How do you read CPU temps?

[joeschmuck]

So I can see that the CPU temp might be viewable but exactly how is that performed?

Thanks,
Mark

 

[pauldonovan]

Code:

sysctl | grep temperature

Or install the mbmon package. Only the latter works on my particular Atom 525 CPU.

Paul

 

[joeschmuck]

Solved

Paul,
Thanks for the reply. Once I got that well it didn't work however it helped me find the answer. Try this...

Code:

sysctl -a | grep temperature

Something else to try is replacing temperature with cpu, a full list of CPU items will be listed. Look for something that lists the cpu temperature and enter it into the command.

Here is what mine looks like...

Code:

%sysctl -a | grep cpu
kern.ccpu: 0
  <cpu count="2" mask="0x3">0, 1</cpu>
    <cpu count="2" mask="0x3">0, 1</cpu>
coretemp0: <CPU On-Die Thermal Sensors> on cpu0
est0: <Enhanced SpeedStep Frequency Control> on cpu0
p4tcc0: <CPU Frequency Thermal Control> on cpu0
coretemp1: <CPU On-Die Thermal Sensors> on cpu1
est1: <Enhanced SpeedStep Frequency Control> on cpu1
p4tcc1: <CPU Frequency Thermal Control> on cpu1
 cpu0 (BSP): APIC ID:  0
 cpu1 (AP): APIC ID:  1
cpu0: <ACPI CPU> on acpi0
cpu1: <ACPI CPU> on acpi0
coretemp0: <CPU On-Die Thermal Sensors> on cpu0
est0: <Enhanced SpeedStep Frequency Control> on cpu0
p4tcc0: <CPU Frequency Thermal Control> on cpu0
coretemp1: <CPU On-Die Thermal Sensors> on cpu1
est1: <Enhanced SpeedStep Frequency Control> on cpu1
p4tcc1: <CPU Frequency Thermal Control> on cpu1
 cpu0 (BSP): APIC ID:  0
 cpu1 (AP): APIC ID:  1
cpu0: <ACPI CPU> on acpi0
cpu1: <ACPI CPU> on acpi0
coretemp0: <CPU On-Die Thermal Sensors> on cpu0
est0: <Enhanced SpeedStep Frequency Control> on cpu0
p4tcc0: <CPU Frequency Thermal Control> on cpu0
coretemp1: <CPU On-Die Thermal Sensors> on cpu1
est1: <Enhanced SpeedStep Frequency Control> on cpu1
p4tcc1: <CPU Frequency Thermal Control> on cpu1
 cpu0 (BSP): APIC ID:  0
 cpu1 (AP): APIC ID:  1
cpu0: <ACPI CPU> on acpi0
cpu1: <ACPI CPU> on acpi0
coretemp0: <CPU On-Die Thermal Sensors> on cpu0
est0: <Enhanced SpeedStep Frequency Control> on cpu0
p4tcc0: <CPU Frequency Thermal Control> on cpu0
coretemp1: <CPU On-Die Thermal Sensors> on cpu1
est1: <Enhanced SpeedStep Frequency Control> on cpu1
p4tcc1: <CPU Frequency Thermal Control> on cpu1
kern.smp.cpus: 2
kern.smp.maxcpus: 32
debug.cpufreq.verbose: 0
debug.cpufreq.lowest: 0
debug.kdb.stop_cpus: 1
hw.ncpu: 2
hw.acpi.cpu.cx_lowest: C1
machdep.hlt_cpus: 0
security.jail.param.cpuset.id: 0
dev.cpu.0.%desc: ACPI CPU
dev.cpu.0.%driver: cpu
dev.cpu.0.%location: handle=\_PR_.P001
dev.cpu.0.%pnpinfo: _HID=none _UID=0
dev.cpu.0.%parent: acpi0
dev.cpu.0.temperature: 43.0C
dev.cpu.0.freq: 3166
dev.cpu.0.freq_levels: 3166/89000 2770/77875 2670/80000 2336/72000 2044/63000 2003/65000 1752/56875 1502/48750 1251/40625 1001/32500 751/24375 500/16250 250/8125
dev.cpu.0.cx_supported: C1/0
dev.cpu.0.cx_lowest: C1
dev.cpu.0.cx_usage: 100.00% last 55us
dev.cpu.1.%desc: ACPI CPU
dev.cpu.1.%driver: cpu
dev.cpu.1.%location: handle=\_PR_.P002
dev.cpu.1.%pnpinfo: _HID=none _UID=0
dev.cpu.1.%parent: acpi0
dev.cpu.1.temperature: 27.0C
dev.cpu.1.cx_supported: C1/0
dev.cpu.1.cx_lowest: C1
dev.cpu.1.cx_usage: 100.00% last 93us
dev.acpi_perf.0.%parent: cpu0
dev.acpi_perf.1.%parent: cpu1
dev.coretemp.0.%parent: cpu0
dev.coretemp.1.%parent: cpu1
dev.est.0.%parent: cpu0
dev.est.1.%parent: cpu1
dev.cpufreq.0.%driver: cpufreq
dev.cpufreq.0.%parent: cpu0
dev.cpufreq.1.%driver: cpufreq
dev.cpufreq.1.%parent: cpu1
dev.p4tcc.0.%parent: cpu0
dev.p4tcc.1.%parent: cpu1
%

And you can see my two cores are dev.cpu.0.temperature: 43.0C and dev.cpu.0.temperature: 27.0C but in your case the temperatures are likely to be closer as my CPU has a bad CPU 0 sensor. It's a known issue but I wasn't going to return my CPU since it works. Not worth the money to ship it back.

So I'll do this to read my temp on my good core...

Code:

%sysctl -a | grep cpu.1.temp
dev.cpu.1.temperature: 27.0C
%

And thanks again, without your comment I wouldn't think I was on the right path.

-Mark

P.S. I'd be curious if this works for everyone or if it fails. I placed a feature ticket in earlier today desiring a graph and possibly an email for temp alarms. I would like the ability to choose the core(s) and temp alarm set point. Any failure data might help the developers implementing it.