Dnia 26-03-2008 o 07:57:17 Andreas Mohr <[EMAIL PROTECTED]> napisał(a):
<cut>
> What _I_ would do in this case (and you may choose to do the same)
> would be
>
> linux-2.6.25-rc6.tar.bz2 (or newer)
<cut>
Thanks for suggestions. I've compiled newest 2.6.25-rc7 but results are
very poor. Amount of wakeups is still the same, wifi is somehow broken
(can't connect to wpa-psk network), sound doesn't work (don't have time to
play with it, alsa needs to be recompiled and maybe patched?).
Powertop dump - totally idle watching my desktop (2.6.25-rc7 vanilla):
PowerTOP 1.9 (C) 2007 Intel Corporation
Collecting data for 15 seconds
Cn Avg residency
C0 (cpu running) (40,9%)
C1 0,0ms ( 0,0%)
C2 0,0ms ( 0,0%)
C3 0,0ms (59,1%)
P-states (frequencies)
2,41 Ghz 1,1%
2,40 Ghz 0,0%
2,00 Ghz 0,0%
800 Mhz 98,9%
Wakeups-from-idle per second : 15491,9 interval: 15,0s
no ACPI power usage estimate available
Top causes for wakeups:
36,8% ( 38,9) <interrupt> : acpi
18,0% ( 19,0) <kernel IPI> : Rescheduling interrupts
15,4% ( 16,3) <interrupt> : iwl4965
13,9% ( 14,7) <interrupt> : extra timer interrupt
4,9% ( 5,2) nm-applet : schedule_timeout (process_timeout)
3,8% ( 4,0) <kernel module> : usb_hcd_poll_rh_status (rh_timer_func)
0,8% ( 0,9) tor : schedule_timeout (process_timeout)
0,8% ( 0,8) gnome-terminal : schedule_timeout (process_timeout)
0,6% ( 0,7) wpa_supplicant : schedule_timeout (process_timeout)
0,6% ( 0,6) <kernel IPI> : TLB shootdowns
0,5% ( 0,5) <interrupt> : eth0
0,5% ( 0,5) tor : sk_reset_timer (tcp_write_timer)
0,4% ( 0,5) cpufreq-applet : schedule_timeout (process_timeout)
0,4% ( 0,5) dhcdbd : schedule_timeout (process_timeout)
0,4% ( 0,4) NetworkManager : schedule_timeout (process_timeout)
0,3% ( 0,3) pulseaudio : schedule_timeout (process_timeout)
0,3% ( 0,3) gnome-panel : schedule_timeout (process_timeout)
0,3% ( 0,3) iwl4965 : ieee80211_sta_work
(ieee80211_sta_timer)
0,3% ( 0,3) NetworkManager : e1000_intr_msi (e1000_watchdog)
0,3% ( 0,3) <kernel module> : neigh_table_init_no_netlink
(neigh_periodic_timer)
0,2% ( 0,2) gnome-power-man : schedule_timeout (process_timeout)
0,2% ( 0,2) <kernel core> : neigh_table_init_no_netlink
(neigh_periodic_timer)
0,1% ( 0,1) update-notifier : schedule_timeout (process_timeout)
0,1% ( 0,1) hald : schedule_timeout (process_timeout)
0,1% ( 0,1) sensors-applet : schedule_timeout (process_timeout)
0,1% ( 0,1) <interrupt> : PS/2 keyboard/mouse/touchpad
0,1% ( 0,1) <kernel core> : neigh_add_timer (neigh_timer_handler)
0,1% ( 0,1) <kernel core> : inet_twsk_schedule (inet_twdr_hangman)
Rescheduling dropped a little bit but strage wakeups still exists. It
seems to be a module/kernel issue..
According to the suggestions to use "top" - it was on - showing only Xorg
using 5% of CPU.
Recently i've made a little test. Killed _all_ killable applications and
run powertop from console. There was still about 30k wakeups per second..
