NET_ACTIVE_WINDOW' to determine currently focused window, \# rather than listening to 'FocusIn'/'FocusOut' event. Might have more accuracy, \# provided that the WM supports it. \# \# use-ewmh-active-win = false \# Unredirect all windows if a full-screen opaque window is detected, \# to maximize performance for full-screen windows. Known to cause flickering \# when redirecting/unredirecting windows. \# unredir-if-possible = false; \# Delay before unredirecting the window, in milliseconds. Defaults to 0. \# unredir-if-possible-delay = 0 \# Conditions of windows that shouldn't be considered full-screen for unredirecting screen. \# unredir-if-possible-exclude = [] \# Use 'WM_TRANSIENT_FOR' to group windows, and consider windows \# in the same group focused at the same time. \# \# detect-transient = false detect-transient = true \# Use 'WM_CLIENT_LEADER' to group windows, and consider windows in the same \# group focused at the same time. 'WM_TRANSIENT_FOR' has higher priority if \# detect-transient is enabled, too. \# \# detect-client-leader = false detect-client-leader = true \# Resize damaged region by a specific number of pixels. \# A positive value enlarges it while a negative one shrinks it. \# If the value is positive, those additional pixels will not be actually painted \# to screen, only used in blur calculation, and such. (Due to technical limitations, \# with use-damage, those pixels will still be incorrectly painted to screen.) \# Primarily used to fix the line corruption issues of blur, \# in which case you should use the blur radius value here \# (e.g. with a 3x3 kernel, you should use `--resize-damage 1`, \# with a 5x5 one you use `--resize-damage 2`, and so on). \# May or may not work with *--glx-no-stencil*. Shrinking doesn't function correctly. \# \# resize-damage = 1 \# Specify a list of conditions of windows that should be painted with inverted color. \# Resource-hogging, and is not well tested. \# \# invert-color-include = [] \# GLX backend: Avoid using stencil buffer, useful if you don't have a stencil buffer. \# Might cause incorrect opacity when rendering transparent content (but never \# practically happened) and may not work with blur-background. \# My tests show a 15% performance boost. Recommended. \# glx-no-stencil = false \# GLX backend: Avoid rebinding pixmap on window damage. \# Probably could improve performance on rapid window content changes, \# but is known to break things on some drivers (LLVMpipe, xf86-video-intel, etc.). \# Recommended if it works. \# glx-no-rebind-pixmap = false \# Disable the use of damage information. \# This cause the whole screen to be redrawn everytime, instead of the part of the screen \# has actually changed. Potentially degrades the performance, but might fix some artifacts. \# The opposing option is use-damage \# \# no-use-damage = false use-damage = true \# Use X Sync fence to sync clients' draw calls, to make sure all draw \# calls are finished before picom starts drawing. Needed on nvidia-drivers \# with GLX backend for some users. \# \# xrender-sync-fence = false \# GLX backend: Use specified GLSL fragment shader for rendering window contents. \# See `compton-default-fshader-win.glsl` and `compton-fake-transparency-fshader-win.glsl` \# in the source tree for examples. \# \# glx-fshader-win = '' \# Force all windows to be painted with blending. Useful if you \# have a glx-fshader-win that could turn opaque pixels transparent. \# \# force-win-blend = false \# Do not use EWMH to detect fullscreen windows. \# Reverts to checking if a window is fullscreen based only on its size and coordinates. \# \# no-ewmh-fullscreen = false \# Dimming bright windows so their brightness doesn't exceed this set value. \# Brightness of a window is estimated by averaging all pixels in the window, \# so this could comes with a performance hit. \# Setting this to 1.0 disables this behaviour. Requires --use-damage to be disabled. (default: 1.0) \# \# max-brightness = 1.0 \# Make transparent windows clip other windows like non-transparent windows do, \# instead of blending on top of them. \# \# transparent-clipping = false \# Set the log level. Possible values are: \# "trace", "debug", "info", "warn", "error" \# in increasing level of importance. Case doesn't matter. \# If using the "TRACE" log level, it's better to log into a file \# using *--log-file*, since it can generate a huge stream of logs. \# \# log-level = "debug" log-level = "warn"; \# Set the log file. \# If *--log-file* is never specified, logs will be written to stderr. \# Otherwise, logs will to written to the given file, though some of the early \# logs might still be written to the stderr. \# When setting this option from the config file, it is recommended to use an absolute path. \# \# log-file = '/path/to/your/log/file' \# Show all X errors (for debugging) \# show-all-xerrors = false \# Write process ID to a file. \# write-pid-path = '/path/to/your/log/file' \# Window type settings \# \# 'WINDOW_TYPE' is one of the 15 window types defined in EWMH standard: \# "unknown", "desktop", "dock", "toolbar", "menu", "utility", \# "splash", "dialog", "normal", "dropdown_menu", "popup_menu", \# "tooltip", "notification", "combo", and "dnd". \# \# Following per window-type options are available: :: \# \# fade, shadow::: \# Controls window-type-specific shadow and fade settings. \# \# opacity::: \# Controls default opacity of the window type. \# \# focus::: \# Controls whether the window of this type is to be always considered focused. \# (By default, all window types except "normal" and "dialog" has this on.) \# \# full-shadow::: \# Controls whether shadow is drawn under the parts of the window that you \# normally won't be able to see. Useful when the window has parts of it \# transparent, and you want shadows in those areas. \# \# redir-ignore::: \# Controls whether this type of windows should cause screen to become \# redirected again after been unredirected. If you have unredir-if-possible \# set, and doesn't want certain window to cause unnecessary screen redirection, \# you can set this to `true`. \# wintypes: { tooltip = { fade = true; shadow = false; opacity = 0.85; focus = true; full-shadow = false; }; dock = { shadow = false; }; dnd = { shadow = false; opacity = 0.85; }; popup_menu = { opacity = 1; shadow = false; }; dropdown_menu = { shadow = false; }; };

