nmi_watchdog is set to NMI_NONE by default (ie disabled) on _any_
mode so lets fix documentation too.
Signed-off-by: Cyrill Gorcunov <[email protected]>
---
Index: linux-2.6.git/Documentation/nmi_watchdog.txt
====================================================================
--- linux-2.6.git.orig/Documentation/nmi_watchdog.txt 2008-04-15 23:01:26.000000000 +0400
+++ linux-2.6.git/Documentation/nmi_watchdog.txt 2008-06-27 19:39:21.000000000 +0400
@@ -10,7 +10,7 @@ us to generate 'watchdog NMI interrupts'
which get executed even if the system is otherwise locked up hard).
This can be used to debug hard kernel lockups. By executing periodic
NMI interrupts, the kernel can monitor whether any CPU has locked up,
-and print out debugging messages if so.
+and print out debugging messages if so.
In order to use the NMI watchdog, you need to have APIC support in your
kernel. For SMP kernels, APIC support gets compiled in automatically. For
@@ -22,8 +22,7 @@ CONFIG_X86_UP_IOAPIC is for uniprocessor
kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
may implicitly disable the NMI watchdog.]
-For x86-64, the needed APIC is always compiled in, and the NMI watchdog is
-always enabled with I/O-APIC mode (nmi_watchdog=1).
+For x86-64, the needed APIC is always compiled in.
Using local APIC (nmi_watchdog=2) needs the first performance register, so
you can't use it for other purposes (such as high precision performance
@@ -63,16 +62,15 @@ when the system is idle), but if your sy
"hlt", then you are out of luck -- the event will not happen at all and the
watchdog won't trigger. This is a shortcoming of the local APIC watchdog
-- unfortunately there is no "clock ticks" event that would work all the
-time. The I/O APIC watchdog is driven externally and has no such shortcoming.
+time. The I/O APIC watchdog is driven externally and has no such shortcoming.
But its NMI frequency is much higher, resulting in a more significant hit
to the overall system performance.
-NOTE: starting with 2.4.2-ac18 the NMI-oopser is disabled by default,
-you have to enable it with a boot time parameter. Prior to 2.4.2-ac18
-the NMI-oopser is enabled unconditionally on x86 SMP boxes.
+On x86 nmi_watchdog is disabled by default so you have to enable it with
+a boot time parameter.
-On x86-64 the NMI oopser is on by default. On 64bit Intel CPUs
-it uses IO-APIC by default and on AMD it uses local APIC.
+NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
+on x86 SMP boxes.
[ feel free to send bug reports, suggestions and patches to
Ingo Molnar <[email protected]> or the Linux SMP mailing
On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
> +NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
> +on x86 SMP boxes.
While you are at it: s/is/was/.
Maciej
[Maciej W. Rozycki - Fri, Jun 27, 2008 at 04:54:19PM +0100]
| On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
|
| > +NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
| > +on x86 SMP boxes.
|
| While you are at it: s/is/was/.
|
| Maciej
|
Thanks, Maciej, updated.
- Cyrill -
---
From: Cyrill Gorcunov <[email protected]>
Subject: [PATCH -tip/master] x86: nmi_watchdog - documentation fix
nmi_watchdog is set to NMI_NONE by default (ie disabled) on _any_
mode so lets fix documentation too.
Signed-off-by: Cyrill Gorcunov <[email protected]>
CC: Maciej W. Rozycki <[email protected]>
---
Index: linux-2.6.git/Documentation/nmi_watchdog.txt
====================================================================
--- linux-2.6.git.orig/Documentation/nmi_watchdog.txt 2008-06-27 19:50:06.000000000 +0400
+++ linux-2.6.git/Documentation/nmi_watchdog.txt 2008-06-27 19:58:53.000000000 +0400
@@ -10,7 +10,7 @@ us to generate 'watchdog NMI interrupts'
which get executed even if the system is otherwise locked up hard).
This can be used to debug hard kernel lockups. By executing periodic
NMI interrupts, the kernel can monitor whether any CPU has locked up,
-and print out debugging messages if so.