Please look at the results (test was made on 2.6.24-12-generic):
-+- Powertop
-+------------------------------------------------------------------------
PowerTOP 1.9 (C) 2007 Intel Corporation
Collecting data for 15 seconds
Cn Avg residency
C0 (cpu running) (48,3%)
C1 0,0ms ( 0,0%)
C2 0,0ms (51,6%)
C3 0,0ms ( 0,1%)
P-states (frequencies)
2,41 Ghz 0,0%
2,40 Ghz 0,0%
2,00 Ghz 0,0%
800 Mhz 100,0%
Wakeups-from-idle per second : 36702,1 interval: 15,0s
Power usage (ACPI estimate): 24,6W (1,4 hours)
Top causes for wakeups:
61,0% ( 4,1) <kernel module> : usb_hcd_poll_rh_status (rh_timer_func)
12,0% ( 0,8) <interrupt> : ahci
8,0% ( 0,5) <kernel module> : neigh_table_init_no_netlink
(neigh_periodic_timer)
5,0% ( 0,3) <kernel IPI> : Rescheduling interrupts
5,0% ( 0,3) <kernel core> : neigh_table_init_no_netlink
(neigh_periodic_timer)
4,0% ( 0,3) kcryptd : blk_plug_device (blk_unplug_timeout)
2,0% ( 0,1) sm-notify : do_journal_end (delayed_work_timer_fn)
1,0% ( 0,1) <interrupt> : PS/2 keyboard/mouse/touchpad
1,0% ( 0,1) <kernel core> : page_writeback_init (wb_timer_fn)
1,0% ( 0,1) <kernel core> : end_that_request_last (laptop_timer_fn)
-+- Loaded modules
-+------------------------------------------------------------------
Module Size Used by
nls_iso8859_1 4992 0
nls_cp437 6656 0
vfat 14464 0
fat 54556 1 vfat
usb_storage 73664 0
libusual 19108 1 usb_storage
af_packet 23812 0
binfmt_misc 12808 1
rfcomm 41744 0
l2cap 25728 3 rfcomm
bluetooth 61156 2 rfcomm,l2cap
vboxdrv 61104 0
kvm_intel 36032 0
kvm 115252 1 kvm_intel
ppdev 10372 0
parport_pc 36260 0
lp 12324 0
parport 37832 3 ppdev,parport_pc,lp
ipv6 267780 10
container 5632 0
sbs 15112 0
bay 6912 0
sbshc 7680 1 sbs
dock 11280 1 bay
acpi_cpufreq 10796 2
cpufreq_powersave 2688 0
cpufreq_stats 7104 0
cpufreq_userspace 5284 0
cpufreq_ondemand 9740 1
cpufreq_conservative 8712 0
freq_table 5536 3 acpi_cpufreq,cpufreq_stats,cpufreq_ondemand
iptable_filter 3840 0
ip_tables 14820 1 iptable_filter
x_tables 16132 1 ip_tables
ext3 136712 1
jbd 48404 1 ext3
mbcache 9600 1 ext3
thinkpad_ec 8464 0
uinput 10240 0
loop 18948 0
arc4 2944 0
ecb 4480 0
snd_hda_intel 344088 0
snd_pcm_oss 42144 0
snd_mixer_oss 17920 1 snd_pcm_oss
snd_pcm 78596 2 snd_hda_intel,snd_pcm_oss
snd_page_alloc 11400 2 snd_hda_intel,snd_pcm
snd_hwdep 10500 1 snd_hda_intel
joydev 13120 0
pcmcia 40876 0
snd_seq_dummy 4868 0
snd_seq_oss 35584 0
snd_seq_midi 9376 0
usbserial 35816 0
snd_rawmidi 25760 1 snd_seq_midi
battery 14212 0
iwlwifi_mac80211 219108 0
