Skip to contentSkip to conversation

4.10-rc1: thinkpad x60: who ate my cpu?

DISCUSSION Pavel Machek 4 participants 17 messages Jan 8, 2017 – Feb 13, 2017

lore
Share & tools
lore
#0 lore raw

Hi!

I used to have two cpus, and Thinkpad X60 should have two cores, but I only see one on 4.10-rc1. This machine went through many suspend/resume cycles. When backups finish, I'll try -rc2.

pavel@duo:~$ uname -a
Linux duo 4.10.0-rc1+ #304 SMP Mon Dec 26 10:33:24 CET 2016 i686
GNU/Linux
pavel@duo:~$ zcat /proc/config.gz | grep SMP
CONFIG_X86_32_SMP=y
CONFIG_GENERIC_SMP_IDLE_THREAD=y
CONFIG_SMP=y
# CONFIG_X86_BIGSMP is not set
CONFIG_PM_SLEEP_SMP=y
pavel@duo:~$ cat /proc/cpuinfo
processor    : 0
vendor_id    : GenuineIntel
cpu family   : 6
model	       : 14
model name     : Genuine Intel(R) CPU           T2400  @ 1.83GHz
stepping       : 8
cpu MHz	       	 : 1833.000
cache size	 : 2048 KB
physical id	 : 0
siblings : 1
core id	   : 0
cpu cores  : 1
apicid	     : 0
initial apicid : 0
fdiv_bug       : no
f00f_bug       : no
coma_bug       : no
fpu	       	 : yes
fpu_exception	 : yes
cpuid level	 : 10
wp    		 : yes
flags		   : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr
pge mca cmov clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe nx
constant_tsc arch_perfmon bts aperfmperf pni monitor vmx est tm2 xtpr
pdcm dtherm
bugs	:
bogomips	: 3657.62
clflush size	: 64
cache_alignment	: 64
address sizes	: 32 bits physical, 32 bits virtual
power management:

pavel@duo:~$

Pavel

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
#1 lore raw

Hi!

Quoted 3 lines

I used to have two cpus, and Thinkpad X60 should have two cores, but I only see one on 4.10-rc1. This machine went through many suspend/resume cycles. When backups finish, I'll try -rc2.

Whoever did it, he seems to have returned the cpu in -rc3. All seems to be good now.
Pavel

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
#2 lore raw
Quoted 9 lines · Pavel Machek

Hi!

Quoted 3 lines

I used to have two cpus, and Thinkpad X60 should have two cores, but I only see one on 4.10-rc1. This machine went through many suspend/resume cycles. When backups finish, I'll try -rc2.

Whoever did it, he seems to have returned the cpu in -rc3. All seems to be good now.
Pavel

Actually since you have mentioned - I have checked my x60 - same problem - only one CPU. However I was running 4.8.13 with uptime 33 days, multiple sleep/wake-ups. Installed a current EOL 4.8.17 and rebooted - I see 2 CPUs. So the issue is older then 4.10 kernel, and I suspect it is the CPU hotplug / wakeup related...

Woody

#3 lore raw

Hi!

Quoted 9 lines · Woody Suwalski
Quoted 7 lines · Pavel Machek

Hi!

Quoted 3 lines

I used to have two cpus, and Thinkpad X60 should have two cores, but I only see one on 4.10-rc1. This machine went through many suspend/resume cycles. When backups finish, I'll try -rc2.

Whoever did it, he seems to have returned the cpu in -rc3. All seems to be good now.

Quoted 6 lines

Actually since you have mentioned - I have checked my x60 - same problem - only one CPU. However I was running 4.8.13 with uptime 33 days, multiple sleep/wake-ups.
Installed a current EOL 4.8.17 and rebooted - I see 2 CPUs. So the issue is older then 4.10 kernel, and I suspect it is the CPU hotplug / wakeup related...