+and print out debugging messages if so.
In order to use the NMI watchdog, you need to have APIC support in your
kernel. For SMP kernels, APIC support gets compiled in automatically. For
@@ -22,8 +22,7 @@ CONFIG_X86_UP_IOAPIC is for uniprocessor
kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
may implicitly disable the NMI watchdog.]
-For x86-64, the needed APIC is always compiled in, and the NMI watchdog is
-always enabled with I/O-APIC mode (nmi_watchdog=1).
+For x86-64, the needed APIC is always compiled in.
Using local APIC (nmi_watchdog=2) needs the first performance register, so
you can't use it for other purposes (such as high precision performance
@@ -63,16 +62,15 @@ when the system is idle), but if your sy
"hlt", then you are out of luck -- the event will not happen at all and the
watchdog won't trigger. This is a shortcoming of the local APIC watchdog
-- unfortunately there is no "clock ticks" event that would work all the
-time. The I/O APIC watchdog is driven externally and has no such shortcoming.
+time. The I/O APIC watchdog is driven externally and has no such shortcoming.
But its NMI frequency is much higher, resulting in a more significant hit
to the overall system performance.
-NOTE: starting with 2.4.2-ac18 the NMI-oopser is disabled by default,
-you have to enable it with a boot time parameter. Prior to 2.4.2-ac18
-the NMI-oopser is enabled unconditionally on x86 SMP boxes.
+On x86 nmi_watchdog is disabled by default so you have to enable it with
+a boot time parameter.
-On x86-64 the NMI oopser is on by default. On 64bit Intel CPUs
-it uses IO-APIC by default and on AMD it uses local APIC.
+NOTE: Prior to 2.4.2-ac18 the NMI-oopser was enabled unconditionally
+on x86 SMP boxes.
[ feel free to send bug reports, suggestions and patches to
Ingo Molnar <[email protected]> or the Linux SMP mailing
On Fri, 27 Jun 2008 16:54:19 +0100 (BST)
"Maciej W. Rozycki" <[email protected]> wrote:
> On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
>
> > +NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
> > +on x86 SMP boxes.
>
> While you are at it: s/is/was/.
Erm - why ??
It is still true today that kernels < 2.4.2-ac8 have the NMI oopser
enabled.
Alan
Alan Cox wrote:
> On Fri, 27 Jun 2008 16:54:19 +0100 (BST)
> "Maciej W. Rozycki" <[email protected]> wrote:
>
>
>>On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
>>
>>
>>>+NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
>>>+on x86 SMP boxes.
>>
>> While you are at it: s/is/was/.
>
>
> Erm - why ??
>
> It is still true today that kernels < 2.4.2-ac8 have the NMI oopser
> enabled.
To my ear the phrase as written implies past tense for the author/reader
(i.e. "at points in time prior to the release of 2.4.2-ac18"), and thus
grates against "is".
The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
NMI-oopser is enabled..." In this context the phrase itself is in the
present, but we point to past kernels.
Chris
[Chris Friesen - Fri, Jun 27, 2008 at 10:32:12AM -0600]
> Alan Cox wrote:
>> On Fri, 27 Jun 2008 16:54:19 +0100 (BST)
>> "Maciej W. Rozycki" <[email protected]> wrote:
>>> On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
>>>
>>>
>>>> +NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
>>>> +on x86 SMP boxes.
>>>
>>> While you are at it: s/is/was/.
>> Erm - why ??
>> It is still true today that kernels < 2.4.2-ac8 have the NMI oopser
>> enabled.
>
> To my ear the phrase as written implies past tense for the author/reader
> (i.e. "at points in time prior to the release of 2.4.2-ac18"), and thus
> grates against "is".
>
> The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
> NMI-oopser is enabled..." In this context the phrase itself is in the
> present, but we point to past kernels.
>
> Chris
>
And the winner is? I'm not native English speaker so I can't select
a better candidate in {is,was} limited set.
- Cyrill -
On Fri, 27 Jun 2008 20:51:25 +0400 Cyrill Gorcunov wrote:
> [Chris Friesen - Fri, Jun 27, 2008 at 10:32:12AM -0600]
> > Alan Cox wrote:
> >> On Fri, 27 Jun 2008 16:54:19 +0100 (BST)
> >> "Maciej W. Rozycki" <[email protected]> wrote:
> >>> On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
> >>>
> >>>
> >>>> +NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
> >>>> +on x86 SMP boxes.
> >>>
> >>> While you are at it: s/is/was/.
> >> Erm - why ??
> >> It is still true today that kernels < 2.4.2-ac8 have the NMI oopser
> >> enabled.
> >
> > To my ear the phrase as written implies past tense for the author/reader
> > (i.e. "at points in time prior to the release of 2.4.2-ac18"), and thus
> > grates against "is".
> >
> > The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
> > NMI-oopser is enabled..." In this context the phrase itself is in the
> > present, but we point to past kernels.
> >
> > Chris
> >
>
> And the winner is? I'm not native English speaker so I can't select
> a better candidate in {is,was} limited set.
Use the text that Chris suggested...
---
~Randy
Linux Plumbers Conference, 17-19 September 2008, Portland, Oregon USA
http://linuxplumbersconf.org/
[Randy Dunlap - Fri, Jun 27, 2008 at 09:56:08AM -0700]
| On Fri, 27 Jun 2008 20:51:25 +0400 Cyrill Gorcunov wrote:
|
| > [Chris Friesen - Fri, Jun 27, 2008 at 10:32:12AM -0600]
| > > Alan Cox wrote:
| > >> On Fri, 27 Jun 2008 16:54:19 +0100 (BST)
| > >> "Maciej W. Rozycki" <[email protected]> wrote:
| > >>> On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
| > >>>
| > >>>
| > >>>> +NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
| > >>>> +on x86 SMP boxes.
| > >>>
| > >>> While you are at it: s/is/was/.
| > >> Erm - why ??
| > >> It is still true today that kernels < 2.4.2-ac8 have the NMI oopser
| > >> enabled.
| > >
| > > To my ear the phrase as written implies past tense for the author/reader
| > > (i.e. "at points in time prior to the release of 2.4.2-ac18"), and thus
| > > grates against "is".
| > >
| > > The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
| > > NMI-oopser is enabled..." In this context the phrase itself is in the
| > > present, but we point to past kernels.
| > >
| > > Chris
| > >
| >
| > And the winner is? I'm not native English speaker so I can't select
| > a better candidate in {is,was} limited set.
|
| Use the text that Chris suggested...
|
|
| ---
| ~Randy
| Linux Plumbers Conference, 17-19 September 2008, Portland, Oregon USA
| http://linuxplumbersconf.org/
|
Ok, you choose ;)
- Cyrill -
---
From: Cyrill Gorcunov <[email protected]>
Subject: [PATCH -tip/master] x86: nmi_watchdog - documentation fix
mi_watchdog is set to NMI_NONE by default (ie disabled) on _any_
mode so lets fix documentation too.
Signed-off-by: Cyrill Gorcunov <[email protected]>
CC: Maciej W. Rozycki <[email protected]>
---
Index: linux-2.6.git/Documentation/nmi_watchdog.txt
====================================================================
--- linux-2.6.git.orig/Documentation/nmi_watchdog.txt 2008-06-27 19:50:06.000000000 +0400
+++ linux-2.6.git/Documentation/nmi_watchdog.txt 2008-06-27 21:15:02.000000000 +0400
@@ -10,7 +10,7 @@ us to generate 'watchdog NMI interrupts'
which get executed even if the system is otherwise locked up hard).
This can be used to debug hard kernel lockups. By executing periodic
NMI interrupts, the kernel can monitor whether any CPU has locked up,
-and print out debugging messages if so.
+and print out debugging messages if so.
In order to use the NMI watchdog, you need to have APIC support in your
kernel. For SMP kernels, APIC support gets compiled in automatically. For
@@ -22,8 +22,7 @@ CONFIG_X86_UP_IOAPIC is for uniprocessor
kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
may implicitly disable the NMI watchdog.]
