Summary: | [APL] Init time is high | ||||||
---|---|---|---|---|---|---|---|
Product: | DRI | Reporter: | cprigent <christophe.prigent> | ||||
Component: | DRM/Intel | Assignee: | Intel GFX Bugs mailing list <intel-gfx-bugs> | ||||
Status: | CLOSED NOTABUG | QA Contact: | Intel GFX Bugs mailing list <intel-gfx-bugs> | ||||
Severity: | critical | ||||||
Priority: | high | CC: | intel-gfx-bugs | ||||
Version: | unspecified | ||||||
Hardware: | x86-64 (AMD64) | ||||||
OS: | Linux (All) | ||||||
Whiteboard: | |||||||
i915 platform: | BXT | i915 features: | power/suspend-resume | ||||
Attachments: |
|
Description
cprigent
2016-03-27 10:08:33 UTC
What are the results with i915.fastboot=1 module parameter? It is reproduced with kernel boot command line i915.fastboot=1: init: 1093444 usecs Suspend: 60299 usecs Resume: 330746 usecs And also with processor.max_cstate=2 Sharing actual results and configuration: Init: 2042.896 ms Suspend : 49.291 ms Resume: 692.497 ms Configuration: ++ Platform : BXT-P ++ Motherboard model : Broxton P ++ Motherboard type : NOTEBOOK Hand Held ++ Motherboard manufacturer : Intel Corp. ++ CPU family : Other ++ CPU information : 06/5c ++ GPU Card : Intel Corporation Device 5a84 (rev 03) (prog-if 00 [VGA controller]) ++ Memory ram : 8 GB ++ Maximum memory ram allowed : 16 GB ++ Display resolution : ++ CPU's number : 4 ++ Hard drive capacity : 120 GB ++ Kernel version : 4.6.0-rc3-nightly+ ++ Linux distribution : Ubuntu 15.10 ++ Architecture : 64-bit ++ xf86-video-intel version : 2.99.917 ++ Xorg-Xserver version : 1.17.2 ++ DRM version : 2.4.64 ++ Cairo version : 1.14.2 ++ Intel GPU Tools version : Tag [intel-gpu-tools-1.14-133-gc89e8db] / Commit [c89e8db] ++ Kernel driver in use : i915 ++ Hardware acceleration : ++ Bios revision : 131.10 ++ KSC revision : 1.12 Could you try https://github.com/ideak/linux/commits/bxt-tsc ? It has the following patchset from Gao Bin/Len Brown fixing the system clock rate: https://lkml.org/lkml/2016/3/31/6 Tested on RVP1C A0 stepping with kernel 4.6.0-rc4 d998658 from https://github.com/ideak/linux/commits/bxt-tsc commit d998658f9e8595eb6a530adaf8f306d0aac7a362 Author: Bin Gao <bin.gao@intel.com> Date: Mon Apr 18 02:37:45 2016 +0300 x86 tsc: enumerate BXT tsc_khz via CPUID Tried 3 times: Init time is about 1 second Suspend to RAM does not work. DUT reboots instead of resuming, with nothing restored. Milestone blocker so increasing priority Christophe, please check latest comment in bug 94722 and then re-test No milestone blocker, reducing priority Ricardo (or Christophe) - please re-check if this is still valid. Hi Ricardo, Please reassign as soon as it can be tested on a production device. Luis could you please retest to see if the problem continues to exist We are still out of the criteria range, I tested with latest drm-tip kernel on APL NUC, I found the following results for init time: Boot: [ 3.176236] calling i915_init+0x0/0x6e [i915] @ 177 [ 3.448193] initcall i915_init+0x0/0x6e [i915] returned 0 after 265513 usecs Resume: [ 433.010636] call 0000:00:02.0+ returned 0 after 163014 usecs [ 433.091960] call 0000:00:02.0+ returned 0 after 13809 usecs [ 433.096424] call 0000:00:02.0+ returned 0 after 1 usecs [ 433.251991] call 0000:00:02.0+ returned 0 after 11063 usecs [ 433.273124] call 0000:00:02.0+ returned 0 after 7389 usecs [ 434.019411] call 0000:00:02.0+ returned 0 after 722061 usecs This is my config: Software ====================================== kernel version : 4.12.0-rc4-drm-tip-ww23-commit-17f9a91+ architecture : x86_64 os version : Ubuntu 17.04 kernel driver : i915 bios revision : 5.6 bios release date : 03/10/2017 ksc : 16.0 modesetting : modesetting_drv.so xorg-xserver : 1.19.3 libdrm : 2.4.76 libva : 1.7.3-2 vaapi (intel-driver) : 1.7.3 cairo : 1.14.8-1 dmc version : 1.7 Hardware ====================================== motherboard model : NUC6CAYS motherboard id : NUC6CAYB form factor : Desktop manufacturer : Intelcorporation cpu family : Celeron cpu family id : 6 cpu information : Intel(R) Celeron(R) CPU J3455 @ 1.50GHz gpu card : Intel Corporation Device 5a85 (rev 0b) (prog-if 00 [VGA controller]) memory ram : 15.54 GB cpu thread : 4 cpu core : 4 cpu model : 92 cpu stepping : 9 signature : Type 0, Family 6, Model 92, Stepping 9 kernel parameters ====================================== quiet splash drm.debug=0xe i915.fastboot=1 initcall_debug no_console_suspend Closing this due to "Test method of using Kernel logs has the problem of not pointing these times to i915 only. That is case even for the init time where i915 init is interrupted several times and cannot be assigned to be entirely spend in graphics init." Please open a new bug with another measurement scenario, if there is something that one should fix. |
Use of freedesktop.org services, including Bugzilla, is subject to our Code of Conduct. How we collect and use information is described in our Privacy Policy.