Hmm. So I seen two cores in -rc3 after boot. But it is quite well possible that -rc1 was ok just after boot, too, and problem happened sometime later (probably during suspend/resume cycles). Let me go back to -rc1 to check.

Best regards,
Pavel

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
#4 lore raw
Quoted 19 lines · Pavel Machek

Hi!

Quoted 9 lines · Woody Suwalski
Quoted 7 lines · Pavel Machek

Hi!

Quoted 3 lines

I used to have two cpus, and Thinkpad X60 should have two cores, but I only see one on 4.10-rc1. This machine went through many suspend/resume cycles. When backups finish, I'll try -rc2.

Whoever did it, he seems to have returned the cpu in -rc3. All seems to be good now.

Quoted 6 lines

Actually since you have mentioned - I have checked my x60 - same problem - only one CPU. However I was running 4.8.13 with uptime 33 days, multiple sleep/wake-ups.
Installed a current EOL 4.8.17 and rebooted - I see 2 CPUs. So the issue is older then 4.10 kernel, and I suspect it is the CPU hotplug / wakeup related...

Quoted 4 lines

Hmm. So I seen two cores in -rc3 after boot. But it is quite well possible that -rc1 was ok just after boot, too, and problem happened sometime later (probably during suspend/resume cycles). Let me go back to -rc1 to check.

Indeed in -rc1 I see both CPUs after boot. So we have hard to reproduce case where 4.8 to 4.10 kernels lose one of the cpu cores...

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
#5 lore raw
Quoted 18 lines · Pavel Machek
Quoted 17 lines · Pavel Machek

Hi!

Quoted 14 lines · Woody Suwalski
Quoted 7 lines · Pavel Machek

Hi!

Quoted 3 lines

I used to have two cpus, and Thinkpad X60 should have two cores, but I only see one on 4.10-rc1. This machine went through many suspend/resume cycles. When backups finish, I'll try -rc2.

Whoever did it, he seems to have returned the cpu in -rc3. All seems to be good now.

Actually since you have mentioned - I have checked my x60 - same problem - only one CPU. However I was running 4.8.13 with uptime 33 days, multiple sleep/wake-ups.
Installed a current EOL 4.8.17 and rebooted - I see 2 CPUs. So the issue is older then 4.10 kernel, and I suspect it is the CPU hotplug / wakeup related...

Quoted 9 lines
Quoted 4 lines

Hmm. So I seen two cores in -rc3 after boot. But it is quite well possible that -rc1 was ok just after boot, too, and problem happened sometime later (probably during suspend/resume cycles). Let me go back to -rc1 to check.

Indeed in -rc1 I see both CPUs after boot. So we have hard to reproduce case where 4.8 to 4.10 kernels lose one of the cpu cores...

Managed to duplicate - but it took again a long time - I have an uptime of 29 days. It must have happened in the last day, as I kept checking as often as I remembered.

The kernel is 4.8.17 EOL, installed almost a month ago.
Platform ThinkPad x60, Intel(R) Core(TM) Duo CPU T2400 @ 1.83GHz

In dmesg I see that it used to be when 2 CPUs were OK:

[690409.476107] PM: noirq suspend of devices complete after 79.914 msecs
[690409.476547] ACPI: Preparing to enter system sleep state S3
[690409.780081] ACPI : EC: EC stopped
[690409.780083] PM: Saving platform NVS memory
[690409.780284] Disabling non-boot CPUs ...
[690409.805284] smpboot: CPU 1 is now offline
[690409.816464] ACPI: Low-level resume complete
[690409.816464] ACPI : EC: EC started
[690409.816464] PM: Restoring platform NVS memory
[690409.816464] Enabling non-boot CPUs ...
[690409.840574] x86: Booting SMP configuration:
[690409.840576] smpboot: Booting Node 0 Processor 1 APIC 0x1
[690409.805271] Initializing CPU#1
[690409.805271] Disabled fast string operations
[690409.888252]  cache: parent cpu1 should not be sleeping
[690409.920185] CPU1 is up
[690409.922288] ACPI: Waking up from system sleep state S3

