On Fri, Dec 4, 2009 at 3:38 PM,  <brabuhr / gmail.com> wrote:
>>> =A020.5% (133.5) =A0 =A0 =A0 =A0 =A0 firefox : hrtimer_start_range_ns (=
hrtimer_wakeup)
>>> =A015.3% ( 99.5) =A0 =A0 =A0 =A0 =A0 =A0subtle : hrtimer_start_range_ns=
 (hrtimer_wakeup)
>>> =A015.3% ( 99.5) =A0 =A0 =A0 =A0 =A0 =A0 =A0 irb : hrtimer_start_range_=
ns (hrtimer_wakeup)
>>>
>>> It's hard to believe that firefox with 13 tabs causes only 34 wakeups m=
ore than my irb session which basically waits for input.
>>
>> What platform?
>
> Linux eXist 2.6.31-14-generic #48-Ubuntu SMP Fri Oct 16 14:04:26 UTC
> 2009 i686 GNU/Linux
> model name =A0 =A0 =A0: Intel(R) Pentium(R) M processor 1.60GHz
> ruby 1.8.7 (2009-06-12 patchlevel 174) [i486-linux]
>
> Top causes for wakeups:
> =A049.2% (127.7) =A0 =A0 =A0 =A0 =A0 firefox : hrtimer_start_range_ns (hr=
timer_wakeup)
> =A016.4% ( 42.6) =A0 =A0 =A0 =A0 =A0 =A0 =A0java : hrtimer_start_range_ns=
 (hrtimer_wakeup)
> =A012.3% ( 31.9) =A0 =A0 <kernel core> : hrtimer_start_range_ns (tick_sch=
ed_timer)
> =A0 6.2% ( 16.1) =A0 =A0 =A0 <interrupt> : ata_piix
> =A0 3.8% ( 10.0) =A0 =A0 <kernel core> : timer_action (ehci_watchdog)
>
> An idle irb seesion is barely even ever in the top 30 on this machine.

Which version of readline and readline development dependencies?

Readline is a known issue of CPU eating, at least on Windows

For RubyInstaller we replaced it with a pure-ruby version and CPU
usage went down.

--=20
Luis Lavena
AREA 17
-
Perfection in design is achieved not when there is nothing more to add,
but rather when there is nothing more to take away.
Antoine de Saint-Exup=E9ry