| View previous topic :: View next topic |
| Author |
Message |
jeffk
l33t
Joined: 13 Sep 2003
Posts: 671
|
 Posted: Sun Sep 30, 2007 4:18 pm Post subject: HD spinup:echo 1500 > /proc/sys/vm/dirty_writeback_centis |
 |
|
Originally Titled: "HD access every 5 sec in GNOME-2.20, how to disable?"
I have a newly installed ~x86 on a Thinkpad T61p with an SATA hard drive. Under GNOME-2.20, the hard drive accesses every 5 seconds even at idle. This is something I'd like to control and suppress. I don't need or want beagle or other indexing, file alteration monitoring, etc to run when at idle. I'd rather do those things manually, or ideally switch into a 'work mode' where such services are enabled temporarily. I don't think the periodic hard drive access happens when out of X/GNOME, but perhaps it is so fast that the drive light never indicates.
What can I examine to find the offending daemon or library? All options on menu System | Administration | Search and Indexing are unchecked. I'll excerpt some notes of my configuration below:
| Code: | # grep -e 'ACPI\|POWER\|FREQ\|ATA|NO_HZ' kernel-config-x86-2.6.22-gentoo-r8
# Power management options (ACPI, APM)
# ACPI (Advanced Configuration and Power Interface) Support
CONFIG_ACPI=y
CONFIG_ACPI_PROCFS=y
CONFIG_ACPI_AC=m
CONFIG_ACPI_BATTERY=m
CONFIG_ACPI_BUTTON=m
CONFIG_ACPI_VIDEO=m
CONFIG_ACPI_FAN=m
# CONFIG_ACPI_DOCK is not set
CONFIG_ACPI_PROCESSOR=m
CONFIG_ACPI_THERMAL=m
# CONFIG_ACPI_ASUS is not set
# CONFIG_ACPI_TOSHIBA is not set
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
CONFIG_ACPI_EC=y
CONFIG_ACPI_POWER=y
CONFIG_ACPI_SYSTEM=y
# CONFIG_ACPI_CONTAINER is not set
# CONFIG_ACPI_SBS is not set
# CONFIG_APM_REAL_MODE_POWER_OFF is not set
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_TABLE=m
# CONFIG_CPU_FREQ_DEBUG is not set
CONFIG_CPU_FREQ_STAT=m
# CONFIG_CPU_FREQ_STAT_DETAILS is not set
CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
# CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE is not set
CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
CONFIG_CPU_FREQ_GOV_POWERSAVE=m
CONFIG_CPU_FREQ_GOV_USERSPACE=m
CONFIG_CPU_FREQ_GOV_ONDEMAND=m
CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m
CONFIG_X86_ACPI_CPUFREQ=m
# CONFIG_X86_POWERNOW_K6 is not set
# CONFIG_X86_POWERNOW_K7 is not set
# CONFIG_X86_POWERNOW_K8 is not set
CONFIG_X86_SPEEDSTEP_CENTRINO_ACPI=y
# CONFIG_X86_CPUFREQ_NFORCE2 is not set
# CONFIG_X86_E_POWERSAVER is not set
# CONFIG_X86_ACPI_CPUFREQ_PROC_INTF is not set
CONFIG_PNPACPI=y
CONFIG_THINKPAD_ACPI=m
# CONFIG_THINKPAD_ACPI_DEBUG is not set
# CONFIG_THINKPAD_ACPI_DOCK is not set
CONFIG_THINKPAD_ACPI_BAY=y
# CONFIG_BLK_DEV_IDEACPI is not set
CONFIG_ATA_ACPI=y
# CONFIG_USB_HIDINPUT_POWERBOOK is not set |
| Code: |
# lsmod
Module Size Used by
nvidiafb 44572 0
fb_ddc 2880 1 nvidiafb
i2c_algo_bit 6212 1 nvidiafb
vgastate 8000 1 nvidiafb
nvidia 6215144 26
sg 29340 0
intel_agp 23252 0
i2c_i801 8464 0
i2c_core 24320 5 nvidiafb,fb_ddc,i2c_algo_bit,nvidia,i2c_i801
agpgart 32388 2 nvidia,intel_agp
snd_hda_intel 237208 1
snd_pcm 72452 1 snd_hda_intel
snd_timer 21764 1 snd_pcm
snd 49300 5 snd_hda_intel,snd_pcm,snd_timer
soundcore 8324 1 snd
snd_page_alloc 10376 2 snd_hda_intel,snd_pcm
e1000 112128 0
scsi_wait_scan 1664 0
sbp2 22152 0
firewire_core 39112 0
crc_itu_t 2432 1 firewire_core
ohci1394 32496 0
ieee1394 86780 2 sbp2,ohci1394
sl811_hcd 12160 0
usbhid 26068 0
ohci_hcd 19972 0
uhci_hcd 23180 0
usb_storage 37316 0
ehci_hcd 28940 0
usbcore 118956 7 sl811_hcd,usbhid,ohci_hcd,uhci_hcd,usb_storage,ehci_hcd |
| Code: | # lspci
00:00.0 Host bridge: Intel Corporation Mobile Memory Controller Hub (rev 0c)
00:01.0 PCI bridge: Intel Corporation Mobile PCI Express Root Port (rev 0c)
00:19.0 Ethernet controller: Intel Corporation 82566MM Gigabit Network Connection (rev 03)