Then the CPU1 failed to start:

[691329.776108] PM: noirq suspend of devices complete after 79.941 msecs
[691329.776550] ACPI: Preparing to enter system sleep state S3
[691330.080081] ACPI : EC: EC stopped
[691330.080083] PM: Saving platform NVS memory
[691330.080284] Disabling non-boot CPUs ...
[691330.105303] smpboot: CPU 1 is now offline
[691330.116477] ACPI: Low-level resume complete
[691330.116477] ACPI : EC: EC started
[691330.116477] PM: Restoring platform NVS memory
[691330.116477] Enabling non-boot CPUs ...
[691330.140570] x86: Booting SMP configuration:
[691330.140572] smpboot: Booting Node 0 Processor 1 APIC 0x1
[691340.140015] smpboot: do_boot_cpu failed(-1) to wakeup CPU#1
[691340.164445] Error taking CPU1 up: -5
[691340.166309] ACPI: Waking up from system sleep state S3

And now it is:

[692517.868523] ACPI: Preparing to enter system sleep state S3
[692518.172074] ACPI : EC: EC stopped
[692518.172076] PM: Saving platform NVS memory
[692518.172269] Disabling non-boot CPUs ...
[692518.172269] ACPI: Low-level resume complete
[692518.172269] ACPI : EC: EC started
[692518.172269] PM: Restoring platform NVS memory
[692518.172269] ACPI: Waking up from system sleep state S3

Is there any test I could do on the CPU wakeup while in that state?

Woody

#6 lore raw
Quoted 81 lines · Woody Suwalski
Quoted 18 lines · Pavel Machek
Quoted 17 lines · Pavel Machek

Hi!

Quoted 14 lines · Woody Suwalski
Quoted 7 lines · Pavel Machek

Hi!

Quoted 3 lines

I used to have two cpus, and Thinkpad X60 should have two cores, but I only see one on 4.10-rc1. This machine went through many suspend/resume cycles. When backups finish, I'll try -rc2.

Whoever did it, he seems to have returned the cpu in -rc3. All seems to be good now.

Actually since you have mentioned - I have checked my x60 - same problem - only one CPU. However I was running 4.8.13 with uptime 33 days, multiple sleep/wake-ups.
Installed a current EOL 4.8.17 and rebooted - I see 2 CPUs. So the issue is older then 4.10 kernel, and I suspect it is the CPU hotplug / wakeup related...

Quoted 9 lines
Quoted 4 lines

Hmm. So I seen two cores in -rc3 after boot. But it is quite well possible that -rc1 was ok just after boot, too, and problem happened sometime later (probably during suspend/resume cycles). Let me go back to -rc1 to check.

Indeed in -rc1 I see both CPUs after boot. So we have hard to reproduce case where 4.8 to 4.10 kernels lose one of the cpu cores...

Managed to duplicate - but it took again a long time - I have an uptime of 29 days. It must have happened in the last day, as I kept checking as often as I remembered.

The kernel is 4.8.17 EOL, installed almost a month ago.
Platform ThinkPad x60, Intel(R) Core(TM) Duo CPU T2400 @ 1.83GHz

In dmesg I see that it used to be when 2 CPUs were OK:

[690409.476107] PM: noirq suspend of devices complete after 79.914 msecs
[690409.476547] ACPI: Preparing to enter system sleep state S3
[690409.780081] ACPI : EC: EC stopped
[690409.780083] PM: Saving platform NVS memory
[690409.780284] Disabling non-boot CPUs ...
[690409.805284] smpboot: CPU 1 is now offline
[690409.816464] ACPI: Low-level resume complete
[690409.816464] ACPI : EC: EC started
[690409.816464] PM: Restoring platform NVS memory
[690409.816464] Enabling non-boot CPUs ...
[690409.840574] x86: Booting SMP configuration:
[690409.840576] smpboot: Booting Node 0 Processor 1 APIC 0x1
[690409.805271] Initializing CPU#1
[690409.805271] Disabled fast string operations
[690409.888252]  cache: parent cpu1 should not be sleeping
[690409.920185] CPU1 is up
[690409.922288] ACPI: Waking up from system sleep state S3

Then the CPU1 failed to start:

[691329.776108] PM: noirq suspend of devices complete after 79.941 msecs
[691329.776550] ACPI: Preparing to enter system sleep state S3
[691330.080081] ACPI : EC: EC stopped
[691330.080083] PM: Saving platform NVS memory
[691330.080284] Disabling non-boot CPUs ...
[691330.105303] smpboot: CPU 1 is now offline
[691330.116477] ACPI: Low-level resume complete
[691330.116477] ACPI : EC: EC started
[691330.116477] PM: Restoring platform NVS memory
[691330.116477] Enabling non-boot CPUs ...
[691330.140570] x86: Booting SMP configuration:
[691330.140572] smpboot: Booting Node 0 Processor 1 APIC 0x1
[691340.140015] smpboot: do_boot_cpu failed(-1) to wakeup CPU#1
[691340.164445] Error taking CPU1 up: -5
[691340.166309] ACPI: Waking up from system sleep state S3

And now it is:

[692517.868523] ACPI: Preparing to enter system sleep state S3
[692518.172074] ACPI : EC: EC stopped
[692518.172076] PM: Saving platform NVS memory
[692518.172269] Disabling non-boot CPUs ...
[692518.172269] ACPI: Low-level resume complete
[692518.172269] ACPI : EC: EC started
[692518.172269] PM: Restoring platform NVS memory
[692518.172269] ACPI: Waking up from system sleep state S3
Quoted 4 lines

Is there any test I could do on the CPU wakeup while in that state?

Woody

Is there a way to kick the offline-CPU into operation from /sys level?

#7 lore raw

Hi!

Quoted 50 lines
Quoted 50 lines

The kernel is 4.8.17 EOL, installed almost a month ago.
Platform ThinkPad x60, Intel(R) Core(TM) Duo CPU T2400 @ 1.83GHz

In dmesg I see that it used to be when 2 CPUs were OK:

[690409.476107] PM: noirq suspend of devices complete after 79.914 msecs
[690409.476547] ACPI: Preparing to enter system sleep state S3
[690409.780081] ACPI : EC: EC stopped
[690409.780083] PM: Saving platform NVS memory
[690409.780284] Disabling non-boot CPUs ...
[690409.805284] smpboot: CPU 1 is now offline
[690409.816464] ACPI: Low-level resume complete
[690409.816464] ACPI : EC: EC started
[690409.816464] PM: Restoring platform NVS memory
[690409.816464] Enabling non-boot CPUs ...
[690409.840574] x86: Booting SMP configuration:
[690409.840576] smpboot: Booting Node 0 Processor 1 APIC 0x1
[690409.805271] Initializing CPU#1
[690409.805271] Disabled fast string operations
[690409.888252]  cache: parent cpu1 should not be sleeping
[690409.920185] CPU1 is up
[690409.922288] ACPI: Waking up from system sleep state S3

Then the CPU1 failed to start:

[691329.776108] PM: noirq suspend of devices complete after 79.941 msecs
[691329.776550] ACPI: Preparing to enter system sleep state S3
[691330.080081] ACPI : EC: EC stopped
[691330.080083] PM: Saving platform NVS memory
[691330.080284] Disabling non-boot CPUs ...
[691330.105303] smpboot: CPU 1 is now offline
[691330.116477] ACPI: Low-level resume complete
[691330.116477] ACPI : EC: EC started
[691330.116477] PM: Restoring platform NVS memory
[691330.116477] Enabling non-boot CPUs ...
[691330.140570] x86: Booting SMP configuration:
[691330.140572] smpboot: Booting Node 0 Processor 1 APIC 0x1
[691340.140015] smpboot: do_boot_cpu failed(-1) to wakeup CPU#1
[691340.164445] Error taking CPU1 up: -5
[691340.166309] ACPI: Waking up from system sleep state S3

