On Tue, 2018-07-31 at 17:04 +0200, Peter Zijlstra wrote: > On Mon, Jul 30, 2018 at 07:06:21AM -0700, Srinivas Pandruvada wrote: > > On Mon, 2018-07-30 at 14:16 +0300, Eero Tamminen wrote: > > > Questions: > > > > > > * Does currently kernel CPU freq management have any idea which > > > IO > > > devices share TDP with the CPU cores? > > No. The requests we do to hardware is just indication only (HW can > > ignore it). The HW has a bias register to adjust and distribute > > power > > among users. > > We can have several other active device on servers beside CPU which > > when runs need extra power. So the HW arbitrates power. > > That's not entirely accurate AFAIK. "No" is accurate for Intel, but > the > ARM people have their IPA thing (not a beer): We also have that for using space programs (E.g. KBL-G).
Thanks, Srinivas > > https://developer.arm.com/open-source/intelligent-power-allocation > > drivers/thermal/power_allocator.c > > which IIUC interacts with their cpufreq driver to disallow certain > OPP > states. > > And note that I discourage intel_pstate active mode.