00:1a.0 USB Controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Contoller #4 (rev 03)
00:1a.1 USB Controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #5 (rev 03)
00:1a.7 USB Controller: Intel Corporation 82801H (ICH8 Family) USB2 EHCI Controller #2 (rev 03)
00:1b.0 Audio device: Intel Corporation 82801H (ICH8 Family) HD Audio Controller (rev 03)
00:1c.0 PCI bridge: Intel Corporation 82801H (ICH8 Family) PCI Express Port 1 (rev 03)
00:1c.1 PCI bridge: Intel Corporation 82801H (ICH8 Family) PCI Express Port 2 (rev 03)
00:1c.2 PCI bridge: Intel Corporation 82801H (ICH8 Family) PCI Express Port 3 (rev 03)
00:1c.3 PCI bridge: Intel Corporation 82801H (ICH8 Family) PCI Express Port 4 (rev 03)
00:1c.4 PCI bridge: Intel Corporation 82801H (ICH8 Family) PCI Express Port 5 (rev 03)
00:1d.0 USB Controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #1 (rev 03)
00:1d.1 USB Controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #2 (rev 03)
00:1d.2 USB Controller: Intel Corporation 82801H (ICH8 Family) USB UHCI Controller #3 (rev 03)
00:1d.7 USB Controller: Intel Corporation 82801H (ICH8 Family) USB2 EHCI Controller #1 (rev 03)
00:1e.0 PCI bridge: Intel Corporation 82801 Mobile PCI Bridge (rev f3)
00:1f.0 ISA bridge: Intel Corporation Mobile LPC Interface Controller (rev 03)
00:1f.1 IDE interface: Intel Corporation Mobile IDE Controller (rev 03)
00:1f.2 SATA controller: Intel Corporation Mobile SATA AHCI Controller (rev 03)
00:1f.3 SMBus: Intel Corporation 82801H (ICH8 Family) SMBus Controller (rev 03)
01:00.0 VGA compatible controller: nVidia Corporation Unknown device 040c (rev a1)
03:00.0 Network controller: Intel Corporation Unknown device 4230 (rev 61)
15:00.0 CardBus bridge: Ricoh Co Ltd RL5c476 II (rev ba)
15:00.1 FireWire (IEEE 1394): Ricoh Co Ltd R5C832 IEEE 1394 Controller (rev 04)
15:00.2 Generic system peripheral [0805]: Ricoh Co Ltd R5C822 SD/SDIO/MMC/MS/MSPro Host Adapter (rev 21)
15:00.3 System peripheral: Ricoh Co Ltd Unknown device 0843 (rev 11)
15:00.4 System peripheral: Ricoh Co Ltd R5C592 Memory Stick Bus Host Adapter (rev 11)
15:00.5 System peripheral: Ricoh Co Ltd xD-Picture Card Controller (rev 11)
|
| Code: | # rc-update show
bootmisc | boot
checkfs | boot
checkroot | boot
clock | boot
consolefont | boot
hald | default
hostname | boot
keymaps | boot
local | default nonetwork
localmount | boot
modules | boot
net.eth0 | default
net.lo | boot
netmount | default
postgresql | default
rmnologin | boot
sshd | default
syslog-ng | default
urandom | boot
vixie-cron | default |
| Code: | $ cat /etc/fstab
# <fs> <mountpoint> <type> <opts> <dump/pass>
/dev/sda3 / ext3 noatime 0 1
/dev/sda1 /boot ext2 noauto,noatime 1 2
/dev/sda2 none swap sw 0 0
/dev/cdrom /mnt/cdrom auto noauto,ro 0 0
shm /dev/shm tmpfs nodev,nosuid,noexec 0 0 |
| Code: | P-states (frequencies)
< Detailed C-state information is only available on Mobile CPUs (laptops) >
Wakeups-from-idle per second : 91.3 interval: 10.0s
Top causes for wakeups:
50.0% ( 91.3) <interrupt> : ahci, uhci_hcd:usb5, nvidia
11.9% ( 21.7) firefox-bin : futex_wait (hrtimer_wakeup)
9.6% ( 17.5) X : do_setitimer (it_real_fn)
7.6% ( 13.9) mixer_applet2 : schedule_timeout (process_timeout)
6.6% ( 12.0) <kernel module> : usb_hcd_poll_rh_status (rh_timer_func)
4.9% ( 9.0) <interrupt> : ide0
2.3% ( 4.2) irssi : schedule_timeout (process_timeout)
1.6% ( 3.0) <kernel core> : queue_delayed_work_on (delayed_work_timer_fn)
1.1% ( 2.0) <kernel core> : clocksource_register (clocksource_watchdog)
0.6% ( 1.1) <interrupt> : uhci_hcd:usb3, eth0
0.6% ( 1.1) gnome-terminal : schedule_timeout (process_timeout)
0.5% ( 1.0) X : nv_start_rc_timer (nv_kern_rc_timer)
0.3% ( 0.5) ifconfig : e1000_intr (e1000_watchdog)
0.3% ( 0.5) hald-addon-stor : schedule_timeout (process_timeout)
0.3% ( 0.5) firefox-bin : schedule_timeout (process_timeout)