snd_seq_midi_event 8320 2 snd_seq_oss,snd_seq_midi
ac 6916 0
nvidia 7825536 0
snd_seq 54224 6
snd_seq_dummy,snd_seq_oss,snd_seq_midi,snd_seq_midi_event
cfg80211 15112 1 iwlwifi_mac80211
agpgart 34760 1 nvidia
i2c_core 24832 1 nvidia
snd_timer 24836 2 snd_pcm,snd_seq
snd_seq_device 9612 5
snd_seq_dummy,snd_seq_oss,snd_seq_midi,snd_rawmidi,snd_seq
wmi_acer 9644 0
video 20112 0
output 4736 1 video
snd 56996 11
snd_hda_intel,snd_pcm_oss,snd_mixer_oss,snd_pcm,snd_hwdep,snd_seq_dummy,snd_seq_oss,snd_rawmidi,snd_seq,snd_timer,snd_seq_device
psmouse 40336 0
serio_raw 7940 0
button 9232 0
yenta_socket 27276 1
rsrc_nonstatic 13696 1 yenta_socket
pcmcia_core 40596 3 pcmcia,yenta_socket,rsrc_nonstatic
nvram 9992 0
iTCO_wdt 13092 0
iTCO_vendor_support 4868 1 iTCO_wdt
soundcore 8800 1 snd
shpchp 34452 0
pci_hotplug 30880 1 shpchp
evdev 13056 0
pcspkr 4224 0
reiserfs 239616 1
sha256_generic 12160 0
aes_i586 33536 2
cbc 5504 1
blkcipher 8324 2 ecb,cbc
sr_mod 17956 0
cdrom 37408 1 sr_mod
sg 36880 0
ata_piix 19588 0
ata_generic 8324 0
sd_mod 30720 3
ahci 28420 2
ohci1394 33584 0
ieee1394 93752 1 ohci1394
pata_acpi 8320 0
libata 159344 4 ata_piix,ata_generic,ahci,pata_acpi
scsi_mod 151436 5 usb_storage,sr_mod,sg,sd_mod,libata
uhci_hcd 27024 0
ehci_hcd 37516 0
usbcore 146028 6
usb_storage,libusual,usbserial,uhci_hcd,ehci_hcd
e1000 125760 0
dm_crypt 15364 1
dm_mirror 24832 0
dm_snapshot 19620 0
dm_mod 62660 10 dm_crypt,dm_mirror,dm_snapshot
thermal 16796 0
processor 36872 4 acpi_cpufreq,thermal
fan 5636 0
fbcon 42912 0
tileblit 3456 1 fbcon
font 9472 1 fbcon
bitblit 6784 1 fbcon
softcursor 3072 1 bitblit
fuse 50580 1
-+- Ps axuw
-+-------------------------------------------------------------------------------
USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND
root 1 0.0 0.0 2976 1860 ? Ss 21:02 0:01 /sbin/init
root 2 0.0 0.0 0 0 ? S< 21:02 0:00 [kthreadd]
root 3 0.0 0.0 0 0 ? S< 21:02 0:00
[migration/0]
root 4 0.0 0.0 0 0 ? S< 21:02 0:00
[ksoftirqd/0]
root 5 0.0 0.0 0 0 ? S< 21:02 0:00
[watchdog/0]
root 6 0.0 0.0 0 0 ? S< 21:02 0:00
[migration/1]
root 7 0.0 0.0 0 0 ? S< 21:02 0:00
[ksoftirqd/1]
root 8 0.0 0.0 0 0 ? S< 21:02 0:00
[watchdog/1]
root 9 0.0 0.0 0 0 ? S< 21:02 0:00 [events/0]
root 10 0.0 0.0 0 0 ? S< 21:02 0:00 [events/1]
root 11 0.0 0.0 0 0 ? S< 21:02 0:00 [khelper]
root 48 0.0 0.0 0 0 ? S< 21:02 0:00
[kblockd/0]
root 49 0.0 0.0 0 0 ? S< 21:02 0:00
[kblockd/1]
root 52 0.0 0.0 0 0 ? S< 21:02 0:00 [kacpid]
root 53 0.0 0.0 0 0 ? S< 21:02 0:00
[kacpi_notify]
