Re: [gentoo-user] Xorg Performance, on Intel Graphics

[Thomas Kahle]

Thomas Kahle wrote:
> Hi everyone,
>
> I use the thinkpad X61s with Intel Graphics Mobile GM965/GL960 running
> Gentoo.
>
> Since an update on Monday I cannot get my X to work the smooth way it
> was working before.
>
> 1) The 2D performance feels very slack, Redrawing Windows just takes
> longer than it took before and reaction times in general are worse.
> 2) glxgears performance is down to 50FPS (200FPS before, but I remember
> 1000FPS a year ago), but reading about kernel 2.6.29 probably it should
> be this way.
> 3) Googleearth is very slow
> 4) X consumes more CPU 10-14 percent when showing 'top' in an xterm, up
> to a whole cpu when using firefox.
> 5) After using it a while(2 hours, say) X consumes a lot of memory and
> responsiveness and performance start getting worse and worse. Feels like
> some memory leakage.

One very important thing seems to be to disable "Synchronization with
vertical refresh" in driconf. Up to now it seems to restore the old
behaviour for 1-4.
Appearently this options default value was changed from mesa 7.3 to 7.4

>
> The things updated are kernel from 2.6.27 to 2.6.29, mesa from 7.3 to
> 7.4, intel driver from 2.6.1 to 2.6.3.
>
> The Xorg Version is 1.5.3 and unchanged.
>
> Unfortunately I upgraded all these things at once, which is a mistake,
> but well.
>
> Now, the fun thing is that switching back makes the sluggish behaviour
> 1-4, go away, but 5 stays and I thought I reverted everything back to
> the original state but it is still there.
>
> Does anybody know a consistent guide how to configure kernel and Xorg to
> be on the safe side for the future ?
>
> Here is glxinfo, just if it matters
> ---------------
> name of display: :0.0
> display: :0  screen: 0
> direct rendering: Yes
> server glx vendor string: SGI
> server glx version string: 1.2
> server glx extensions:
>     GLX_ARB_multisample, GLX_EXT_import_context,
> GLX_EXT_texture_from_pixmap,
>     GLX_EXT_visual_info, GLX_EXT_visual_rating,
> GLX_MESA_copy_sub_buffer,
>     GLX_OML_swap_method, GLX_SGI_swap_control, GLX_SGIS_multisample,
>
>     GLX_SGIX_fbconfig, GLX_SGIX_visual_select_group
>
> client glx vendor string: SGI
>
> client glx version string: 1.4
>
> client glx extensions:
>
>     GLX_ARB_get_proc_address, GLX_ARB_multisample,
> GLX_EXT_import_context,
>     GLX_EXT_visual_info, GLX_EXT_visual_rating,
> GLX_MESA_allocate_memory,
>     GLX_MESA_copy_sub_buffer, GLX_MESA_swap_control,
>
>     GLX_MESA_swap_frame_usage, GLX_OML_swap_method,
> GLX_OML_sync_control,
>     GLX_SGI_make_current_read, GLX_SGI_swap_control, GLX_SGI_video_sync,
>
>     GLX_SGIS_multisample, GLX_SGIX_fbconfig, GLX_SGIX_pbuffer,
>
>     GLX_SGIX_visual_select_group, GLX_EXT_texture_from_pixmap
>
> GLX version: 1.2
>
> GLX extensions:
>
>     GLX_ARB_get_proc_address, GLX_ARB_multisample,
> GLX_EXT_import_context,
>     GLX_EXT_visual_info, GLX_EXT_visual_rating,
> GLX_MESA_copy_sub_buffer,
>     GLX_MESA_swap_control, GLX_MESA_swap_frame_usage,
> GLX_OML_swap_method,
>     GLX_SGI_swap_control, GLX_SGI_video_sync, GLX_SGIS_multisample,
>
>     GLX_SGIX_fbconfig, GLX_SGIX_visual_select_group
>
> OpenGL vendor string: Tungsten Graphics, Inc
>
> OpenGL renderer string: Mesa DRI Intel(R) 965GM GEM 20090326 2009Q1 RC2
> x86/MMX/SSE2
> OpenGL version string: 2.0 Mesa 7.4
>
> OpenGL shading language version string: 1.10
>
> OpenGL extensions:
>
>     GL_ARB_depth_texture, GL_ARB_draw_buffers, GL_ARB_fragment_program,
>
>     GL_ARB_fragment_program_shadow, GL_ARB_fragment_shader,
>
>     GL_ARB_multisample, GL_ARB_multitexture, GL_ARB_occlusion_query,
>
>     GL_ARB_pixel_buffer_object, GL_ARB_point_parameters,
> GL_ARB_point_sprite,
>     GL_ARB_shader_objects, GL_ARB_shading_language_100, GL_ARB_shadow,
>
>     GL_ARB_texture_border_clamp, GL_ARB_texture_compression,
>
>     GL_ARB_texture_cube_map, GL_ARB_texture_env_add,
>
>     GL_ARB_texture_env_combine, GL_ARB_texture_env_crossbar,
>
>     GL_ARB_texture_env_dot3, GL_ARB_texture_mirrored_repeat,
>
>     GL_ARB_texture_non_power_of_two, GL_ARB_texture_rectangle,
>
>     GL_ARB_transpose_matrix, GL_ARB_vertex_buffer_object,
>
>     GL_ARB_vertex_program, GL_ARB_vertex_shader, GL_ARB_window_pos,
>
>     GL_EXT_abgr, GL_EXT_bgra, GL_EXT_blend_color,
>
>     GL_EXT_blend_equation_separate, GL_EXT_blend_func_separate,
>
>     GL_EXT_blend_logic_op, GL_EXT_blend_minmax, GL_EXT_blend_subtract,
>
>     GL_EXT_clip_volume_hint, GL_EXT_cull_vertex,
> GL_EXT_compiled_vertex_array,
>     GL_EXT_copy_texture, GL_EXT_draw_range_elements,
>
>     GL_EXT_framebuffer_object, GL_EXT_fog_coord,
> GL_EXT_multi_draw_arrays,
>     GL_EXT_packed_depth_stencil, GL_EXT_packed_pixels,
