[Bug 12788] After suspend/resume, processor spends more time in C0 state, C3 hardly used

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



http://bugzilla.kernel.org/show_bug.cgi?id=12788





--- Comment #32 from James Ettle <theholyettlz@xxxxxxxxxxxxxx>  2009-03-26 09:22:20 ---
(In reply to comment #29)
> Hi, James
>     Will you please add the boot option of "idle=nomwait" on the latest kernel
> and see whether this issue still exists after resume?
>     Thanks.

I tried that option on kernel-2.6.29-3.fc10.x86_64. In this case, the system
took quite a bit longer to resume after pressing the power button and was also
*very* sluggish. Here's a powertop screenshot:


     PowerTOP version 1.10      (C) 2007 Intel Corporation

Cn                Avg residency       P-states (frequencies)
C0 (cpu running)        (52.9%)         2.11 Ghz    40.4%
C0                0.0ms ( 0.0%)         2.10 Ghz     2.2%
C1 halt           0.0ms ( 0.0%)         1200 Mhz     1.4%
C2                0.1ms ( 0.0%)          800 Mhz    55.1%
C3                0.6ms (47.1%)

Wakeups-from-idle per second : 847.9    interval: 10.0s
no ACPI power usage estimate available

Top causes for wakeups:
  27.3% ( 81.6)      <kernel IPI> : Rescheduling interrupts 
  16.6% ( 49.6)       <interrupt> : acpi 
  14.0% ( 41.9)   USB device  6-1 : USB Optical Mouse (Logitech) 
  13.2% ( 39.4)       <interrupt> : uhci_hcd:usb6, firewire_ohci, eth0 
   3.9% ( 11.7)       <interrupt> : ata_piix 
   3.9% ( 11.6)       <interrupt> : uhci_hcd:usb3, mmc0, mmc1,
i915@pci:0000:00:
02.0, iwlagn 
Suggestion: Disable the unused bluetooth interface with the following command:
  hciconfig hci0 down ; rmmod hci_usb
Bluetooth is a radio and consumes quite some power, and keeps USB busy as well.
 Q - Quit   R - Refresh   B - Turn Bluetooth off 


So it looks like the number of wakeups is reduced (I'll run it again later to
confirm this), but the C0 residence is still too high for idle and C1 is marked
as halt for some reason (is this the reason for the slowness?).

Without idle=nomwait, things are as before.

-- 
Configure bugmail: http://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.
--
To unsubscribe from this list: send the line "unsubscribe cpufreq" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[Index of Archives]     [Linux Kernel Devel]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Forum]     [Linux SCSI]

  Powered by Linux