Re: Clocksource tsc is always unstable with 2.6.25-* kernels and CONFIG_NO_HZ=y on my box
Gabriel C wrote:[color=blue]
> Hi,
>
> I noticed tsc is always marked unstable on my box with 2.6.25* , 2.6.24 is fine.
>
> ..
>
> [ 0.825760] ACPI: PCI Interrupt 0000:03:0e.0[A] -> GSI 22 (level, low) -> IRQ 22
> [ 0.805755] Switched to high resolution mode on CPU 1
> [ 0.794244] Switched to high resolution mode on CPU 2
> [ 0.766968] Switched to high resolution mode on CPU 3
> [ 1.083944] Switched to high resolution mode on CPU 0
> [ 15.388792] Clocksource tsc unstable (delta = 9373391604 ns)
> [ 15.714648] Time: acpi_pm clocksource has been installed.
>
> ..
>
> Booting nohz=off fixes that.
>
> Another strange thing is when I try to boot that kernel with clocksource=acpi_pm it just hangs.
>
> config is attached.
>
> Please let me know if you need more infos / want me to try patches or anything else.[/color]
Please post your full dmesg output.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email]majordomo@vger.kernel.org[/email]
More majordomo info at [url]http://vger.kernel.org/majordomo-info.html[/url]
Please read the FAQ at [url]http://www.tux.org/lkml/[/url]
Re: Clocksource tsc is always unstable with 2.6.25-* kernels and CONFIG_NO_HZ=y on my box
On Sun, 24 Feb 2008, Robert Han**** wrote:[color=blue]
> Gabriel C wrote:[color=green]
> > Hi,
> >
> > I noticed tsc is always marked unstable on my box with 2.6.25* , 2.6.24 is
> > fine.
> >
> > ..
> >
> > [ 0.825760] ACPI: PCI Interrupt 0000:03:0e.0[A] -> GSI 22 (level, low) ->
> > IRQ 22
> > [ 0.805755] Switched to high resolution mode on CPU 1
> > [ 0.794244] Switched to high resolution mode on CPU 2
> > [ 0.766968] Switched to high resolution mode on CPU 3
> > [ 1.083944] Switched to high resolution mode on CPU 0
> > [ 15.388792] Clocksource tsc unstable (delta = 9373391604 ns)[/color][/color]
Doh, this looks like the acpi_pm timer is not working at all.
[color=blue][color=green]
> > [ 15.714648] Time: acpi_pm clocksource has been installed.
> > ..
> >
> > Booting nohz=off fixes that.
> >
> > Another strange thing is when I try to boot that kernel with
> > clocksource=acpi_pm it just hangs.[/color][/color]
Which confirms the above.
[color=blue][color=green]
> > config is attached.
> >
> > Please let me know if you need more infos / want me to try patches or
> > anything else.[/color]
>
> Please post your full dmesg output.[/color]
Yes please.
Thanks,
tglx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email]majordomo@vger.kernel.org[/email]
More majordomo info at [url]http://vger.kernel.org/majordomo-info.html[/url]
Please read the FAQ at [url]http://www.tux.org/lkml/[/url]
Re: Clocksource tsc is always unstable with 2.6.25-* kernels and CONFIG_NO_HZ=y on my box
Thomas Gleixner wrote:[color=blue]
> On Sun, 24 Feb 2008, Robert Han**** wrote:[color=green]
>> Gabriel C wrote:[color=darkred]
>>> Hi,
>>>
>>> I noticed tsc is always marked unstable on my box with 2.6.25* , 2.6.24 is
>>> fine.
>>>
>>> ..
>>>
>>> [ 0.825760] ACPI: PCI Interrupt 0000:03:0e.0[A] -> GSI 22 (level, low) ->
>>> IRQ 22
>>> [ 0.805755] Switched to high resolution mode on CPU 1
>>> [ 0.794244] Switched to high resolution mode on CPU 2
>>> [ 0.766968] Switched to high resolution mode on CPU 3
>>> [ 1.083944] Switched to high resolution mode on CPU 0
>>> [ 15.388792] Clocksource tsc unstable (delta = 9373391604 ns)[/color][/color]
>
> Doh, this looks like the acpi_pm timer is not working at all.
>[color=green][color=darkred]
>>> [ 15.714648] Time: acpi_pm clocksource has been installed.
>>> ..
>>>
>>> Booting nohz=off fixes that.
>>>
>>> Another strange thing is when I try to boot that kernel with
>>> clocksource=acpi_pm it just hangs.[/color][/color]
>
> Which confirms the above.
>[color=green][color=darkred]
>>> config is attached.