And now it is:

[692517.868523] ACPI: Preparing to enter system sleep state S3
[692518.172074] ACPI : EC: EC stopped
[692518.172076] PM: Saving platform NVS memory
[692518.172269] Disabling non-boot CPUs ...
[692518.172269] ACPI: Low-level resume complete
[692518.172269] ACPI : EC: EC started
[692518.172269] PM: Restoring platform NVS memory
[692518.172269] ACPI: Waking up from system sleep state S3
Quoted 3 lines
Quoted 2 lines

Is there any test I could do on the CPU wakeup while in that state?

Is there a way to kick the offline-CPU into operation from /sys level?

echo 0 > /sys/devices/system/cpu/cpu1/online

should work. And... good thinking :-).

Pavel

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
#8 lore raw
Quoted 52 lines · Pavel Machek

Hi!

Quoted 50 lines
Quoted 50 lines

The kernel is 4.8.17 EOL, installed almost a month ago.
Platform ThinkPad x60, Intel(R) Core(TM) Duo CPU T2400 @ 1.83GHz

In dmesg I see that it used to be when 2 CPUs were OK:

[690409.476107] PM: noirq suspend of devices complete after 79.914 msecs
[690409.476547] ACPI: Preparing to enter system sleep state S3
[690409.780081] ACPI : EC: EC stopped
[690409.780083] PM: Saving platform NVS memory
[690409.780284] Disabling non-boot CPUs ...
[690409.805284] smpboot: CPU 1 is now offline
[690409.816464] ACPI: Low-level resume complete
[690409.816464] ACPI : EC: EC started
[690409.816464] PM: Restoring platform NVS memory
[690409.816464] Enabling non-boot CPUs ...
[690409.840574] x86: Booting SMP configuration:
[690409.840576] smpboot: Booting Node 0 Processor 1 APIC 0x1
[690409.805271] Initializing CPU#1
[690409.805271] Disabled fast string operations
[690409.888252]  cache: parent cpu1 should not be sleeping
[690409.920185] CPU1 is up
[690409.922288] ACPI: Waking up from system sleep state S3

Then the CPU1 failed to start:

[691329.776108] PM: noirq suspend of devices complete after 79.941 msecs
[691329.776550] ACPI: Preparing to enter system sleep state S3
[691330.080081] ACPI : EC: EC stopped
[691330.080083] PM: Saving platform NVS memory
[691330.080284] Disabling non-boot CPUs ...
[691330.105303] smpboot: CPU 1 is now offline
[691330.116477] ACPI: Low-level resume complete
[691330.116477] ACPI : EC: EC started
[691330.116477] PM: Restoring platform NVS memory
[691330.116477] Enabling non-boot CPUs ...
[691330.140570] x86: Booting SMP configuration:
[691330.140572] smpboot: Booting Node 0 Processor 1 APIC 0x1
[691340.140015] smpboot: do_boot_cpu failed(-1) to wakeup CPU#1
[691340.164445] Error taking CPU1 up: -5
[691340.166309] ACPI: Waking up from system sleep state S3

And now it is:

[692517.868523] ACPI: Preparing to enter system sleep state S3
[692518.172074] ACPI : EC: EC stopped
[692518.172076] PM: Saving platform NVS memory
[692518.172269] Disabling non-boot CPUs ...
[692518.172269] ACPI: Low-level resume complete
[692518.172269] ACPI : EC: EC started
[692518.172269] PM: Restoring platform NVS memory
[692518.172269] ACPI: Waking up from system sleep state S3
Quoted 8 lines
Quoted 3 lines
Quoted 2 lines

Is there any test I could do on the CPU wakeup while in that state?

