From mboxrd@z Thu Jan 1 00:00:00 1970 Content-Type: multipart/mixed; boundary="===============8865882056590177404==" MIME-Version: 1.0 From: Marc MERLIN Subject: [Powertop] powertop 2.6 still reports incorrect device battery usage Date: Thu, 21 Aug 2014 13:49:45 -0700 Message-ID: <20140821204945.GD3875@merlins.org> To: powertop@lists.01.org List-ID: --===============8865882056590177404== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On kernel 3.15.5, thinkpad T540p IDPS display, intel graphics I'm still getting bogus numbers for devices. Snapshot #1: = - My wifi card is certainly not using 12.7W - Display backlight + wifi =3D 17.9W, which means the entire laptop would be running on 2W? That's of course wrong - The 1117 wakeups are not accounted for and apps blamed correctly for that use > The battery reports a discharge rate of 19.8 W > The estimated remaining time is 2 hours, 37 minutes > = > Summary: 1117.0 wakeups/second, 182.7 GPU ops/seconds, 0.0 VFS ops/sec a= nd 9.0% CPU use > = > Power est. Usage Events/s Category Description > 12.7 W 36.3 pkts/s Device Network interface:= wlan0 (iwlwifi) > 5.17 W 8.0% Device Display backlight > 322 mW 25.0 ms/s 331.3 Process /usr/bin/enlighten= ment > 179 mW 19.7 ms/s 60.7 Process /usr/bin/X :0 vt7 = -br -nolisten tcp -auth > 178 mW 4.8 ms/s 246.2 Process xmms I blew away my calibration, upgraded from powertop 2.4 to 2.6.1, and now I see: The battery reports a discharge rate of 17.6 W The estimated remaining time is 5 hours, 10 minutes Summary: 893.0 wakeups/second, 26.4 GPU ops/seconds, 0.0 VFS ops/sec and 1= 1.3% CPU use Power est. Usage Events/s Category Description 18.7 W 216.8 pkts/s Device Network interface: w= lan0 (iwlwifi) 5.16 W 33.0% Device Display backlight 61.0 mW 35.8 ms/s 86.5 Process dpkg 39.4 mW 1.6 ms/s 24.9 Process xfce4-terminal -T wi= ndow1.10 --role=3Dwindow1.10 --tab 35.6 mW 8.2 ms/s 133.2 kWork normal_work_helper How can powertop tell me that my wireless card is using more power than the entire laptop? Clearly the calibration didn't work right, but shouldn't the code have chec= ks for things that are clearly wrong and tell the user what to do to fix them/= recalibrate? Or better, shouldn't it retune the device usage on its own when it finds something clearly wrong like power use of the laptop being negative after removing devices, or inconsistent with the basic power usage calculated during calibration? Thanks, Marc -- = "A mouse is a device used to point at the xterm you want to type in" - A.S.= R. Microsoft is to operating systems .... .... what McDonalds is to gourmet coo= king Home page: http://marc.merlins.org/ | PGP 1024R/763= BE901 --===============8865882056590177404==--