Re: [RFC 0/4] GPU/CPU timestamps correlation for relating OA samples with system events

[Sagar Arun Kamble <sagar.a.kamble@xxxxxxxxx>]

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>

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@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx