Skip to contentSkip to conversation

Confusing behaviour with /proc/sys/kernel/nmi_watchdog

DISCUSSION Anton Blanchard 3 participants 7 messages Nov 4, 2014 – Jan 21, 2015

lore
Share & tools
lore
#0 lore raw

Hi,

commit 9919e39a1738 ("kvm: ensure hard lockup detection is disabled by default") provided a way for the kernel to disable the hard lockup detector at runtime.

I'm using it on ppc64 but notice some weird behaviour with the nmi_watchdog procfs variable. At boot, that the hard lockup detector appears to be enabled even when we disable it via watchdog_enable_hardlockup_detector(false):

# cat /proc/sys/kernel/nmi_watchdog 
1

I have to echo 0 to it then echo 1 again to enable it.

Anton

#1 lore raw
Quoted 12 lines · Anton Blanchard

Hi,

commit 9919e39a1738 ("kvm: ensure hard lockup detection is disabled by default") provided a way for the kernel to disable the hard lockup detector at runtime.

I'm using it on ppc64 but notice some weird behaviour with the nmi_watchdog procfs variable. At boot, that the hard lockup detector appears to be enabled even when we disable it via watchdog_enable_hardlockup_detector(false):

Quoted 6 lines
# cat /proc/sys/kernel/nmi_watchdog 
1

I have to echo 0 to it then echo 1 again to enable it.

Anton

Hi Anton,

Yes, the nmi watchdog proc variables are currently a bit confusing. Uli has posted a series to clear all that up though. Please see

https://lkml.org/lkml/2014/10/17/340

drew

#2 lore raw

Hi Andrew,

Quoted 17 lines · Anton Blanchard
Quoted 9 lines

commit 9919e39a1738 ("kvm: ensure hard lockup detection is disabled by default") provided a way for the kernel to disable the hard lockup detector at runtime.

I'm using it on ppc64 but notice some weird behaviour with the nmi_watchdog procfs variable. At boot, that the hard lockup detector appears to be enabled even when we disable it via watchdog_enable_hardlockup_detector(false):

Quoted 6 lines
# cat /proc/sys/kernel/nmi_watchdog 
1

I have to echo 0 to it then echo 1 again to enable it.

Anton

Quoted 7 lines

Hi Anton,

Yes, the nmi watchdog proc variables are currently a bit confusing. Uli has posted a series to clear all that up though. Please see

https://lkml.org/lkml/2014/10/17/340

Any progress on this? I'm rebasing our hardware NMI patch for ppc64 and notice the strange behaviour is still in mainline.

Anton

#3 lore raw
Quoted 21 lines · Anton Blanchard

Hi Andrew,

Quoted 19 lines · Anton Blanchard
Quoted 9 lines

commit 9919e39a1738 ("kvm: ensure hard lockup detection is disabled by default") provided a way for the kernel to disable the hard lockup detector at runtime.

I'm using it on ppc64 but notice some weird behaviour with the nmi_watchdog procfs variable. At boot, that the hard lockup detector appears to be enabled even when we disable it via watchdog_enable_hardlockup_detector(false):

Quoted 6 lines
# cat /proc/sys/kernel/nmi_watchdog 
1

I have to echo 0 to it then echo 1 again to enable it.

Anton

Hi Anton,

Quoted 9 lines
Quoted 5 lines

Yes, the nmi watchdog proc variables are currently a bit confusing. Uli has posted a series to clear all that up though. Please see

https://lkml.org/lkml/2014/10/17/340

Any progress on this? I'm rebasing our hardware NMI patch for ppc64 and notice the strange behaviour is still in mainline.

Hi Anton,

I'm not aware of anything blocking this series, but maybe I missed something. Andrew Morton and Don Zickus are the ones to ask. Andrew? Don?

Thanks,
drew

#4 lore raw
Quoted 32 lines · Andrew Jones
Quoted 21 lines · Anton Blanchard

Hi Andrew,

Quoted 19 lines · Anton Blanchard
Quoted 9 lines

commit 9919e39a1738 ("kvm: ensure hard lockup detection is disabled by default") provided a way for the kernel to disable the hard lockup detector at runtime.

I'm using it on ppc64 but notice some weird behaviour with the nmi_watchdog procfs variable. At boot, that the hard lockup detector appears to be enabled even when we disable it via watchdog_enable_hardlockup_detector(false):

Quoted 6 lines
# cat /proc/sys/kernel/nmi_watchdog 
1

I have to echo 0 to it then echo 1 again to enable it.

Anton

Hi Anton,

Quoted 9 lines
Quoted 5 lines

Yes, the nmi watchdog proc variables are currently a bit confusing. Uli has posted a series to clear all that up though. Please see

https://lkml.org/lkml/2014/10/17/340

Any progress on this? I'm rebasing our hardware NMI patch for ppc64 and notice the strange behaviour is still in mainline.

Quoted 5 lines

Hi Anton,

I'm not aware of anything blocking this series, but maybe I missed something. Andrew Morton and Don Zickus are the ones to ask. Andrew? Don?

Hi Drew,

I poked Andrew again. I believe he is the person who usually takes my patches in.

Cheers,
Don

#5 lore raw
In reply to Anton Blanchard
Quoted 12 lines · Anton Blanchard

Hi,

commit 9919e39a1738 ("kvm: ensure hard lockup detection is disabled by default") provided a way for the kernel to disable the hard lockup detector at runtime.

I'm using it on ppc64 but notice some weird behaviour with the nmi_watchdog procfs variable. At boot, that the hard lockup detector appears to be enabled even when we disable it via watchdog_enable_hardlockup_detector(false):

Quoted 4 lines
# cat /proc/sys/kernel/nmi_watchdog 
1

I have to echo 0 to it then echo 1 again to enable it.

Hi Anton,

I believe Andrew answered the question for you, it's a WIP and we have patches to clean that up.

I don't see ppc64 watchdog support in arch/powerpc, is that something you are working with on implementing?

Cheers,
Don

#6 lore raw

Hi Don,

Quoted 9 lines
Quoted 9 lines

commit 9919e39a1738 ("kvm: ensure hard lockup detection is disabled by default") provided a way for the kernel to disable the hard lockup detector at runtime.

I'm using it on ppc64 but notice some weird behaviour with the nmi_watchdog procfs variable. At boot, that the hard lockup detector appears to be enabled even when we disable it via watchdog_enable_hardlockup_detector(false):

Quoted 7 lines
Quoted 4 lines
# cat /proc/sys/kernel/nmi_watchdog 
1

I have to echo 0 to it then echo 1 again to enable it.

I believe Andrew answered the question for you, it's a WIP and we have patches to clean that up.

Thanks, yes good to see it being worked on.

Quoted 2 lines

I don't see ppc64 watchdog support in arch/powerpc, is that something you are working with on implementing?

I've submitted it over on linuxppc-dev:

http://patchwork.ozlabs.org/patch/406802/

Anton