Of the two flags, est (Enhanced SpeedStep) is the more interesting, as tm2 (Thermal Monitor 2) simply delivers a better way for the CPU to slow down (and draw less power) when it gets too hot. Alas none of my other servers do, as it was slow to move from the laptop cpus to the desktop and server ones. My core 1 laptop cpu supports both, all the core 2 laptops I've come across do too, all my xeon powered servers from the last 6 months do, and a smattering of the ones from the 12 months before that do too. The two main ones of interest are tm2 and est.
Handy for making your laptop batter life go longer, but also very handy for cutting your datacenter power bill!įirst up, can your x86 / 圆4 cpu support the more interesting new cpu power features? The answer hides in the flags section /proc/cpuinfo if you know what to look for. However, in the last few years, there are a couple of interesting new CPU features (and matching linux kernel code) which aim to deliver some fairly decent power savings when the cpu load is idle. It used to be a slightly fiddly thing involving acpi states, and didn't always deliver quite the savings one might want. How could I fix it (i.e.Intel (and AMD) cpus have been supporting some power management for some time now, especially on the mobile focused cpus. Maximum transition latency: Cannot determine or is not supported.Īvailable cpufreq governors: performance powersaveĬurrent CPU frequency: Unable to call hardwareĬurrent CPU frequency: 2.25 GHz (asserted by call to kernel)īoth these commands show basically the same than this which parse some cpu files: $ cd /sys/devices/system/cpu/cpu0/cpufreq & paste The governor "powersave" may decide which speed to useĪ same kind of output is shown by $ sudo cpupower frequency-info: analyzing CPU 0:
I also checked $ sudo cpufreq-info which shows the same high frequencies, which is strange because they are out of the allowed range for the powersave governor I set using the above command: cpufrequtils 008: cpufreq-info (C) Dominik Brodowski 2004-2009ĬPUs which run at the same hardware frequency: 0ĬPUs which need to have their frequency coordinated by software: 0Īvailable cpufreq governors: performance, powersaveĬurrent policy: frequency should be within 800 MHz and 800 MHz.
There isn't actually much than 1-2% CPU load at that time. I took it back a few hours later, and the command doesn't seem to be effective anymore, so I ran it again, but the watch process always shows higher-than-allowed frequencies now: Every 20.0s: cat /proc/cpuinfo | grep -i "mhz" I have set the frequencies of the 4 cores of my Intel(R) Core(TM) i7-4600U CPU 2.10GHz CPU to lower values ( 800Mhz) for energy saving when using the computer on the field using this command: for i in -g powersave -min 500Mhz -max 800Mhz doneĪnd it worked the first time I ran it, as shown by watch -n2 'cat /proc/cpuinfo | grep -i "mhz"': Every 20.0s: cat /proc/cpuinfo | grep -i "mhz"Īfter a while, I closed the lid, and the laptop (Lenovo T440s / Ubuntu 16.04 4.15.0-120-generic x86_64 GNU/Linux + another one where the same issue appears on Ubuntu 18.04 5.4.0-48-generic x86_64 GNU/Linux) went to sleep as usual.
0 kommentar(er)