>>>
>>> Please let me know if you need more infos / want me to try patches or
>>> anything else.[/color]
>> Please post your full dmesg output.[/color]
>
> Yes please.[/color]
dmesg's from 2.6.25-rc3 witch nohz={on,off} , lspci , dmidecode and the used config for this kernel can be found there :
[url]http://frugalware.org/~crazy/dmesg/lara/[/url]
[color=blue]
>
> Thanks,
> tglx
>[/color]
Regards,
Gabriel
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email]majordomo@vger.kernel.org[/email]
More majordomo info at [url]http://vger.kernel.org/majordomo-info.html[/url]
Please read the FAQ at [url]http://www.tux.org/lkml/[/url]
Re: Clocksource tsc is always unstable with 2.6.25-* kernels and CONFIG_NO_HZ=y on my box
On Mon, 25 Feb 2008, Gabriel C wrote:[color=blue][color=green][color=darkred]
> >>> Booting nohz=off fixes that.
> >>>
> >>> Another strange thing is when I try to boot that kernel with
> >>> clocksource=acpi_pm it just hangs.[/color][/color][/color]
What happens if you add clocksource=acpi_pm and nohz=off to the kernel
commandline ?
[color=blue][color=green][color=darkred]
> >> Please post your full dmesg output.[/color]
> >
> > Yes please.[/color]
>
> dmesg's from 2.6.25-rc3 witch nohz={on,off} , lspci , dmidecode and
> the used config for this kernel can be found there :
>
> [url]http://frugalware.org/~crazy/dmesg/lara/[/url][/color]
Hmm. Nothing really obvious.
Thanks,
tglx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email]majordomo@vger.kernel.org[/email]
More majordomo info at [url]http://vger.kernel.org/majordomo-info.html[/url]
Please read the FAQ at [url]http://www.tux.org/lkml/[/url]
Re: Clocksource tsc is always unstable with 2.6.25-* kernels and CONFIG_NO_HZ=y on my box
Thomas Gleixner wrote:[color=blue]
> On Mon, 25 Feb 2008, Gabriel C wrote:[color=green][color=darkred]
>>>>> Booting nohz=off fixes that.
>>>>>
>>>>> Another strange thing is when I try to boot that kernel with
>>>>> clocksource=acpi_pm it just hangs.[/color][/color]
>
> What happens if you add clocksource=acpi_pm and nohz=off to the kernel
> commandline ?
>[/color]
Then the kernel boots and it seems to work.
[url]http://frugalware.org/~crazy/dmesg/lara/dmesg2[/url]
[color=blue][color=green][color=darkred]
>>>> Please post your full dmesg output.
>>> Yes please.[/color]
>> dmesg's from 2.6.25-rc3 witch nohz={on,off} , lspci , dmidecode and
>> the used config for this kernel can be found there :
>>
>> [url]http://frugalware.org/~crazy/dmesg/lara/[/url][/color]
>
> Hmm. Nothing really obvious.[/color]
If you want I can build an debug kernel and boot with initcall_debug or anything else may help to find the problem,
just let me know.
[color=blue]
>
> Thanks,
> tglx
>[/color]
Gabriel
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email]majordomo@vger.kernel.org[/email]
More majordomo info at [url]http://vger.kernel.org/majordomo-info.html[/url]
Please read the FAQ at [url]http://www.tux.org/lkml/[/url]
Re: Clocksource tsc is always unstable with 2.6.25-* kernels and CONFIG_NO_HZ=y on my box
On Mon, 25 Feb 2008, Gabriel C wrote:[color=blue]
>[color=green]
> > What happens if you add clocksource=acpi_pm and nohz=off to the kernel
> > commandline ?[/color]
>
> Then the kernel boots and it seems to work.
>
> If you want I can build an debug kernel and boot with initcall_debug
> or anything else may help to find the problem, just let me know.[/color]
Sorry, this thread slipped out of my attention.
Is this still true with 2.6.25-rc5 ?
Thanks,
tglx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email]majordomo@vger.kernel.org[/email]
More majordomo info at [url]http://vger.kernel.org/majordomo-info.html[/url]
Please read the FAQ at [url]http://www.tux.org/lkml/[/url]
Re: Clocksource tsc is always unstable with 2.6.25-* kernels and CONFIG_NO_HZ=y on my box
Thomas Gleixner wrote:[color=blue]
> On Mon, 25 Feb 2008, Gabriel C wrote:[color=green][color=darkred]
>>> What happens if you add clocksource=acpi_pm and nohz=off to the kernel
>>> commandline ?[/color]
>> Then the kernel boots and it seems to work.
>>
>> If you want I can build an debug kernel and boot with initcall_debug
>> or anything else may help to find the problem, just let me know.[/color]
>
> Sorry, this thread slipped out of my attention.
>
> Is this still true with 2.6.25-rc5 ?[/color]
Yes it is , I'm running 2.6.25-rc5-00232-g93d7446 and it has the same problem.
[color=blue]
>
> Thanks,
>
> tglx
>
>[/color]
Gabriel
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email]majordomo@vger.kernel.org[/email]
More majordomo info at [url]http://vger.kernel.org/majordomo-info.html[/url]
Please read the FAQ at [url]http://www.tux.org/lkml/[/url]