>
>     GL_EXT_pixel_buffer_object, GL_EXT_point_parameters,
>
>     GL_EXT_polygon_offset, GL_EXT_rescale_normal,
> GL_EXT_secondary_color,
>     GL_EXT_separate_specular_color, GL_EXT_shadow_funcs,
> GL_EXT_stencil_wrap,
>     GL_EXT_subtexture, GL_EXT_texture, GL_EXT_texture3D,
>
>     GL_EXT_texture_edge_clamp, GL_EXT_texture_env_add,
>
>     GL_EXT_texture_env_combine, GL_EXT_texture_env_dot3,
>
>     GL_EXT_texture_filter_anisotropic, GL_EXT_texture_lod_bias,
>
>     GL_EXT_texture_object, GL_EXT_texture_rectangle,
> GL_EXT_texture_sRGB,
>     GL_EXT_vertex_array, GL_3DFX_texture_compression_FXT1,
>
>     GL_APPLE_client_storage, GL_APPLE_packed_pixels,
>
>     GL_ATI_blend_equation_separate, GL_ATI_texture_env_combine3,
>
>     GL_ATI_separate_stencil, GL_IBM_rasterpos_clip,
>
>     GL_IBM_texture_mirrored_repeat, GL_INGR_blend_func_separate,
>
>     GL_MESA_pack_invert, GL_MESA_ycbcr_texture, GL_MESA_window_pos,
>
>     GL_NV_blend_square, GL_NV_light_max_exponent, GL_NV_point_sprite,
>
>     GL_NV_texture_rectangle, GL_NV_texgen_reflection,
> GL_NV_vertex_program,
>     GL_NV_vertex_program1_1, GL_OES_read_format,
> GL_SGIS_generate_mipmap,
>     GL_SGIS_texture_border_clamp, GL_SGIS_texture_edge_clamp,
>
>     GL_SGIS_texture_lod, GL_SGIX_depth_texture, GL_SUN_multi_draw_arrays
>
>
> 3 GLX Visuals
>    visual  x  bf lv rg d st colorbuffer ax dp st accumbuffer  ms  cav
>  id dep cl sp sz l  ci b ro  r  g  b  a bf th cl  r  g  b  a ns b eat
> ----------------------------------------------------------------------
> 0x21 24 tc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x22 24 dc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x71 32 tc  0 32  0 r  .  .  8  8  8  8  0  0  0  0  0  0  0  0 0 None
>
> 36 GLXFBConfigs:
>    visual  x  bf lv rg d st colorbuffer ax dp st accumbuffer  ms  cav
>  id dep cl sp sz l  ci b ro  r  g  b  a bf th cl  r  g  b  a ns b eat
> ----------------------------------------------------------------------
> 0x72  0 tc  0 32  0 r  .  .  8  8  8  8  0  0  0  0  0  0  0  0 0 None
> 0x73  0 tc  0 32  0 r  .  .  8  8  8  8  0  0  0 16 16 16 16  0 0 Slow
> 0x74  0 tc  0 32  0 r  y  .  8  8  8  8  0  0  0  0  0  0  0  0 0 None
> 0x75  0 tc  0 32  0 r  y  .  8  8  8  8  0  0  0 16 16 16 16  0 0 Slow
> 0x76  0 tc  0 32  0 r  y  .  8  8  8  8  0  0  0  0  0  0  0  0 0 None
> 0x77  0 tc  0 32  0 r  y  .  8  8  8  8  0  0  0 16 16 16 16  0 0 Slow
> 0x78  0 tc  0 32  0 r  .  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x79  0 tc  0 32  0 r  .  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x7a  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x7b  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x7c  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x7d  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x7e  0 tc  0 32  0 r  .  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x7f  0 tc  0 32  0 r  .  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x80  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x81  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x82  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x83  0 tc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x84  0 dc  0 32  0 r  .  .  8  8  8  8  0  0  0  0  0  0  0  0 0 None
> 0x85  0 dc  0 32  0 r  .  .  8  8  8  8  0  0  0 16 16 16 16  0 0 Slow
> 0x86  0 dc  0 32  0 r  y  .  8  8  8  8  0  0  0  0  0  0  0  0 0 None
> 0x87  0 dc  0 32  0 r  y  .  8  8  8  8  0  0  0 16 16 16 16  0 0 Slow
> 0x88  0 dc  0 32  0 r  y  .  8  8  8  8  0  0  0  0  0  0  0  0 0 None
> 0x89  0 dc  0 32  0 r  y  .  8  8  8  8  0  0  0 16 16 16 16  0 0 Slow
> 0x8a  0 dc  0 32  0 r  .  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x8b  0 dc  0 32  0 r  .  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x8c  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x8d  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x8e  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x8f  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x90  0 dc  0 32  0 r  .  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x91  0 dc  0 32  0 r  .  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x92  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x93  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> 0x94  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8  0  0  0  0  0 0 None
> 0x95  0 dc  0 32  0 r  y  .  8  8  8  8  0 24  8 16 16 16 16  0 0 Slow
> ---------------
>


-- 
Thomas Kahle

The fundamental theorem of algebra is open source. Like any other
mathematical theorem it can be applied free of charge and everybody
has access to its proof and can convince himself how it works. Why
should software be any different?