root 149 0.0 0.0 0 0 ? S< 21:02 0:00 [kseriod]
root 191 0.0 0.0 0 0 ? S 21:02 0:00 [pdflush]
root 192 0.0 0.0 0 0 ? S 21:02 0:00 [pdflush]
root 193 0.0 0.0 0 0 ? S< 21:02 0:00 [kswapd0]
root 234 0.0 0.0 0 0 ? S< 21:02 0:00 [aio/0]
root 235 0.0 0.0 0 0 ? S< 21:02 0:00 [aio/1]
root 1375 0.0 0.0 0 0 ? S< 21:02 0:00 [ksnapd]
root 1690 0.0 0.0 0 0 ? S< 21:02 0:00
[ksuspend_usbd]
root 1692 0.0 0.0 0 0 ? S< 21:02 0:00 [khubd]
root 1754 0.0 0.0 0 0 ? S< 21:02 0:00 [ata/0]
root 1756 0.0 0.0 0 0 ? S< 21:02 0:00 [ata/1]
root 1757 0.0 0.0 0 0 ? S< 21:02 0:00 [ata_aux]
root 1766 0.0 0.0 0 0 ? S< 21:02 0:00 [khpsbpkt]
root 2609 0.0 0.0 0 0 ? S< 21:02 0:00
[scsi_eh_0]
root 2610 0.0 0.0 0 0 ? S< 21:02 0:00
[scsi_eh_1]
root 2611 0.0 0.0 0 0 ? S< 21:02 0:00
[scsi_eh_2]
root 2692 0.0 0.0 0 0 ? S< 21:02 0:00
[knodemgrd_0]
root 2705 0.0 0.0 0 0 ? S< 21:02 0:00
[scsi_eh_3]
root 2706 0.0 0.0 0 0 ? S< 21:02 0:00
[scsi_eh_4]
root 3249 0.0 0.0 0 0 ? S< 21:02 0:00
[kcryptd_io]
root 3252 0.2 0.0 0 0 ? S< 21:02 0:17 [kcryptd]
root 3375 0.0 0.0 0 0 ? S< 21:02 0:00
[reiserfs/0]
root 3376 0.0 0.0 0 0 ? S< 21:02 0:00
[reiserfs/1]
root 4559 0.0 0.0 0 0 ? S< 21:03 0:00 [pccardd]
root 4579 0.0 0.0 0 0 ? S< 21:03 0:00
[kpsmoused]
root 7156 0.0 0.0 0 0 ? S< 21:03 0:00
[kjournald]
root 7770 0.0 0.0 1716 512 tty4 Ss+ 21:03 0:00
/sbin/getty 38400 tty4
root 7771 0.0 0.0 1716 504 tty5 Ss+ 21:03 0:00
/sbin/getty 38400 tty5
root 7773 0.0 0.0 1716 504 tty2 Ss+ 21:03 0:00
/sbin/getty 38400 tty2
root 7776 0.0 0.0 1716 512 tty3 Ss+ 21:03 0:00
/sbin/getty 38400 tty3
root 7777 0.0 0.0 19264 1516 tty1 Ss 21:03 0:00
/bin/login --
root 7778 0.0 0.0 1716 508 tty6 Ss+ 21:03 0:00
/sbin/getty 38400 tty6
root 7852 0.0 0.0 0 0 ? S< 21:03 0:00
[kondemand/0]
root 7853 0.0 0.0 0 0 ? S< 21:03 0:00
[kondemand/1]
root 9167 0.0 0.0 0 0 ? S< 21:03 0:00
[btaddconn]
root 9168 0.0 0.0 0 0 ? S< 21:03 0:00
[btdelconn]
root 9225 0.0 0.0 0 0 ? S< 21:03 0:00 [krfcommd]
root 19488 0.0 0.0 4200 1840 tty1 S 22:59 0:00 -bash
root 20074 0.0 0.0 2644 988 tty1 R+ 23:06 0:00 ps axuw
-+--+-------------------------------------------------------------------------------
> Distro change? Laughable ;)
Just a joke ;-)
But somehow ubuntu gets more and more complicated with milions of daemons
working without any couse. There are some lighter distros like arch (for
example) where I decide what to run, not distor makers...
Regards,
Barteq
_______________________________________________
Power mailing list
[email protected]
http://www.bughost.org/mailman/listinfo/power
