PowerMac G5 quad-core, CPU A1 DIODE TEMP: 90.8 C (for example): How to handle? [more data]

[Adrian Chadd]

On 17 January 2015 at 08:09, Justin Hibbits <chmeeedalf at gmail.com> wrote:
> The new algorithm in this patch is supposed to put the fans at full
> throttle around the midpoint, so around 70C they should be at full
> blast.
>
> Have you tried the same machine under heavy load with OS X or Linux?
> We can keep adjusting the algorithm, as long as your machine is known
> to be good enough under one of those OSs.  If they also overheat,
> there's nothing we can do, since OS X at least should run fine with
> heavy load, as long as the hardware can handle it.

Can you force introduce halt cycles to compensate for the increasing
rise in temperature?




-adrian

> - Justin
>
> On Sat, 17 Jan 2015 03:38:33 -0800
> Mark Millard <markmi at dsl-only.net> wrote:
>
>> I've now tested the new patch and strongly expect that the new code
>> is much better but it is not sufficient to keep the temperature down
>> on the problematical quad-core G5 that I've been testing via
>> buildworld. It did last over 30 minutes and there were no 0 rpm
>> figures sampled for this new code.
>>
>> Note: it turns out the two sysctl dumps of samples (dev.smu and
>> dev.smusat) are done (as a pair) more like once every 3 to 4 seconds,
>> not once a second. I include timestamps this time.
>>
>> The new code ended up keeping the intake and exhaust fans near the
>> 3200 maxrpm for a long time and the pump near the maxrpm 3600 too.
>> But that was not enough for this G5 to keep its cool. It would
>> apparently take giving the CPUs/cores some periodic idle time to cool
>> down in order to keep this G5 cool enough. (Really just cpu a1
>> needing such.)
>>
>> Over the interval below (01:45:51 to 02:13:50) no .rpm figure was
>> sampled as < 3100 and no pump.rpm was sampled as < 3400.
>>
>> Sat Jan 17 01:45:51 PST 2015
>> dev.smu.0.fans.cpu_a_intake.rpm: 3131
>> dev.smu.0.fans.cpu_b_intake.rpm: 3131
>> dev.smu.0.fans.cpu_a_exhaust.rpm: 3127
>> dev.smu.0.fans.cpu_b_exhaust.rpm: 3143
>> dev.smu.0.fans.cpu_a_pump.rpm: 3549
>> dev.smusat.0.cpu_a0_diode_temp: 59.4C
>> dev.smusat.0.cpu_a1_diode_temp: 70.3C
>> dev.smusat.1.cpu_b0_diode_temp: 59.1C
>> dev.smusat.1.cpu_b1_diode_temp: 64.8C
>> Sat Jan 17 01:45:54 PST 2015
>> ... Over the below range pump.rpm is sampled as < 3500 only 6 times
>> (each > 3400)... Sat Jan 17 02:01:46 PST 2015
>> dev.smu.0.fans.cpu_a_intake.rpm: 3197
>> dev.smu.0.fans.cpu_b_intake.rpm: 3202
>> dev.smu.0.fans.cpu_a_exhaust.rpm: 3200
>> dev.smu.0.fans.cpu_b_exhaust.rpm: 3198
>> dev.smu.0.fans.cpu_a_pump.rpm: 3636
>> dev.smusat.0.cpu_a0_diode_temp: 67.6C
>> dev.smusat.0.cpu_a1_diode_temp: 81.6C
>> dev.smusat.1.cpu_b0_diode_temp: 61.0C
>> dev.smusat.1.cpu_b1_diode_temp: 65.6C
>> Sat Jan 17 02:01:50 PST 2015
>> ... The last lines that made it into the file before automatic
>> shutdown were ... Sat Jan 17 02:13:50 PST 2015
>> dev.smu.0.fans.cpu_a_intake.rpm: 3200
>> dev.smu.0.fans.cpu_b_intake.rpm: 3199
>> dev.smu.0.fans.cpu_a_exhaust.rpm: 3199
>> dev.smu.0.fans.cpu_b_exhaust.rpm: 3197
>> dev.smu.0.fans.cpu_a_pump.rpm: 3614
>> dev.smusat.0.cpu_a0_diode_temp: 73.0C
>> dev.smusat.0.cpu_a1_diode_temp: 90.9C
>> dev.smusat.1.cpu_b0_diode_temp: 62.6C
>> dev.smusat.1.cpu_b1_diode_temp: 67.1C
>> Sat Jan 17 02:13:54 PST 2015
>>
>> So for the last 12 minutes or so the cpu intakes, exhausts, and pump
>> were going basically full blast. It was not enough for my context but
>> likely would help some other contexts.