Hi,
I wonder if someone on this mailing list may be able to help me
understand what's going on inside of my laptop.
It's an Intel Core2 Duo CPU and powertop tells me that even though I
have connected a usb keyboard and mouse (the laptop and the port
replicator lack PS/2 completely, but as long as I'm not on battery I
don't mind) the CPU enters C3 state a lot (99.x %).
At least with my last laptop the CPU was not able to enter C-states
below C2 with USB-HID devices plugged in because the devices needed to
be polled - otherwise they wouldn't work, would they?
So now I'm wondering if the CPU really enters C3 with the devices
plugged in or if this may be a misleading information - AFAIK the two
cores of the Core2 Duo can enter C-states individually and so I conclude
that at least one core shold be unable to enter C-states lower than C2.
How does PowerTOP handle the case of multiple CPUs/cores being present
regarding the C-state information?
This is what I PowerTOP is telling me:
PowerTOP version 1.7 (C) 2007 Intel Corporation
Cn Avg residency P-states (frequencies)
C0 (cpu running) ( 0.3%)
C1 0.0ms ( 0.0%) 2.01 Ghz 7.5%
C2 0.1ms ( 0.0%) 2.00 Ghz 0.0%
C3 29.7ms (99.6%) 1200 Mhz 0.0%
800 Mhz 92.5%
Wakeups-from-idle per second : 34.9 interval: 15.0s
no ACPI power usage estimate available
Top causes for wakeups:
34.0% ( 15.9) rc.local : queue_delayed_work_on
(delayed_work_timer_fn)
21.4% ( 10.0) <kernel core> : ehci_work (ehci_watchdog)
17.2% ( 8.1) icedove-bin : futex_wait (hrtimer_wakeup)
4.4% ( 2.1) Xorg : do_setitimer (it_real_fn)
4.3% ( 2.0) <kernel core> : queue_delayed_work_on
(delayed_work_timer_fn)
4.3% ( 2.0) xfsbufd : schedule_timeout (process_timeout)
3.6% ( 1.7) fluxbox : schedule_timeout (process_timeout)
2.6% ( 1.2) Xorg : schedule_timeout (process_timeout)
2.1% ( 1.0) mpd : schedule_timeout (process_timeout)
1.3% ( 0.6) <interrupt> : eth0
1.0% ( 0.5) <kernel core> : e1000_intr_msi (e1000_watchdog)
0.6% ( 0.3) <kernel core> : neigh_table_init_no_netlink
(neigh_periodic_timer)
0.4% ( 0.2) events/1 : __netdev_watchdog_up (dev_watchdog)
0.4% ( 0.2) init : schedule_timeout (process_timeout)
0.3% ( 0.1) gaim : schedule_timeout (process_timeout)
0.3% ( 0.1) xfssyncd : schedule_timeout (process_timeout)
0.3% ( 0.1) <kernel core> : inet_twsk_schedule (inet_twdr_hangman)
0.1% ( 0.1) <interrupt> : acpi
0.1% ( 0.1) <interrupt> : libata
The kernel is a 2.6.22-hrt3 64-bit if that matters. And BTW, 2.6.22-hrt3
is the first -hrt kernel that actually boots on my laptop, previous -hrt
kernels did not boot (the screen simply stayed black without any obvious
activity of the hard disk or everything else - it just didn't work at all).
So if anyone had similar trouble, give 2.6.22-hrt3 a try :)
Peter
_______________________________________________
Power mailing list
[email protected]
http://www.bughost.org/mailman/listinfo/power
