[Intel-gfx] [RFC 0/4] GPU/CPU timestamps correlation for relating OA samples with system events

Fri Dec 22 05:26:03 UTC 2017


On 12/22/2017 10:45 AM, Sagar Arun Kamble wrote:
>
>
>
> On 12/7/2017 1:32 AM, Lionel Landwerlin wrote:
>> I've put together some trival IGT tests : 
>> https://github.com/djdeath/intel-gpu-tools/commits/wip/djdeath/cpu-timestamps
>> With a few changes which I pointed in the review : 
>> https://github.com/djdeath/linux/commit/d0e4cf4d3f464491b4ffe97d112284d1ce73656d
>>
>> Put together it seems to work relatively well.
>> There is still a small drift happening between the 2 timestamps. I've 
>> noticed over a 160ms of OA reports, there is a accumulated difference 
>> of ~35us between the GPU timestamp and cpu timestamps.
>> I may be doing something wrong with the scaling in the tests, or 
>> maybe there is an issue in the kernel, or both.
> Went through the testcase. scaled_gpu_delta calculation is same as 
> what timecounter does in kernel for calculating system_time corresponding
> to gpu timestamp hence we don't see much of delta between these two 
> times/time deltas.
> Ideally we should be testing the system time delta by sampling system 
> time and gpu timestamp atomically (which isn't feasible unless we do 
> some precise adjustments)
> I have attempted to check these two times/delta by sampling them in 
> debugfs and reading over variable periods manually and checking the delta.
> https://github.com/sakamble/i915-timestamp-support/commit/03be3056752d7b05a02cd01f5c20b3fcfcf18395
>
> It is showing that delta is less than 10us in most cases for 30min and 
> occasionally around 20-30us. Again this delta might be because of 
> initial time setting as well.
> timecounter initializing system time and gpu clocks as pair should be 
> highly accurate for which I have currently taken 350us start offset.
>
> I think gpu timestamp clock is highly stable as seen in my testing on 
> SKL. I think this clock is used for calculations in GuC too so will
> be good to get confirmation about the stability of this clock from 
> them and HW team.
>
>    systemd-udevd-169   [001] ....     3.035812: i915_driver_load: sys 
> start time: 1512308011156099790
>
>    systemd-udevd-169   [001] d...     3.036012: 
> i915_cyclecounter_read: 52025098974
>
>              cat-1654  [001] ....    52.407957: 
> i915_cyclecounter_read: 52617562292
>
>              cat-1654  [001] ....    52.407958: i915_timestamp_info: 
> sys time: 1512308060527894638
>
>              cat-1654  [001] ....    52.407958: i915_timestamp_info: 
> ts: 52617562292 device time: 1512308060528043050
>
>              cat-1684  [001] ....   177.239733: 
> i915_cyclecounter_read: 54115543581
>
>              cat-1684  [001] ....   177.239736: i915_timestamp_info: 
> sys time: 1512308185359666602
>
>              cat-1684  [001] ....   177.239737: i915_timestamp_info: 
> ts: 54115543581 device time: 1512308185359817372
>
>              cat-1693  [001] ....   329.820374: 
> i915_cyclecounter_read: 55946511277
>
>              cat-1693  [001] ....   329.820377: i915_timestamp_info: 
> sys time: 1512308337940301732
>
>              cat-1693  [001] ....   329.820378: i915_timestamp_info: 
> ts: 55946511277 device time: 1512308337940458996
>
>
> <delta between system time delta and gpu time delta for above two 
> samples (177, 329) = 6494ns>
>
>
>              cat-1702  [001] ....   506.980313: 
> i915_cyclecounter_read: 58072430542
>
>              cat-1702  [001] ....   506.980315: i915_timestamp_info: 
> sys time: 1512308515100233102
>
>              cat-1702  [001] ....   506.980317: i915_timestamp_info: 
> ts: 58072430542 device time: 1512308515100398084
>
> <delta between system time delta and gpu time delta for above two 
> samples (329, 506) = 6494ns>
>
Fixing typo here:
<delta between system time delta and gpu time delta for above two 
samples (329, 506) = 7718ns>
>>
>> I'll build the GPUTop parts and see if the results make sense.
>>
>> Thanks!,
>>
>> -
>> Lionel
>>
>> On 15/11/17 12:13, Sagar Arun Kamble wrote:
>>> We can compute system time corresponding to GPU timestamp by taking a
>>> reference point (CPU monotonic time, GPU timestamp) and then adding
>>> delta time computed using timecounter/cyclecounter support in kernel.
>>> We have to configure cyclecounter with the GPU timestamp frequency.
>>> Earlier approach that was based on cross-timestamp is not needed. It
>>> was being used to approximate the frequency based on invalid 
>>> assumptions
>>> (possibly drift was being seen in the time due to precision issue).
>>> The precision of time from GPU clocks is already in ns and timecounter
>>> takes care of it as verified over variable durations.
>>>
>>> This series adds base timecounter/cyclecounter changes and changes to
>>> get GPU and CPU timestamps in OA samples.
>>>
>>> Sagar Arun Kamble (1):
>>>    drm/i915/perf: Add support to correlate GPU timestamp with system 
>>> time
>>>
>>> Sourab Gupta (3):
>>>    drm/i915/perf: Add support for collecting 64 bit timestamps with OA
>>>      reports
>>>    drm/i915/perf: Extract raw GPU timestamps from OA reports
>>>    drm/i915/perf: Send system clock monotonic time in perf samples
>>>
>>>   drivers/gpu/drm/i915/i915_drv.h  |  11 ++++
>>>   drivers/gpu/drm/i915/i915_perf.c | 124 
>>> ++++++++++++++++++++++++++++++++++++++-
>>>   drivers/gpu/drm/i915/i915_reg.h  |   6 ++
>>>   include/uapi/drm/i915_drm.h      |  14 +++++
>>>   4 files changed, 154 insertions(+), 1 deletion(-)
>>>
>>
>
>
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/intel-gfx

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-gfx/attachments/20171222/e5d79f0c/attachment.html>