Re: [PATCH v3] drm/i915: Use exponential backoff for wait_for()

John Harrison <John.C.Harrison@xxxxxxxxx> · Wed, 29 Nov 2017 19:04:14 -0800



    On 11/24/2017 6:12 AM, Chris Wilson wrote:

    
      Quoting Michał Winiarski (2017-11-24 12:37:56)

      
        Since we see the effects for GuC preeption, let's gather some evidence.

(SKL)
intel_guc_send_mmio latency: 100 rounds of gem_exec_latency --r '*-preemption'

drm-tip:
     usecs               : count     distribution
         0 -> 1          : 0        |                                        |
         2 -> 3          : 0        |                                        |
         4 -> 7          : 0        |                                        |
         8 -> 15         : 44       |                                        |
        16 -> 31         : 1088     |                                        |
        32 -> 63         : 832      |                                        |
        64 -> 127        : 0        |                                        |
       128 -> 255        : 0        |                                        |
       256 -> 511        : 12       |                                        |
       512 -> 1023       : 0        |                                        |
      1024 -> 2047       : 29899    |*********                               |
      2048 -> 4095       : 131033   |****************************************|

      
      Such pretty graphs. Reminds me of the bpf hist output, I wonder if we
could create a tracepoint/kprobe that would output a histogram for each
waiter (filterable ofc). Benefit? Just thinking of tuning the
spin/sleep, in which case overall metrics are best
(intel_eait_for_register needs to be optimised for the typical case). I
am wondering if we could tune the spin period down to 5us, 2us? And then
have the 10us sleep.

We would also need a typical workload to run, it's profile-guided
optimisation after all. Hmm.
-Chris

    
    It took me a while to get back to this but I've now had chance to
    run with this exponential backoff scheme on the original system that
    showed the problem. It was a slightly messy back port due to the
    customer tree being much older than current nightly. I'm pretty sure
    I got it correct though. However, I'm not sure what the
    recommendation is for the two timeout values. Using the default of
    '10, 10' in the patch, I still get lots of very long delays. I have
    to up the Wmin value to at least 140 to get a stall free result.
    Which is plausible given that the big spike in the results of any
    fast version is at 110-150us. Also of note is that a Wmin between 10
    and 110 actually makes things worse. Changing Wmax has no effect.

    
    In the following table, 'original' is the original driver before any
    changes and 'retry loop' is the version using the first workaround
    of just running the busy poll wait in a 10x loop. The other columns
    are using the backoff patch with the given Wmin/Wmax values. Note
    that the times are bucketed to 10us up to 500us and then in 500us
    lumps thereafter. The value listed is the lower limit, i.e. there
    were no times of <10us measured. Each case was run for 1000
    samples.

    
        Time        Original    10/10    
          50/10    100/10    110/10    130/10    140/10  RetryLoop

              10us:          2         2         2         2        
          2         2         2         2

              30us:                              1         1        
          1         1         1

              50us:                              1

              70us:                             14        63       
          56        64        63        61

              80us:                              8        41       
          52        44        46        41

              90us:                              6        24       
          10        28        12        17

             100us:                    2         4        20       
          16        17        17        22

             110us:                                       13       
          21        14        13        11

             120us:                              6       366      
          633       636       660       650

             130us:                    2         2        46      
          125        95        86        95

             140us:                    3         2        16       
          18        32        46        48

             150us:                  210         3        12       
          13        37        32        31

             160us:                  322         1        18       
          10        14        12        17

             170us:                  157         4         5        
          5         3         5         2

             180us:                   62        11         3        
          1         2         1         1

             190us:                   32       212        
          1                   1         2

             200us:                   27       266        
          1                   1

             210us:                   16      
          181                                                 1

             220us:                   16       
          51                                       1

             230us:                   10        43         4

             240us:                   12        22        62         1

             250us:                    4        12       112         3

             260us:                    3        13        73         8

             270us:                    5        12        12        
          8         2

             280us:                    4         7        12        
          5         1

             290us:                              9         4

             300us:                    1         3         9        
          1         1

             310us:                    2         3         5        
          1         1

             320us:                    1         4         2         3

             330us:                    1         5         1

             340us:                    1                  
          2                   1

             350us:                              2         1

             360us:                              2         1

             370us:                    2                   2

             380us:                                        1

             390us:                    2         1         2         1

             410us:                    1

             420us:                    3

             430us:                    2         2         1

             440us:                    2         1

             450us:                              4

             460us:                    3         1

             470us:                              3         1

             480us:                    2                   2

             490us:                                        1

             500us:                   19        13        17

            1000us:        249        22        30        11

            1500us:        393         4         4         2         1

            2000us:        132         7         8         8        
          2         1                   1

            2500us:         63         4         4         6        
          1         1         1

            3000us:         59         9         7         6         1

            3500us:         34         2        
          1                             1

            4000us:         17         9         4         1

            4500us:          8         2         1         1

            5000us:          7         1         2

            5500us:          7         2                   1

            6000us:          4         2         1         1

            6500us:          3                             1

            7000us:          6         2                   1

            7500us:          4         1                             1

            8000us:          5                             1

            8500us:                    1         1

            9000us:          2

            9500us:          2         1

          >10000us:          3                             1

        
    John.

    
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx