[Rescheduling interrupts] <kernel IPI> and i8042, too many wakeups are consuming my battery

Bug #1031459 reported by carlosv on 2012-07-31
18
This bug affects 3 people
Affects Status Importance Assigned to Milestone
Linux
Incomplete
Medium
The Ubuntu Power Consumption Project
Undecided
Unassigned

Bug Description

Hi,

My laptop is wasting too much energy. I have a Lenovo e420s. Core i5 sandy bridge. Normaly it supposed to last 5 hours the battery life but in Ubuntu is reduced to 2,5 hours. I have tried all the ACPI options in the documentation https://help.ubuntu.com/community/ReschedulingInterrupts and no help.

The powertop shows:

Wakeups-from-idle per second : 57.6 interval: 60.0s
Power usage (ACPI estimate): 16.2W (2.5 hours)
Top causes for wakeups:
  27.0% ( 67.8) [Rescheduling interrupts] <kernel IPI>
  16.9% ( 42.4) [iwlwifi] <interrupt>
   8.5% ( 21.4) [i915] <interrupt>
   8.3% ( 20.9) compiz
   6.7% ( 16.9) fingerprint-pol
   6.7% ( 16.8) swapper/2
   6.2% ( 15.5) PS/2 keyboard/mouse/touchpad interrupt
   6.0% ( 15.1) swapper/0
   0.4% ( 1.1)D tor
   0.0% ( 0.1)D nmbd
   2.0% ( 5.0) syndaemon
   1.7% ( 4.2) swapper/1
   1.4% ( 3.4) swapper/3
   1.2% ( 3.0) Xorg
   1.0% ( 2.5) [ahci] <interrupt>
   0.8% ( 2.0) [ehci_hcd:usb2] <interrupt>
   0.8% ( 2.0) nautilus
   0.7% ( 1.8) [acpi] <interrupt>
   0.4% ( 1.1) kworker/0:3
   0.4% ( 1.0) gvfs-afc-volume

And in the file /proc/interrupts I got:

          CPU0 CPU1 CPU2 CPU3
  0: 51 0 0 0 IO-APIC-edge timer
  1: 1682 0 0 0 IO-APIC-edge i8042
  8: 1 0 0 0 IO-APIC-edge rtc0
  9: 4898 0 60 0 IO-APIC-fasteoi acpi
 12: 620964 0 0 0 IO-APIC-edge i8042
 16: 4652 0 0 0 IO-APIC-fasteoi ehci_hcd:usb1
 18: 0 0 0 0 IO-APIC-fasteoi mmc0
 23: 4874 0 22381 0 IO-APIC-fasteoi ehci_hcd:usb2
 41: 44574 0 0 0 PCI-MSI-edge ahci
 42: 0 0 0 0 PCI-MSI-edge eth1
 43: 24972 0 200125 0 PCI-MSI-edge i915
 44: 15 0 0 0 PCI-MSI-edge mei
 45: 86374 0 0 0 PCI-MSI-edge iwlwifi
 46: 935 0 0 0 PCI-MSI-edge snd_hda_intel
NMI: 235 79 190 74 Non-maskable interrupts
LOC: 138801 99257 130245 107984 Local timer interrupts
SPU: 0 0 0 0 Spurious interrupts
PMI: 235 79 190 74 Performance monitoring interrupts
IWI: 0 0 0 0 IRQ work interrupts
RES: 400015 111852 409898 123532 Rescheduling interrupts
CAL: 646 703 672 724 Function call interrupts
TLB: 21777 7266 15390 6198 TLB shootdowns
TRM: 4 4 4 4 Thermal event interrupts
THR: 0 0 0 0 Threshold APIC interrupts
MCE: 0 0 0 0 Machine check exceptions
MCP: 7 7 7 7 Machine check polls
ERR: 0
MIS: 0

The module (or driver) i8042 woke up 620964 times the CPU.

