我遇到了 Chrome 性能问题。当我有两个或多个 Chrome 窗口,其中一个窗口包含正在播放的视频 (youtube) 时,其他所有 Chrome 窗口在页面滚动或播放 CSS 动画时都会变得不流畅 (FPS 较低)。
如您所见,GPU 进程占用了太多的 CPU 资源。
我还注意到,将任何窗口拖到 Chrome 窗口上方(播放 YouTube 视频)也不太顺畅。非常烦人。
我尝试使用禁用 GPU 垂直同步键和滚动变得流畅,但任何 CSS 动画都会使用 100% 的一个 CPU 核心来实现最大 FPS。
在 nvidia-settings/ccsm 中禁用 vsync 具有相同的效果,即使禁用了复合。
所以我不知道该怎么办。Firefox 没有这样的问题,但我不想切换。
chrome://gpu 的输出
Graphics Feature Status
Canvas: Software only, hardware acceleration unavailable
Flash: Hardware accelerated
Flash Stage3D: Hardware accelerated
Flash Stage3D Baseline profile: Hardware accelerated
Compositing: Hardware accelerated
Multiple Raster Threads: Enabled
Native GpuMemoryBuffers: Software only. Hardware acceleration disabled
Rasterization: Software only. Hardware acceleration disabled
Video Decode: Software only, hardware acceleration unavailable
Video Encode: Hardware accelerated
WebGL: Hardware accelerated
Driver Bug Workarounds
clear_uniforms_before_first_program_use
force_cube_complete
init_gl_position_in_vertex_shader
init_vertex_attributes
pack_parameters_workaround_with_pack_buffer
scalarize_vec_and_mat_constructor_args
unpack_alignment_workaround_with_unpack_buffer
use_current_program_after_successful_link
use_virtualized_gl_contexts
Problems Detected
Accelerated 2d canvas is unstable in Linux at the moment
Disabled Features: accelerated_2d_canvas
Accelerated video decode is unavailable on Linux: 137247
Disabled Features: accelerated_video_decode
Always call glUseProgram after a successful link to avoid a driver bug: 349137
Applied Workarounds: use_current_program_after_successful_link
Program link fails in NVIDIA Linux if gl_Position is not set: 286468
Applied Workarounds: init_gl_position_in_vertex_shader
Clear uniforms before first program use on all platforms: 124764, 349137
Applied Workarounds: clear_uniforms_before_first_program_use
Linux NVIDIA drivers don't have the correct defaults for vertex attributes: 351528
Applied Workarounds: init_vertex_attributes
Always rewrite vec/mat constructors to be consistent: 398694
Applied Workarounds: scalarize_vec_and_mat_constructor_args
MakeCurrent is slow on Linux with NVIDIA drivers
Applied Workarounds: use_virtualized_gl_contexts
NVIDIA fails glReadPixels from incomplete cube map texture: 518889
Applied Workarounds: force_cube_complete
Pack parameters work incorrectly with pack buffer bound: 563714
Applied Workarounds: pack_parameters_workaround_with_pack_buffer
Alignment works incorrectly with unpack buffer bound: 563714
Applied Workarounds: unpack_alignment_workaround_with_unpack_buffer
Accelerated rasterization has been disabled, either via about:flags or command line.
Disabled Features: rasterization
我的电脑配置:
i7 6700k
32Gb DDR4 RAM
Nvidia GTX1080 配备最新的 nvidia 驱动程序-370
Ubuntu 16.04 / 最新的 chrome/chromium(均试过)
更新
此问题在具有不同 DE 和复合管理器的其他 Linux 发行版上重现。而且不只对我而言。
因此最有可能的问题nvidia 驱动程序适用于 gtx10xx 卡。
答案1
我猜 nVidia 对 Linux 的支持很差。尝试使用集成显卡来处理 chrome 和 nvidia 来处理其他东西。我甚至找不到适合我的 760m 的驱动程序,在那里我可以控制要切换哪个 gpu + 基本电源控制。