Details

After update to the v 10, the interface start working with visible reduced performance (low fps, jerky windows drawings, etc). Now, I have installed v 9.1. again, and everything works as expected.

wimgoeman commented 1 year ago

Same issue here. When Im not running much applications all is fine, but when I start a Jetbrains product, all my memory gets taken by the X server until it gets oom killed. When I run VSCode however, the memory is fine, but 1 CPU core is used for 100% by X.

absolutelynothelix commented 1 year ago

@wimgoeman,

when I start a Jetbrains product, all my memory gets taken by the X server until it gets oom killed

looks like you're encountering a memory leak somewhere. there are some recent issues about memory leaks, see if any of them fits your case and join them or create your own.

When I run VSCode however, the memory is fine, but 1 CPU core is used for 100% by X.

this sounds interesting. it doesn't happen without a compositor running, right? i think this case deserves it's own issue.

absolutelynothelix commented 1 year ago

@erydit, when you was running v9.1, did you use --experimental-backends? what happens if you use --legacy-backends with v10?

p.s, you may try the new egl backend. maybe it'll run better than glx one for you. p.p.s, is it possible for you and your gpu to test amdgpu driver instead of radeon one (i'm not sure if your gpu is supported by amdgpu though, but for me nvidia driver performs way better than nouveau one, maybe it'll work the same way for you as well)?

erydit commented 1 year ago

@absolutelynothelix With --legacy-backends in v 10.2-1 picom works fine, as it was in v 9. Thank you. But what to do if it would be removed one day...)

egl backends does not work at all, when i set it everything looks like any compositor is disabled. and, unfortunately, amdgpu does not support my embended gpu.

absolutelynothelix commented 1 year ago

But what to do if it would be removed one day...)

i don't think that they'll be removed anytime soon, especially when there are still several unresolved issues with new backends.

egl backends does not work at all, when i set it everything looks like any compositor is disabled.

and picom is running, i.e. it doesn't crash spitting out any errors? that's weird, maybe your embedded gpu doesn't support egl?.. (i'm not sure about inner workings of egl, though)

vaygr commented 1 year ago

Same issue here on Manjaro. GPU is Intel Xe though. Too bad legacy-backends = true; doesn't work in the config file.

