[ltp] T60p overheating problem (fixed)

[Richard]

Dear All,

Just thought it might be worth publishing a data point on this.

My T60p has been suffering for a long time from random crashes
- typically if the CPU load ever gets to 100% and stays there for more 
than 10 seconds, it will lock up totally. I even sent it back to IBM,
who replaced the system board (under warranty) and the problem remained.

Anyway, if I run  burnP6 & burnP6 &, I used to be able to reproduce the 
lockup within about 10 seconds (proc/acpi/ibm/thermal showed 100 degrees 
as the critical point just before lockup).

Having disassembled the machine, and put some arctic silver between CPU 
and fan (there was practically no goo there before), it's now much better 
behaved. I can now really hammer the machine (4 x burnP6, glxgears 
fullscreen, and cat /dev/sda > /dev/null) to test all 3 main systems. 
After half an hour, it's hit 96 degrees, but hasn't crashed yet.

* What's the critical temp? Aren't Intel CPUs supposed to underclock 
themselves automatically in order to cool down, and then recover the OS 
where it was?

* This is in a cool room (20 degrees) - I still haven't lots of margin.
Anything I can do better?
  [The fan is running fine, and I already blew the dust out]


On a different point, I just put an Intel SSD (X25-M 160 GB Gen2 
"mainstream") into it, and installed Lucid. The difference is amazing: it 
goes from power-button to login-screen in 7 seconds!


Best wishes,

Richard