I tried the rc6-power3 kernel and these are the powertop numbers
Wakeups-from-idle per second : 258.3 interval: 15.0s
no ACPI power usage estimate available
Top causes for wakeups:
35.2% ( 70.1) [kernel scheduler] Load balancing tick
20.7% ( 41.1) [extra timer interrupt]
6.5% ( 12.9) [iwlagn] <interrupt>
6.0% ( 11.9) firefox-bin
5.5% ( 11.0) nautilus
5.0% ( 9.9) syndaemon
4.1% ( 8.1) [kernel core] usb_hcd_poll_rh_status (rh_timer_func)
2.4% ( 4.9) [kernel core] hrtimer_start (tick_sched_timer)
2.2% ( 4.3) [TLB shootdowns] <kernel IPI>
So the results are worse than with the rc5-power2 kernel but better than the original rc5 Brian Rogers kernel in that there are no wakeups from
[kernel core] hrtimer_start (tick_sched_timer)
which amounts to about 40 wakeups.
These changes are clearly influencing this problem but I feel like we need an expert (kernel dev) to interpret what is going on with the benchmarks from various code changes.....
I tried the rc6-power3 kernel and these are the powertop numbers
Wakeups-from-idle per second : 258.3 interval: 15.0s poll_rh_ status (rh_timer_func)
no ACPI power usage estimate available
Top causes for wakeups:
35.2% ( 70.1) [kernel scheduler] Load balancing tick
20.7% ( 41.1) [extra timer interrupt]
6.5% ( 12.9) [iwlagn] <interrupt>
6.0% ( 11.9) firefox-bin
5.5% ( 11.0) nautilus
5.0% ( 9.9) syndaemon
4.1% ( 8.1) [kernel core] usb_hcd_
2.4% ( 4.9) [kernel core] hrtimer_start (tick_sched_timer)
2.2% ( 4.3) [TLB shootdowns] <kernel IPI>
So the results are worse than with the rc5-power2 kernel but better than the original rc5 Brian Rogers kernel in that there are no wakeups from
[kernel core] hrtimer_start (tick_sched_timer)
which amounts to about 40 wakeups.
These changes are clearly influencing this problem but I feel like we need an expert (kernel dev) to interpret what is going on with the benchmarks from various code changes.....