HSwift commented 1 year ago

Same issue on Archlinux. When I use the mouse to switch between two monitors, the CPU usage of XServer is close to 100%. The load on XServer decreased after I tried to kill the picom, but I could still feel the latency.

I tried to analyze Xorg using perf and found that the damageRemoveDamage function was taking up most of the CPU time. And I can't determine whether this problem is caused by picom or by XServer itself

absolutelynothelix commented 1 year ago

@HSwift, that’s a nice point. can you share your configuration and basic details about your setup?

HSwift commented 1 year ago

OS: Archlinux Kernel: 6.1.1-arch1-1 WM: i3 version 4.21.1 Picom: 10.2-1 XServer: 21.1.6-1

picom.conf

vsync = true;
detect-transient = true;
shadow = false;
log-level = "warn";

glxinfo -B

name of display: :0
display: :0  screen: 0
direct rendering: Yes
Extended renderer info (GLX_MESA_query_renderer):
    Vendor: AMD (0x1002)
    Device: AMD Radeon Graphics (renoir, LLVM 14.0.6, DRM 3.49, 6.1.1-arch1-1) (0x1638)
    Version: 22.3.1
    Accelerated: yes
    Video memory: 1024MB
    Unified memory: no
    Preferred profile: core (0x1)
    Max core profile version: 4.6
    Max compat profile version: 4.6
    Max GLES1 profile version: 1.1
    Max GLES[23] profile version: 3.2
Memory info (GL_ATI_meminfo):
    VBO free memory - total: 468 MB, largest block: 468 MB
    VBO free aux. memory - total: 7341 MB, largest block: 7341 MB
    Texture free memory - total: 468 MB, largest block: 468 MB
    Texture free aux. memory - total: 7341 MB, largest block: 7341 MB
    Renderbuffer free memory - total: 468 MB, largest block: 468 MB
    Renderbuffer free aux. memory - total: 7341 MB, largest block: 7341 MB
Memory info (GL_NVX_gpu_memory_info):
    Dedicated video memory: 1024 MB
    Total available memory: 8449 MB
    Currently available dedicated video memory: 468 MB
OpenGL vendor string: AMD
OpenGL renderer string: AMD Radeon Graphics (renoir, LLVM 14.0.6, DRM 3.49, 6.1.1-arch1-1)
OpenGL core profile version string: 4.6 (Core Profile) Mesa 22.3.1
OpenGL core profile shading language version string: 4.60
OpenGL core profile context flags: (none)
OpenGL core profile profile mask: core profile

OpenGL version string: 4.6 (Compatibility Profile) Mesa 22.3.1
OpenGL shading language version string: 4.60
OpenGL context flags: (none)
OpenGL profile mask: compatibility profile

OpenGL ES profile version string: OpenGL ES 3.2 Mesa 22.3.1
OpenGL ES profile shading language version string: OpenGL ES GLSL ES 3.20

@absolutelynothelix. It is difficult to reproduce this exception, which basically happens randomly some time after I have started the Jetbrains product (idea). Once the exception is triggered, XServer gradually becomes unresponsive and I have to restart it.

This is the result of measuring XServer with perf after killing picom. miSpriteTrace does not take up a lot of CPU time under normal conditions, while under abnormal conditions it takes up most of the CPU time.

+   28.16%    27.99%  Xorg         Xorg                    [.] miSpriteTrace
+   18.66%     0.00%  Xorg:cs0     [kernel.kallsyms]       [k] entry_SYSCALL_64_after_hwframe
+   18.66%     0.00%  Xorg:cs0     [kernel.kallsyms]       [k] do_syscall_64
+   18.16%     0.00%  Xorg:cs0     [unknown]               [k] 0x0000000000000003
+   18.16%     0.00%  Xorg:cs0     libc.so.6               [.] ioctl
+   18.16%     0.00%  Xorg:cs0     [kernel.kallsyms]       [k] __x64_sys_ioctl
+   18.16%     0.00%  Xorg:cs0     [amdgpu]                [k] 0xffffffffc27352de
+   18.16%     0.00%  Xorg:cs0     [kernel.kallsyms]       [k] drm_ioctl
+   18.16%     0.00%  Xorg:cs0     [kernel.kallsyms]       [k] drm_ioctl_kernel
+   11.53%    11.53%  Xorg:gdrv0   radeonsi_dri.so         [.] 0x00000000008dbbe7
+   11.53%     0.00%  Xorg:gdrv0   radeonsi_dri.so         [.] 0x00007f9f220dbbe7
absolutelynothelix commented 1 year ago

@HSwift, your setup seems capable of running glx or egl backend. why you're using xrender?

