Hi I tried running: echo 10 >/sys/class/thermal/cooling_device0/cur_state echo 10 >/sys/class/thermal/cooling_device1/cur_state Both "max_state" is 10 and cur_state was 0 before. After that the whole system runs horribly slow. Running "htop" didn't show any CPU consuming process, though. Even the kernel threads were idle. Setting *either of them* to 0 made the system response timer much better again. Setting one to 10 and the other one to 5 makes the system slow again, but not as slow as with both at 10 so I think this is incremental. Since htop doesn't show anything I guess this attribute either changes the wrong option or the kernel is running in lots of interrupt handlers. Also I didn't notice any speed change of my fans. They run at the same "noise-level" with state 0 and 10. "cooling_device2" (LCD) doesn't show this behaviour. I run an Intel Atom N450 @ 1.66ghz (dual core or HT, I am not sure). Both cooling_devices correspond to one of the CPUs. Is there an easy way to debug this? Does running oprofile help? Or am I just misunderstanding what "cooling_deviceX" does? Regards David -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
