[Pkg-xfce-devel] Bug#637631: Bug#637631: Severe RAID0 performance drop after starting xfce4-power-manager

[Björn A. Herwig]

> That looks like a behavior from laptop-mode or upower hooks. Can you
> check if they're installed, and if there's log from them when xfpm
> starts? Itmight be worth running xfpm from command line with debug
> options.
>
> Regards,
> Yves-Alexis

Hello Yves-Alexis,

$ LANG=C dpkg -l *laptop* *upower* *udisks* pm-utils
Desired=Unknown/Install/Remove/Purge/Hold
| Status=Not/Inst/Conf-files/Unpacked/halF-conf/Half-inst/trig-aWait/Trig-pend
|/ Err?=(none)/Reinst-required (Status,Err: uppercase=bad)
||/ Name           Version        Description
+++-==============-==============-============================================
ii  laptop-detect  0.13.7         attempt to detect a laptop
un  laptop-mode-to <none>         (no description available)
ii  libupower-glib 0.9.12-1+b1    abstraction for power management - shared li
ii  pm-utils       1.4.1-8        utilities and scripts for power management
ii  udisks         1.0.3-1        storage media interface
ii  upower         0.9.12-1+b1    abstraction for power management

Thanks for the hint. In fact, running both upower --monitor-detail and 
udisks --monitor-detail while starting 
xfce4-power-manager --debug --no-daemon did not reveal anything.

greping through /var/log/pm-powersave.log, I found some references 
to /dev/md0, so I monitored the file during xfce4-power-manager startup.

$ sudo tail -f /var/log/pm-powersave.log
Running hook /usr/lib/pm-utils/power.d/disable_wol false:

/usr/lib/pm-utils/power.d/disable_wol false: success.
Running hook /usr/lib/pm-utils/power.d/hal-cd-polling false:

/usr/lib/pm-utils/power.d/hal-cd-polling false: success.
Running hook /usr/lib/pm-utils/power.d/intel-audio-powersave false:
Setting power savings for snd_ac97_codec to 0...Done.

/usr/lib/pm-utils/power.d/intel-audio-powersave false: success.
Running hook /usr/lib/pm-utils/power.d/journal-commit false:
Setting journal commit time for / to 0...Done.

/usr/lib/pm-utils/power.d/journal-commit false: success.
Running hook /usr/lib/pm-utils/power.d/laptop-mode false:
Laptop mode disabled.

/usr/lib/pm-utils/power.d/laptop-mode false: success.
Running hook /usr/lib/pm-utils/power.d/pcie_aspm false:

/usr/lib/pm-utils/power.d/pcie_aspm false: success.
Running hook /usr/lib/pm-utils/power.d/readahead false:
Setting readahead for /dev/sda1 to 256...Done.
Setting readahead for /dev/md0 to 256...Done.

/usr/lib/pm-utils/power.d/readahead false: success.
Running hook /usr/lib/pm-utils/power.d/sata_alpm false:
Setting SATA APLM on host2 to max_performance...Done.
Setting SATA APLM on host3 to max_performance...Done.
Setting SATA APLM on host4 to max_performance...Done.
Setting SATA APLM on host5 to max_performance...Done.
Setting SATA APLM on host6 to max_performance...Done.
Setting SATA APLM on host7 to max_performance...Done.
Setting SATA APLM on host8 to max_performance...Done.
Setting SATA APLM on host9 to max_performance...Done.

/usr/lib/pm-utils/power.d/sata_alpm false: success.
Running hook /usr/lib/pm-utils/power.d/sched-powersave false:
**sched policy powersave OFF

/usr/lib/pm-utils/power.d/sched-powersave false: success.
Running hook /usr/lib/pm-utils/power.d/wireless false:

/usr/lib/pm-utils/power.d/wireless false: success.
Running hook /usr/lib/pm-utils/power.d/xfs_buffer false:

/usr/lib/pm-utils/power.d/xfs_buffer false: success.

One of that scripts might do counter-productive things for a RAID0. Is it 
sata_alpm or d/xfs_buffer? I'll try to investigate further...

So far,
Björn!