[Bug 89931] New: [SKL]igt/gem_pwrite_pread at display-pwrite-blt-gtt_mmap-performance sporadically causes *ERROR* Hangcheck timer elapsed... blitter ring idle

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=89931

            Bug ID: 89931
           Summary: [SKL]igt/gem_pwrite_pread at display-pwrite-blt-gtt_mmap-
                    performance sporadically causes *ERROR* Hangcheck
                    timer elapsed... blitter ring idle
           Product: DRI
           Version: unspecified
          Hardware: All
                OS: Linux (All)
            Status: NEW
          Severity: normal
          Priority: medium
         Component: DRM/Intel
          Assignee: intel-gfx-bugs at lists.freedesktop.org
          Reporter: huax.lu at intel.com
        QA Contact: intel-gfx-bugs at lists.freedesktop.org
                CC: intel-gfx-bugs at lists.freedesktop.org

Created attachment 114906
  --> https://bugs.freedesktop.org/attachment.cgi?id=114906&action=edit
dmesg

==System Environment==
--------------------------
Regression: not sure

Non-working platforms: SKL

==kernel==
--------------------------
drm-intel-nightly/333cf6eed7cae0ee2d6bb1b4c4d421b94f84fc13
commit 333cf6eed7cae0ee2d6bb1b4c4d421b94f84fc13
Author: Jani Nikula <jani.nikula at intel.com>
Date:   Thu Apr 2 11:38:12 2015 +0300

    drm-intel-nightly: 2015y-04m-02d-08h-37m-57s UTC integration manifest

==Bug detailed description==
-----------------------------
Run it 2 rounds, It fails once.
gem_pwrite_pread at snooped-pwrite-blt-cpu_mmap-performance also has this issue.
output:
IGT-Version: 1.10-g43a1f64 (x86_64) (Linux:
4.0.0-rc6_drm-intel-nightly_333cf6_20150403+ x86_64)
** mmap display copy 16384 bytes x      1:      678.000µs, 24.2MiB/s
** mmap display copy 16384 bytes x      2:      514.500µs, 31.8MiB/s
** mmap display copy 16384 bytes x      4:      509.750µs, 32.1MiB/s
** mmap display copy 16384 bytes x      8:      471.500µs, 34.7MiB/s
** mmap display copy 16384 bytes x     16:      449.500µs, 36.4MiB/s
** mmap display copy 16384 bytes x     32:      435.438µs, 37.6MiB/s
** mmap display copy 16384 bytes x     64:      461.938µs, 35.5MiB/s
** mmap display copy 16384 bytes x    128:      500.539µs, 32.7MiB/s
** mmap display copy 16384 bytes x    256:      500.590µs, 32.7MiB/s
** mmap display copy 16384 bytes x    512:      500.219µs, 32.8MiB/s
** mmap display copy 16384 bytes x   1024:      499.402µs, 32.8MiB/s
** mmap display copy 16384 bytes x   2048:      500.127µs, 32.8MiB/s
** mmap display copy 16384 bytes x   4096:      500.012µs, 32.8MiB/s
** mmap display copy 16384 bytes x   8192:      500.198µs, 32.8MiB/s
** mmap display copy 16384 bytes x  16384:      500.135µs, 32.8MiB/s
** mmap display copy 16384 bytes x  32768:      500.108µs, 32.8MiB/s
** mmap display copy 16384 bytes x  65536:      500.005µs, 32.8MiB/s
** mmap display copy 16384 bytes x 131072:      528.930µs, 31.0MiB/s
Subtest display-pwrite-blt-gtt_mmap-performance: SUCCESS (134.867s)

root at x-skly05:/GFX/Test/Intel_gpu_tools/intel-gpu-tools/tests# dmesg -r|egrep
"<[1-4]>"|grep drm
<3>[ 7016.090135] [drm:i915_hangcheck_elapsed [i915]] *ERROR* Hangcheck timer
elapsed... blitter ring idle

==Reproduce steps==
---------------------------- 
1. ./gem_pwrite_pread --run-subtest display-pwrite-blt-gtt_mmap-performance

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
You are on the CC list for the bug.
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/intel-gfx-bugs/attachments/20150407/06bc00d3/attachment-0001.html>