0.2% ( 0.4) kirqd : schedule_timeout (process_timeout)
0.2% ( 0.3) <kernel core> : neigh_table_init_no_netlink (neigh_periodic_timer)
0.2% ( 0.3) nautilus : schedule_timeout (process_timeout)
0.2% ( 0.3) gnome-settings- : schedule_timeout (process_timeout)
0.1% ( 0.2) init : schedule_timeout (process_timeout)
0.1% ( 0.2) <kernel core> : page_writeback_init (wb_timer_fn)
0.1% ( 0.2) mapping-daemon : schedule_timeout (process_timeout)
0.1% ( 0.2) gnome-panel : schedule_timeout (process_timeout)
0.1% ( 0.2) ifconfig : __netdev_watchdog_up (dev_watchdog)
0.1% ( 0.2) gnome-power-man : schedule_timeout (process_timeout)
0.1% ( 0.1) <kernel core> : input_event (input_repeat_key)
0.1% ( 0.1) X : schedule_timeout (process_timeout)
0.1% ( 0.1) gconfd-2 : schedule_timeout (process_timeout)
0.1% ( 0.1) firefox-bin : __make_request (blk_unplug_timeout)
0.1% ( 0.1) <kernel core> : sk_reset_timer (tcp_delack_timer)
0.1% ( 0.1) touch : start_this_handle (commit_timeout)
0.1% ( 0.1) metacity : schedule_timeout (process_timeout)
0.1% ( 0.1) ssh-agent : schedule_timeout (process_timeout)
Suggestion: Disable 'hal' from polling your cdrom with:
hal-disable-polling --device /dev/scd0 'hal' is the component that auto-opens a
window if you plug in a CD but disables SATA power saving from kicking in. |
I can't disable CONFIG_USB_SUSPEND kernel configuration option until a SANE release (upstream or Gentoo-patched) fixes the known problem with it. I use scanners a lot.
Also, I usually have irssi with logging running in screen. If there's a long-latency logging option I should be using with that, I'll investigate it.
Thanks for any tips.
Last edited by jeffk on Thu Oct 04, 2007 4:45 am; edited 1 time in total |
|
| Back to top |
|
 |
nixnut
Bodhisattva
Joined: 09 Apr 2004
Posts: 10974
Location: the dutch mountains
|
| Posted: Sun Sep 30, 2007 4:55 pm Post subject: |
|
|
Probably something gnomish that it can't do without like beagle, hal or dbus. Try installing powertop.
_________________
Please add [solved] to the initial post's subject line if you feel your problem is resolved. Help answer the unanswered
talk is cheap. supply exceeds demand |
|
| Back to top |
|
|
jeffk
l33t
Joined: 13 Sep 2003
Posts: 671
|
| Posted: Sun Sep 30, 2007 5:37 pm Post subject: |
|
|
The initial post was updated with powertop output, perhaps just after the first reply was started.
I also disabled polling on /dev/cdrom, per powertop recommendations:
| Code: | # ls -al /dev/cdrom
lrwxrwxrwx 1 root root 3 Sep 30 11:04 /dev/cdrom -> hda
# hal-disable-polling --device /dev/hda
Polling for drive /dev/hda have been disabled. The fdi file written was
/etc/hal/fdi/information/media-check-disable-storage_serial_HC43_130370.fdi |
Thanks for any additional tips. I think/hope beagle is disabled per the Search and Index preferences (all unchecked). |
|
| Back to top |
|
|
gasparov
Tux's lil' helper
Joined: 13 Apr 2006
Posts: 105
|
| Posted: Tue Oct 02, 2007 10:23 am Post subject: |
|
|
Hi jeffk,
are you sure is an offending service what you are looking for?.My thinkpad and my packard bell laptop have the same issue but is the power management of the harddisk that causes truble
hdparm -B 255 should solve it
Btw if somebody knows how to to this simple thing in windows I would be glad |
|
| Back to top |
|
|
PaulBredbury
Watchman
Joined: 14 Jul 2005
Posts: 7310
|
| Posted: Tue Oct 02, 2007 11:01 am Post subject: Re: HD access every 5 sec in GNOME-2.20, how to disable? |
|
|
| jeffk wrote: | | the hard drive accesses every 5 seconds |
Try thread. |
|
| Back to top |
|
|
jeffk
l33t
Joined: 13 Sep 2003
Posts: 671
|
| Posted: Wed Oct 03, 2007 2:26 am Post subject: |
|
|
Thanks all, I tried both no-fixed-drives.fdi and hdparm -B 255 (254) /dev/sda. It doesn't change the observed behavior. This may be something other than the loud clicking described by the other users.
