Running tegrastats causes cpufreq fluctuations

Autonomous Machines Jetson & Embedded Systems Jetson AGX Orin
1

I run jetson_clocks, so I expect CPUs to run at constant, max frequencies:

root@orin:~# jetson_clocks --show
SOC family:tegra234  Machine:Jetson AGX Orin
Online CPUs: 0-11
cpu0: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu1: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu10: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu11: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu2: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu3: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu4: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu5: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu6: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu7: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu8: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
cpu9: Online=1 Governor=schedutil MinFreq=2201600 MaxFreq=2201600 CurrentFreq=2201600 IdleStates: WFI=0 c7=0
GPU MinFreq=1300500000 MaxFreq=1300500000 CurrentFreq=1300500000
EMC MinFreq=204000000 MaxFreq=3199000000 CurrentFreq=3199000000 FreqOverride=1
DLA0_CORE:   Online=1 MinFreq=0 MaxFreq=1600000000 CurrentFreq=1600000000
DLA0_FALCON: Online=1 MinFreq=0 MaxFreq=844800000 CurrentFreq=844800000
DLA1_CORE:   Online=1 MinFreq=0 MaxFreq=1600000000 CurrentFreq=1600000000
DLA1_FALCON: Online=1 MinFreq=0 MaxFreq=844800000 CurrentFreq=844800000
PVA0_VPS0: Online=1 MinFreq=0 MaxFreq=1152000000 CurrentFreq=1152000000
PVA0_AXI:  Online=1 MinFreq=0 MaxFreq=832000000 CurrentFreq=832000000
FAN Dynamic Speed control=active hwmon2_pwm1=55
NV Power Mode: MAXN
root@orin:~#

However when I start tegrastats CPU frequencies start to fluctuate:

[ 5479.946808] cpufreq: cpu8,cur:2048000,set:2201600,set ndiv:172
[ 5480.967462] cpufreq: cpu0,cur:2002000,set:2201600,set ndiv:172
[ 5480.968117] cpufreq: cpu0,cur:2331000,set:2201600,set ndiv:172
[ 5481.996510] cpufreq: cpu8,cur:2485000,set:2201600,set ndiv:172
[ 5488.136842] cpufreq: cpu4,cur:2369000,set:2201600,set ndiv:172
[ 5490.182221] cpufreq: cpu0,cur:2390000,set:2201600,set ndiv:172
[ 5490.182872] cpufreq: cpu0,cur:2079000,set:2201600,set ndiv:172
[ 5490.186153] cpufreq: cpu8,cur:2380000,set:2201600,set ndiv:172
[ 5891.527045] cpufreq: cpu4,cur:2056000,set:2201600,set ndiv:172
[ 5893.570458] cpufreq: cpu0,cur:2059000,set:2201600,set ndiv:172
[ 5893.575829] cpufreq: cpu8,cur:2317000,set:2201600,set ndiv:172
[ 5895.618455] cpufreq: cpu0,cur:2348000,set:2201600,set ndiv:172
[ 5896.645144] cpufreq: cpu4,cur:2358000,set:2201600,set ndiv:172
[ 5902.791372] cpufreq: cpu8,cur:2329000,set:2201600,set ndiv:172
[ 5905.858457] cpufreq: cpu0,cur:2398000,set:2201600,set ndiv:172
[ 5905.861206] cpufreq: cpu4,cur:2048000,set:2201600,set ndiv:172
[ 6304.826290] cpufreq: cpu4,cur:2317000,set:2201600,set ndiv:172

It stops when I kill tegrastats.

4

Hi,
We will check this. For information, do you observe it on Jetpack 5.1.1?

5

All Jetpack 5 versions, including 5.1.1

6

I can trigger these “cpufreq” kernel messages just by doing, for example:

watch -n 0.1 "cat /sys/devices/system/cpu/cpufreq/policy8/cpuinfo_cur_freq"

Is there any update here? What’s interesting is in some of the output such as:

cpufreq: cpu8,cur:2390000,set:2201600,set ndiv:172

the cur:2390000 is actually greater than /sys/devices/system/cpu/cpufreq/policy8/cpuinfo_max_freq, which is 2201600

7

Was there a resolution to this?

We see the same issue - we use tegrastats to pull out resource usage statistics, so our log files are getting swamped with these messages.

8

It has not been resolved

9

Hi,
Do you observe the same on Jetpack 5.1.3 or on previous version?

10

Yes, we have
# R35 (release), REVISION: 4.1

12

Hi,
Please upgrade to Jetpack 6.0GA(r36.3) and try. It shall be fixed in the release.

14

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.