David Rees wrote:
> What's the output of `powertop -d` look like?
[EMAIL PROTECTED]:~# powertop -d
PowerTOP 1.9 (C) 2007 Intel Corporation
Collecting data for 15 seconds
< Detailed C-state information is only available on Mobile CPUs (laptops) >
P-states (frequencies)
1500 Mhz 0.9%
800 Mhz 99.1%
Wakeups-from-idle per second : 467.9 interval: 15.0s
no ACPI power usage estimate available
Top causes for wakeups:
32.0% (105.4) mythfrontend.re : schedule_timeout (process_timeout)
26.6% ( 87.7) <interrupt> : ide0
10.5% ( 34.5) <interrupt> : uhci_hcd:usb1, uhci_hcd:usb2,
uhci_hcd:usb3, ehci_hcd:usb4
5.2% ( 17.2) <interrupt> : eth0
5.0% ( 16.5) mythbackend : futex_wait (hrtimer_wakeup)
4.2% ( 13.9) mythfrontend.re : futex_wait (hrtimer_wakeup)
3.8% ( 12.5) cpufreq-set : queue_delayed_work_on
(delayed_work_timer_fn)
2.4% ( 7.9) <kernel module> : usb_hcd_poll_rh_status (rh_timer_func)
2.2% ( 7.1) <kernel core> : ehci_work (ehci_watchdog)
2.0% ( 6.5) khubd : dvb_usb_remote_init
(delayed_work_timer_fn)
0.6% ( 2.1) Xorg : do_setitimer (it_real_fn)
0.6% ( 2.0) xfce-mcs-manage : schedule_timeout (process_timeout)
0.5% ( 1.5) mtd : schedule_timeout (process_timeout)
0.3% ( 1.1) mythbackend : schedule_timeout (process_timeout)
0.3% ( 1.0) ntpd : do_setitimer (it_real_fn)
0.3% ( 1.0) <kernel core> : queue_delayed_work_on
(delayed_work_timer_fn)
0.3% ( 1.0) apache2 : schedule_timeout (process_timeout)
0.3% ( 1.0) gam_server : schedule_timeout (process_timeout)
0.3% ( 1.0) dhcdbd : schedule_timeout (process_timeout)
0.3% ( 1.0) xfce4-panel : schedule_timeout (process_timeout)
0.3% ( 1.0) ntpdate : do_adjtimex (sync_cmos_clock)
0.3% ( 1.0) mtd : futex_wait (hrtimer_wakeup)
0.3% ( 1.0) xfce4-mixer-plu : schedule_timeout (process_timeout)
0.3% ( 1.0) nm-applet : schedule_timeout (process_timeout)
0.2% ( 0.6) <kernel core> : sk_reset_timer (tcp_delack_timer)
0.2% ( 0.6) kdvb-fe-0 : schedule_timeout (process_timeout)
0.2% ( 0.6) <kernel core> : neigh_table_init_no_netlink
(neigh_periodic_timer)
0.2% ( 0.5) events/0 : sk_reset_timer (tcp_write_timer)
0.1% ( 0.2) update-notifier : schedule_timeout (process_timeout)
0.1% ( 0.2) <kernel module> : neigh_table_init_no_netlink
(neigh_periodic_timer)
0.0% ( 0.1) gnome-power-man : schedule_timeout (process_timeout)
0.0% ( 0.1) ssh-agent : schedule_timeout (process_timeout)
0.0% ( 0.1) ssh-agent : do_setitimer (it_real_fn)
0.0% ( 0.1) miniserv.pl : schedule_timeout (process_timeout)
0.0% ( 0.1) sshd : sk_reset_timer (tcp_write_timer)
0.0% ( 0.1) gconfd-2 : schedule_timeout (process_timeout)
0.0% ( 0.1) <kernel core> : __neigh_event_send
(neigh_timer_handler)
0.0% ( 0.1) xfdesktop : schedule_timeout (process_timeout)
0.0% ( 0.1) xfce4-menu-plug : schedule_timeout (process_timeout)
0.0% ( 0.1) gnome-volume-ma : schedule_timeout (process_timeout)
0.0% ( 0.1) <kernel core> : page_writeback_init (wb_timer_fn)
0.0% ( 0.1) <kernel core> : neigh_update (neigh_timer_handler)
This suggests that it might be mythfrontend that's polling the optical
drive (I did tell it to do that), independently of hal because I stopped
that. So I killed the frontend and, sure enough, the ide0 wakeup rate
drops to 22/s. That still looks high for an idle interface.
Note that the device is part of a Via VT8237R south bridge (served by
the via82cxxx module).
00:0f.1 IDE interface: VIA Technologies, Inc.
VT82C586A/B/VT82C686/A/B/VT823x/A/C PIPC Bus Master IDE (rev 06)
(prog-if 8a [Master SecP PriP])
Subsystem: VIA Technologies, Inc. Unknown device aa08
Flags: bus master, medium devsel, latency 240, IRQ 18
[virtual] Memory at 000001f0 (32-bit, non-prefetchable) [size=8]
[virtual] Memory at 000003f0 (type 3, non-prefetchable) [size=1]
[virtual] Memory at 00000170 (32-bit, non-prefetchable) [size=8]
[virtual] Memory at 00000370 (type 3, non-prefetchable) [size=1]
I/O ports at dc00 [size=16]
Capabilities: [c0] Power Management version 2
Anyway, I've now got an explanation for most of the problem. Thanks for
nudging me in the right direction.
Cheers, Jan
_______________________________________________
Power mailing list
[email protected]
http://www.bughost.org/mailman/listinfo/power