This is just a normal quiet hard drive access every 5 or so seconds when idle. I can only hear it because the rest of the machine is so quiet. I think this drive is trying to power down and park the heads, but something is making an unwanted disk request, waking the drive.
I do have 4GB of ram in this machine. I wonder about running without any swap partition mounted. Any thoughts?
| Code: | # mount
/dev/sda3 on / type ext3 (rw,noatime)
proc on /proc type proc (rw,nosuid,nodev,noexec)
sysfs on /sys type sysfs (rw,nosuid,nodev,noexec)
udev on /dev type tmpfs (rw,nosuid)
devpts on /dev/pts type devpts (rw,nosuid,noexec)
shm on /dev/shm type tmpfs (rw,noexec,nosuid,nodev)
usbfs on /proc/bus/usb type usbfs (rw,noexec,nosuid,devmode=0664,devgid=85)
/dev/sda1 on /boot type ext2 (rw,noatime) |
| Code: | # cat /etc/fstab
# <fs> <mountpoint> <type> <opts> <dump/pass>
/dev/sda3 / ext3 noatime 0 1
/dev/sda1 /boot ext2 noauto,noatime 1 2
/dev/sda2 none swap sw 0 0
/dev/cdrom /mnt/cdrom auto noauto,ro 0 0
shm /dev/shm tmpfs nodev,nosuid,noexec 0 0 |
P.S. I just entered the contents of no-fixed-drives.fdi into the file, no special EOF tricks. This should be the same thing, right? |
|
| Back to top |
|
|
jeffk
l33t
Joined: 13 Sep 2003
Posts: 671
|
| Posted: Wed Oct 03, 2007 3:54 am Post subject: |
|
|
OK, I read up on it a bit, and running without swap isn't the answer.
Also, I thought I'd mention that the HD access light does come on during these periodic accesses, so it appears to be a data-driven event, and not an internal drive event like a thermal recalibration.
Also, the accesses happen when I leave X / GNOME, and am back at the console.
Finally, not running irssi, with its logging, does not eliminate the periodic disk accesses.
I need some ubertool that logs disk access events. Without accessing the disk  .
This is becoming an example of the Heisenberg Uncertainty Principle. |
|
| Back to top |
|
|
jeffk
l33t
Joined: 13 Sep 2003
Posts: 671
|
| Posted: Thu Oct 04, 2007 4:52 am Post subject: |
|
|
powertop to the rescue! Recommended:
| Code: | Suggestion: increase the VM dirty writeback time from 4.99 to 15 seconds with:
echo 1500 > /proc/sys/vm/dirty_writeback_centisecs
This wakes the disk up less frequenty for background VM activity |
I did this, and sure enough, the quiet disk access happens about every 15 seconds.
How far can I push this setting for normal latoptop usage on a 4Gb machine?
How do I move this into a permanent setting enabled at boot-time?
Is there a kernel config to optimize it?
| Code: | # grep VM kernel-config-x86-2.6.22-gentoo-r8
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_VM86=y
# Multi-device support (RAID and LVM)
# CONFIG_KVM is not set
# CONFIG_DEBUG_VM is not set |
Also, as an aside, powertop recommended:
| Code: | Suggestion: Disable the CONFIG_IRQBALANCE kernel configuration option.
The in-kernel irq balancer is obsolete and wakes the CPU up far more than needed. |
Which I'm going to fix. Gives me a chance to check out the "/" menuconfig search, which is SO handy, I can't believe I didn't notice it before.
| Code: | # grep IRQ kernel-config-x86-2.6.22-gentoo-r8
CONFIG_IRQBALANCE=y
CONFIG_HT_IRQ=y
CONFIG_IDEPCI_SHARE_IRQ=y
CONFIG_HPET_RTC_IRQ=y
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
# CONFIG_DEBUG_SHIRQ is not set
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_GENERIC_PENDING_IRQ=y |
|
|
| Back to top |
|
|
|
|
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
|
|
Kernel & Hardware
