Canonical Voices

Posts tagged with 'temperature'

Colin Ian King

Sensors reporting hot CPU in Maverick

My clunky old Lenovo has and Intel(R) Core(TM) Duo CPU (model 15) which coretemp in Lucid 10.04 assumed TjMax was 85 degrees C but now in Maverick 10.10 believes TjMax is 100 degrees C.

Kernel commit a321cedb12904114e2ba5041a3673ca24deb09c9 attempts to get TjMax from msr 0x1a2. If it fails to read this msr it defaults TjMax to 100 degrees C for CPU models 14, 15, 22 and 26, and one will see the following warning message:

[ 9.650025] coretemp coretemp.0: TjMax is assumed as 100 C!
[ 9.650322] coretemp coretemp.1: TjMax is assumed as 100 C!

For CPU models 23 and 28 (Atoms) TjMax will be 90 or 100 depending if it's a nettop or a netbook. Otherwise the patch will default TjMax to 100 degrees C.

One can check the value of TjMax using:

cat devices/platform/coretemp*/temp1_crit

Coretemp calculates the core temperature of the CPU by subtracting the thermal status from TjMax. Since the default has been increased from 85 to 100 degrees between Lucid and Maverick, the apparent core temperature now reads 15 degrees higher.

Now, if my machine really was running 15 degrees hotter between Lucid and Maverick I would see more power consumption. I checked the power consumption for Lucid and Maverick kernels on my Lenovo in idle and fully loaded CPU states with a power meter and observed that Maverick uses less power, so that's encouraging.

As for the correct value, why did the default change? Well, from what I can understand from several forums that discuss the setting of TjMax is that this is not well documented and not disclosed by Intel, hence the values are rule-of-thumb guesswork.

So, the bottom line is that if your CPU appears to run hot from the core temp readings between Lucid 10.04 and Maverick 10.10 first check to see if TjMax has changed on your hardware.

Read more
Colin Ian King

There are times when I drive my laptop CPU really hard, for example compressing Gigs of data or running QEMU, and it would be useful to see how hot my processor is actually getting. This is where sensors-applet is useful - it has the ability to show the core temperature of the CPU and HDD if one has the appropriate hardware sensors and drivers installed. However, getting it configured requires a little bit of hand-holding to get it working.

Firstly, install sensors-applet using:

sudo apt-get install sensors-applet

..this will also install the lm-sensors tools.

Next, one needs to probe the H/W to find the appropriate drivers required to be able to sense CPU and HDD temperatures. To do this use:

sudo sensors-detect

This will ask you if you want to probe and scan various I2C, PCI and SMBus adaptors, so answer the probing questions with respect to the hardware you have in your machine. On my machine I answered "YES" to every question, your mileage may vary.

At the end of the probing, sensors-detect will print out some lines that you need to add to /etc/modules. Using sudo, edit /etc/modules and add these lines. Then reboot your machine.

Once you are logged in again, right click on the top Gnome panel and select "Add to Panel.." and scroll down and select the "Hardware Sensors Monitor". Once it's added to the panel, right click on it and select "Preferences". On the Sensors Applet Preferences panel, select the "Sensors" tab and then select the appropriate CPU and HDD devices to monitor.

Once this is done, you will hopefully be able to see your CPU and HDD temperatures rise and fall as you work on your machine:

From the command line one can also get the current sensor data using the sensors command, e.g.:

$ sensors
Adapter: ISA adapter
Core 0: +58.0°C (high = +85.0°C, crit = +85.0°C)

Adapter: ISA adapter
Core 1: +57.0°C (high = +85.0°C, crit = +85.0°C)

Hopefully I won't see my CPU get to 85 degrees C, but now at least I can keep my eye on how hot it's getting :-)

Read more