Does any body has the idea why my laptop is wasting so much power?

carlosv (cvedovatti) wrote :
carlosv (cvedovatti) wrote :
Changed in linux:
importance: Unknown → Medium
status: Unknown → Confirmed
megain (lunch-j) on 2012-08-15
tags: added: i915
megain (lunch-j) wrote :
Download full text (3.9 KiB)

same thing here ubuntu 12. 04 3.2.0-29-generic x86_64
kernel rescheduling and i915 are interrupting the hell out of the cpu

Power usage (ACPI estimate): 16.9W (0.7 hours) (long term: 9.9W,/1.2h)

Top causes for wakeups:
  58.9% (949.1) [Rescheduling interrupts] <kernel IPI>
   9.5% (152.7) [i915] <interrupt>
   6.1% ( 97.9) swapper/1
   4.9% ( 78.9) swapper/0
   3.6% ( 57.6) swapper/3
   3.3% ( 53.5) swapper/2
   2.5% ( 40.7) USB device 1-1.2 : Apple Internal Keyboard / Trackpad (Apple Inc.)
   2.4% ( 38.7) [ehci_hcd:usb1] <interrupt>
   1.0% ( 16.5) compiz
   0.7% ( 11.8) [mmc0, b43] <interrupt>
   0.5% ( 8.1) [acpi] <interrupt>
   0.3% ( 5.0) syndaemon
   0.2% ( 4.0) unity-panel-ser
   0.2% ( 3.7) [TLB shootdowns] <kernel IPI>
   0.2% ( 2.7) [ata_piix, uhci_hcd:usb4] <interrupt>
   0.1% ( 2.0) kworker/1:1
   0.1% ( 2.0) indicator-multi
   0.1% ( 2.0) kworker/u:0
   0.1% ( 1.2) Xorg
   0.1% ( 1.0) gvfs-afc-volume
   0.1% ( 1.0) kworker/u:2
   0.1% ( 1.0) watchdog/0
   0.0% ( 0.7) indicator-cpufr
   0.0% ( 0.7) upowerd
   0.0% ( 0.5) kworker/1:0
   0.0% ( 0.3) accounts-daemon
   0.0% ( 0.3) unity-applicati
   0.0% ( 0.3) zeitgeist-datah
   0.0% ( 0.3) gnome-settings-
   0.0% ( 0.2) update-notifier

/proc/interrupts

        CPU0 CPU1 CPU2 CPU3
  0: 51 0 0 0 IO-APIC-edge timer
  8: 1 0 0 0 IO-APIC-edge rtc0
  9: 23200 0 0 0 IO-APIC-fasteoi acpi
 17: 49638 0 0 0 IO-APIC-fasteoi mmc0, b43
 19: 36781 0 0 0 IO-APIC-fasteoi ata_piix, uhci_hcd:usb4
 21: 0 0 0 0 IO-APIC-fasteoi uhci_hcd:usb3
 22: 61 0 0 0 IO-APIC-fasteoi ehci_hcd:usb2
 23: 123062 41 0 0 IO-APIC-fasteoi ehci_hcd:usb1
 40: 0 0 0 0 PCI-MSI-edge PCIe PME
 41: 0 0 0 0 PCI-MSI-edge PCIe PME
 42: 0 0 0 0 PCI-MSI-edge PCIe PME
 43: 0 0 0 0 PCI-MSI-edge PCIe PME
 44: 0 0 0 0 PCI-MSI-edge PCIe PME
 45: 22 21 0 0 PCI-MSI-edge firewire_ohci
 46: 12 0 0 0 PCI-MSI-edge mei
 47: 331877 0 0 0 PCI-MSI-edge i915
 48: 334 806 0 0 PCI-MSI-edge snd_hda_intel
 49: 1 0 0 0 PCI-MSI-edge eth0-0
 50: 1 0 0 0 PCI-MSI-edge eth0-1
 51: 1 0 0 0 PCI-MSI-edge eth0-2
 52: 1 0 0 0 PCI-MSI-edge eth0-3
 53: 1 0 0 0 PCI-MSI-edge eth0-4
NMI: 60 52 21 20 Non-maskable interrupts
LOC: 306654 ...

Read more...

megain (lunch-j) wrote :
megain (lunch-j) wrote :
Changed in linux:
status: Confirmed → Incomplete
To post a comment you must log in.
This report contains Public information  Edit
Everyone can see this information.

Other bug subscribers

Remote bug watches

Bug watches keep track of this bug in other bug trackers.