-For x86-64, the needed APIC is always compiled in, and the NMI watchdog is
-always enabled with I/O-APIC mode (nmi_watchdog=1).
+For x86-64, the needed APIC is always compiled in.
Using local APIC (nmi_watchdog=2) needs the first performance register, so
you can't use it for other purposes (such as high precision performance
@@ -63,16 +62,15 @@ when the system is idle), but if your sy
"hlt", then you are out of luck -- the event will not happen at all and the
watchdog won't trigger. This is a shortcoming of the local APIC watchdog
-- unfortunately there is no "clock ticks" event that would work all the
-time. The I/O APIC watchdog is driven externally and has no such shortcoming.
+time. The I/O APIC watchdog is driven externally and has no such shortcoming.
But its NMI frequency is much higher, resulting in a more significant hit
to the overall system performance.
-NOTE: starting with 2.4.2-ac18 the NMI-oopser is disabled by default,
-you have to enable it with a boot time parameter. Prior to 2.4.2-ac18
-the NMI-oopser is enabled unconditionally on x86 SMP boxes.
+On x86 nmi_watchdog is disabled by default so you have to enable it with
+a boot time parameter.
-On x86-64 the NMI oopser is on by default. On 64bit Intel CPUs
-it uses IO-APIC by default and on AMD it uses local APIC.
+NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
+on x86 SMP boxes.
[ feel free to send bug reports, suggestions and patches to
Ingo Molnar <[email protected]> or the Linux SMP mailing
On Fri, 27 Jun 2008 21:18:36 +0400 Cyrill Gorcunov wrote:
> [Randy Dunlap - Fri, Jun 27, 2008 at 09:56:08AM -0700]
> | On Fri, 27 Jun 2008 20:51:25 +0400 Cyrill Gorcunov wrote:
> |
> | > [Chris Friesen - Fri, Jun 27, 2008 at 10:32:12AM -0600]
> | > > Alan Cox wrote:
> | > >> On Fri, 27 Jun 2008 16:54:19 +0100 (BST)
> | > >> "Maciej W. Rozycki" <[email protected]> wrote:
> | > >>> On Fri, 27 Jun 2008, Cyrill Gorcunov wrote:
> | > >>>
> | > >>>
> | > >>>> +NOTE: Prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
> | > >>>> +on x86 SMP boxes.
> | > >>>
> | > >>> While you are at it: s/is/was/.
> | > >> Erm - why ??
> | > >> It is still true today that kernels < 2.4.2-ac8 have the NMI oopser
> | > >> enabled.
> | > >
> | > > To my ear the phrase as written implies past tense for the author/reader
> | > > (i.e. "at points in time prior to the release of 2.4.2-ac18"), and thus
> | > > grates against "is".
> | > >
> | > > The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
> | > > NMI-oopser is enabled..." In this context the phrase itself is in the
> | > > present, but we point to past kernels.
> | > >
> | > > Chris
> | > >
> | >
> | > And the winner is? I'm not native English speaker so I can't select
> | > a better candidate in {is,was} limited set.
> |
> | Use the text that Chris suggested...
> |
> |
> | ---
> | ~Randy
> | Linux Plumbers Conference, 17-19 September 2008, Portland, Oregon USA
> | http://linuxplumbersconf.org/
> |
>
> Ok, you choose ;)
>
> - Cyrill -
Looks good to me. Thanks for persisting.
> ---
> From: Cyrill Gorcunov <[email protected]>
> Subject: [PATCH -tip/master] x86: nmi_watchdog - documentation fix
>
> mi_watchdog is set to NMI_NONE by default (ie disabled) on _any_
> mode so lets fix documentation too.
>
> Signed-off-by: Cyrill Gorcunov <[email protected]>
> CC: Maciej W. Rozycki <[email protected]>
> ---
>
> Index: linux-2.6.git/Documentation/nmi_watchdog.txt
> ====================================================================
> --- linux-2.6.git.orig/Documentation/nmi_watchdog.txt 2008-06-27 19:50:06.000000000 +0400
> +++ linux-2.6.git/Documentation/nmi_watchdog.txt 2008-06-27 21:15:02.000000000 +0400
> @@ -10,7 +10,7 @@ us to generate 'watchdog NMI interrupts'
> which get executed even if the system is otherwise locked up hard).
