Re: [RFC PATCH v2 09/13] perf vendor events: Add JSON metrics for imx8mm DDR Perf

[John Garry]

On 20/04/2020 05:17, Joakim Zhang wrote:
> However, it seems that there are small defects from metric.
>
> Firstly, could you help change "ScaleUnit": "9.765625e-4MB" into "ScaleUnit": "9.765625e-4KB", this is a mistake.

ok

> Then, you can see that test is okay from 8MM. However, metric would add twice once time from 8QM which has two ddr perf(ddr0/ddr1), it looks incorrect.
>
> 8MM:
> root@imx8mmevk:~# ./perf stat -v -a -I 1000 -M imx8mm_ddr_write.all
> Using CPUID 0x00000000410fd030
> metric expr imx8_ddr.write_cycles * 4 * 4 for imx8mm_ddr_write.all
> found event imx8_ddr.write_cycles
> adding {imx8_ddr.write_cycles}:W
> imx8_ddr.write_cycles -> imx8_ddr0/event=0x2b/
> imx8_ddr.write_cycles: 13153 1000495125 1000495125
> #           time             counts unit events
>       1.000476625              13153      imx8_ddr.write_cycles     #    205.5 MB  imx8mm_ddr_write.all
> imx8_ddr.write_cycles: 3582 1000681375 1000681375
>       2.001167750               3582      imx8_ddr.write_cycles     #     56.0 MB  imx8mm_ddr_write.all
>
>
> 8QM:
> root@imx8qmmek:~# ./perf stat -v -a -I 1000 -M imx8qm_ddr_read.all

Note: for this example, I don't know why you didn't use 
imx8mm_ddr_write.all, as for your 8MM test, so we can compare the same.

> Using CPUID 0x00000000410fd030
> metric expr imx8_ddr.read_cycles * 4 * 4 for imx8qm_ddr_read.all
> found event imx8_ddr.read_cycles
> metric expr imx8_ddr.read_cycles * 4 * 4 for imx8qm_ddr_read.all
> found event imx8_ddr.read_cycles
> adding {imx8_ddr.read_cycles}:W,{imx8_ddr.read_cycles}:W
> imx8_ddr.read_cycles -> imx8_ddr0/event=0x2a/
> imx8_ddr.read_cycles -> imx8_ddr1/event=0x2a/
> imx8_ddr.read_cycles -> imx8_ddr0/event=0x2a/
> imx8_ddr.read_cycles -> imx8_ddr1/event=0x2a/
> imx8_ddr.read_cycles: 22748 1000378750 1000378750
> imx8_ddr.read_cycles: 24640 1000376625 1000376625
> imx8_ddr.read_cycles: 22800 1000375125 1000375125
> imx8_ddr.read_cycles: 24616 1000372625 1000372625
> #           time             counts unit events
>       1.000377250              47388      imx8_ddr.read_cycles      #    740.4 MB  imx8qm_ddr_read.all
>       1.000377250              47416      imx8_ddr.read_cycles
> imx8_ddr.read_cycles: 32672 1000454375 1000454375
> imx8_ddr.read_cycles: 37888 1000457250 1000457250
> imx8_ddr.read_cycles: 32736 1000460250 1000460250
> imx8_ddr.read_cycles: 38012 1000463000 1000463000
>       2.000812375              70560      imx8_ddr.read_cycles      #   1102.5 MB  imx8qm_ddr_read.all
>       2.000812375              70748      imx8_ddr.read_cycles

I that is just how the aliases work. But how about trying:

./perf stat -v -a -I 1000 -M imx8_ddr0/imx8qm_ddr_read.all/


for just ddr0

I know that the following worked for non-metrics for aliases on a 
specific HW PMU, so I guess should also work for metrics:

./perf stat -e smmuv3_pmcg_200148020/smmuv3_pmcg.l1_tlb/

Thanks,
John