HSwift commented 1 year ago

I just simply configured it and did not notice the backend option.

vaygr commented 1 year ago

@absolutelynothelix my reason behind this is this bug.

I have a multi-monitor setup with 2 external displays connected to the laptop, with the 2nd one in portrait mode. So it's 1920x1080 - 1920x1200 - 1200x1920.

Using a modesetting driver causes terrible screen tearing with my setup, so I had to switch to the intel driver. Running picom with a glx backend results in awful performance, hence I switched back to xrender.

Maybe I'll try the modesetting driver again in a year or so to see if something's changed (it seems that bug was closed a couple of weeks ago, but it will take time to get it to the next xorg release + distro release delays, etc.), but so far intel driver + picom xrender backend + picom legacy backends is the only combination that results in a usable setup for me.

cc @yshui

absolutelynothelix commented 1 year ago

@HSwift, you could try glx backend then (or egl if it works for you), it should perform better. or, since your research led you to something damage related, you may try setting use-damage = false; or passing --no-use-damage to the cli since as i can see damage is enabled by default.

@vaygr, i see. i'm not sure is aur supported on manjaro, but if it is, you may try -git packages you need to have latest changes.

in general, preferable backend is glx (or egl if it works for you). it has more features, less bugs and overall better than xrender one. xrender is mostly intended for old machines that have issues with gl-powered backends. it doesn't recieve much love (it's hard to love something related to x11), but i'm contributing to it and trying to improve it.

Fxzzi commented 1 year ago

when using egl backend on picom with nvidia i get a black screen with only my cursor being visible. Works fine on glx.

absolutelynothelix commented 1 year ago

@Fxzzi, if i understand your issue correctly this should be fixed starting from 766f9f996f5a02d97d85e3c4cee34513501c758a

Fxzzi commented 1 year ago

@Fxzzi, if i understand your issue correctly this should be fixed starting from 766f9f9

Installed picom-git which includes this commit and the issue is fixed, thanks :)

absolutelynothelix commented 1 year ago

ok, i'm joining this myself because the nouveau driver's performance is extremely poor on new backends while it's fine on legacy backends. nvidia driver's performance is fine on both kinds of backends, but it has it's own issues.

man takes forever to draw :skull: image

update: looks like the gl_present function takes ridiculously large amount of gpu time on the nouveau driver:

nvidia driver:

compose: 0.024576, present: 0.270784

nouveau driver:

compose: 0.102464, present: 5.415040

p.s. the gpu time was measured with the GL_TIME_ELAPSED query using entire gl_compose and gl_present functions as scopes. my measurements may be wrong, though.

update 2: nah, they're both slow, the first one just depends on the size of the window.

vaygr commented 1 year ago

Something changed in the very recent Manjaro update, so even legacy backends setting stopped working for me. Maybe it's not as bad as without it, but still pretty noticeable.

Thankfully xf86-video-modesetting TearFree Page-Flipping was merged last year (no xorg-server release though since then). So swapping xorg-server with xorg-server-git allowed me to switch to the modern modesetting driver from intel driver without experiencing tearing on my multi-monitor setup with one of them in portrait mode as per my https://github.com/yshui/picom/issues/967#issuecomment-1365296641 above.

I was able to run recent picom (10.2) w/ or w/o the legacy backends setting with no issues. Didn't notice any visible difference, so decided to drop it. Then I was able to switch to the glx backend from xrender which was causing issues before.

SoniEx2 commented 3 months ago

we have also noticed this issue on old intel igpu (core i5 3330), legacy backend has better performance