RPI4 clock speeds and serial port ( temperatures idle and -j4 buildworld buildkernel )

[Mark Millard]

On 2021-Mar-18, at 13:50, Mark Millard <marklmi at yahoo.com> wrote:

> On 2021-Mar-18, at 13:01, Mark Millard <marklmi at yahoo.com> wrote:
> 
> On 2021-Mar-18, at 12:05, Mark Millard <marklmi at yahoo.com> wrote:
>> 
>>> . . .
>> 
>> I've not done temperate testing in a
>> while. One quick report I can make
>> is that for my "always cpu_freq 2000
>> always sdram_freq 3200" contexts
>> with the RPI4B only doing whatever
>> background tasks are involved in
>> being basically idle but having
>> the heatsinks and active cooling
>> (fans):
>> 
>> # sysctl -a | grep temper
>> hw.cpufreq.temperature: 35012
>> dev.cpu.0.temperature: 35.0C
>> 
>> in a currently 15.5C or so ambient
>> context is rather typical.
>> 
> 
> So I started up a from-scratch "rebuild self"
> -j buildworld buildkernel via an ssh over
> Ethernet session. (This may minimize
> interrupt overhead vs. the output text
> scrolling the serial console?)
> 
> 30+ minutes into the build:
> 
> I'm seeing figures like (the high so far):
> 
> hw.cpufreq.temperature: 49137
> dev.cpu.0.temperature: 49.1C
> 
> (Such pairs give some idea of the
> fairly short term variability.)
> 
> I'm only bothering to look once
> a minute or so:
> 
> # while (true); do sleep 60 ; sysctl hw.cpufreq.temperature dev.cpu.0.temperature ; done
> 
> So far the widest fairly-short-term variation
> was in:
> 
> hw.cpufreq.temperature: 45727
> dev.cpu.0.temperature: 45.6C
> 
> 
> FYI: The build reported:
> 
> make[1]: "/usr/fbsd/mm-src/Makefile.inc1" line 339: SYSTEM_COMPILER: Determined that CC=cc matches the source tree.  Not bootstrapping a cross-compiler.
> make[1]: "/usr/fbsd/mm-src/Makefile.inc1" line 344: SYSTEM_LINKER: Determined that LD=ld matches the source tree.  Not bootstrapping a cross-linker.
> 
> 
> Later I'll report the maximum(s) observed. But it will
> be a few hours for the build to complete.
> 

Looking at the -j4 buildworld buildkernel
output I see a few of examples of making
it into the 50s. The highest being:

hw.cpufreq.temperature: 52059
dev.cpu.0.temperature: 52.0C

Ignoring the start-warmup/end-cooldown: a few under 46.0C

So unlikely that there was any throttling.


FYI:

World build completed on Thu Mar 18 21:31:44 PDT 2021
World built in 29705 seconds, ncpu: 4, make -j4
. . .
Kernel build for GENERIC-NODBG completed on Thu Mar 18 22:10:02 PDT 2021
Kernel(s)  GENERIC-NODBG built in 2298 seconds, ncpu: 4, make -j4

So somewhat under 9 hours.


Note:
I've never checked how much of a difference
using a microsd card instead of the USB3 SSD
makes for such a temperature test.

===
Mark Millard
marklmi at yahoo.com
( dsl-only.net went
away in early 2018-Mar)