> This can be used to debug hard kernel lockups. By executing periodic
> NMI interrupts, the kernel can monitor whether any CPU has locked up,
> -and print out debugging messages if so.
> +and print out debugging messages if so.
>
> In order to use the NMI watchdog, you need to have APIC support in your
> kernel. For SMP kernels, APIC support gets compiled in automatically. For
> @@ -22,8 +22,7 @@ CONFIG_X86_UP_IOAPIC is for uniprocessor
> kernel debugging options, such as Kernel Stack Meter or Kernel Tracer,
> may implicitly disable the NMI watchdog.]
>
> -For x86-64, the needed APIC is always compiled in, and the NMI watchdog is
> -always enabled with I/O-APIC mode (nmi_watchdog=1).
> +For x86-64, the needed APIC is always compiled in.
>
> Using local APIC (nmi_watchdog=2) needs the first performance register, so
> you can't use it for other purposes (such as high precision performance
> @@ -63,16 +62,15 @@ when the system is idle), but if your sy
> "hlt", then you are out of luck -- the event will not happen at all and the
> watchdog won't trigger. This is a shortcoming of the local APIC watchdog
> -- unfortunately there is no "clock ticks" event that would work all the
> -time. The I/O APIC watchdog is driven externally and has no such shortcoming.
> +time. The I/O APIC watchdog is driven externally and has no such shortcoming.
> But its NMI frequency is much higher, resulting in a more significant hit
> to the overall system performance.
>
> -NOTE: starting with 2.4.2-ac18 the NMI-oopser is disabled by default,
> -you have to enable it with a boot time parameter. Prior to 2.4.2-ac18
> -the NMI-oopser is enabled unconditionally on x86 SMP boxes.
> +On x86 nmi_watchdog is disabled by default so you have to enable it with
> +a boot time parameter.
>
> -On x86-64 the NMI oopser is on by default. On 64bit Intel CPUs
> -it uses IO-APIC by default and on AMD it uses local APIC.
> +NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
> +on x86 SMP boxes.
>
> [ feel free to send bug reports, suggestions and patches to
> Ingo Molnar <[email protected]> or the Linux SMP mailing
> --
---
~Randy
Linux Plumbers Conference, 17-19 September 2008, Portland, Oregon USA
http://linuxplumbersconf.org/
> > The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
> > NMI-oopser is enabled..." In this context the phrase itself is in the
> > present, but we point to past kernels.
Agreed.
> And the winner is? I'm not native English speaker so I can't select
> a better candidate in {is,was} limited set.
The suggestion above.
Alan
[Alan Cox - Fri, Jun 27, 2008 at 08:32:04PM +0100]
| > > The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
| > > NMI-oopser is enabled..." In this context the phrase itself is in the
| > > present, but we point to past kernels.
|
| Agreed.
|
| > And the winner is? I'm not native English speaker so I can't select
| > a better candidate in {is,was} limited set.
|
| The suggestion above.
|
| Alan
|
Thanks Alan, I've already sent the updated version. Hope
you will find it in your mbox /I thought I've Cc'ed you/ ;)
- Cyrill -
* Cyrill Gorcunov <[email protected]> wrote:
> [Alan Cox - Fri, Jun 27, 2008 at 08:32:04PM +0100]
> | > > The following sounds better to me: "In kernels prior to 2.4.2-ac18 the
> | > > NMI-oopser is enabled..." In this context the phrase itself is in the
> | > > present, but we point to past kernels.
> |
> | Agreed.
> |
> | > And the winner is? I'm not native English speaker so I can't select
> | > a better candidate in {is,was} limited set.
> |
> | The suggestion above.
> |
> | Alan
> |
>
> Thanks Alan, I've already sent the updated version. Hope you will find
> it in your mbox /I thought I've Cc'ed you/ ;)
applied to tip/x86/nmi-watchdog - thanks everyone.
Ingo