Is there a way to kick the offline-CPU into operation from /sys level?

echo 0 > /sys/devices/system/cpu/cpu1/online

should work. And... good thinking :-).

Pavel

Did not work,
echo 0 > /sys/devices/system/cpu/cpu1/online -su: echo: write error: Device or resource busy

However
echo 1 > /sys/devices/system/cpu/cpu1/online
did not return an error ( but still only CPU0 seen)

Interesting experiment: I have hibernated and then woke up - and still only CPU0. I was expecting that after the power cycle the hotplug will bring CPU1 up...

Woody

#9 lore raw

Hi!

Quoted 21 lines
Quoted 10 lines
Quoted 10 lines
Quoted 10 lines

And now it is:

[692517.868523] ACPI: Preparing to enter system sleep state S3
[692518.172074] ACPI : EC: EC stopped
[692518.172076] PM: Saving platform NVS memory
[692518.172269] Disabling non-boot CPUs ...
[692518.172269] ACPI: Low-level resume complete
[692518.172269] ACPI : EC: EC started
[692518.172269] PM: Restoring platform NVS memory
[692518.172269] ACPI: Waking up from system sleep state S3
Quoted 7 lines
Quoted 3 lines
Quoted 2 lines

Is there any test I could do on the CPU wakeup while in that state?

Is there a way to kick the offline-CPU into operation from /sys level?

echo 0 > /sys/devices/system/cpu/cpu1/online

should work. And... good thinking :-).
Pavel

Did not work,
echo 0 > /sys/devices/system/cpu/cpu1/online -su: echo: write error: Device or resource busy

Quoted 7 lines

However
echo 1 > /sys/devices/system/cpu/cpu1/online
did not return an error ( but still only CPU0 seen)

Interesting experiment: I have hibernated and then woke up - and still only CPU0. I was expecting that after the power cycle the hotplug will bring CPU1 up...

Which is interesting indeed. Hardware was powercycled, so what is broken is probably some kernel state...

[Evil: /sys/devices/cpu/ -- some perf stuff.
/sys/devices/system/cpu -- that's where real CPU stuff is hiding.]

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Pavel

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
#10 lore raw
Quoted 6 lines · Pavel Machek

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Can you tell where it crashes?

Thanks,

tglx

#11 lore raw

Hi!

Quoted 9 lines · Thomas Gleixner
Quoted 6 lines · Pavel Machek

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Can you tell where it crashes?

I did not expect a crash, so I was in X... I have a feeling that this will be reproducible on a lot of hardware, but let me try.

Pavel

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
#12 lore raw
Quoted 7 lines · Pavel Machek

Hi!

Quoted 4 lines · Thomas Gleixner
Quoted 3 lines · Pavel Machek

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Can you tell where it crashes?

I did not expect a crash, so I was in X... I have a feeling that this will be reproducible on a lot of hardware, but let me try.

FYI: Lockup reproduced with 4.10.0-rc7 with an X61s.

Caught a glimpse of something about an RCU stall timeout before the system shut off. Prior to that, during the loop execution, a bunch of systemd processes were experiencing watchdog timeouts, and procps top would start but never refresh, leaving the CPU column all "nan".

Regards,
Vito Caputo

#13 lore raw
Quoted 17 lines · On Mon, 13 Feb 2017, [email protected] wrote:
Quoted 7 lines · Pavel Machek

Hi!

Quoted 4 lines · Thomas Gleixner
Quoted 3 lines · Pavel Machek

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Can you tell where it crashes?

I did not expect a crash, so I was in X... I have a feeling that this will be reproducible on a lot of hardware, but let me try.

Quoted 6 lines

FYI: Lockup reproduced with 4.10.0-rc7 with an X61s.

Caught a glimpse of something about an RCU stall timeout before the system shut off. Prior to that, during the loop execution, a bunch of systemd processes were experiencing watchdog timeouts, and procps top would start but never refresh, leaving the CPU column all "nan".

Does the machine use intel_idle by chance?

Thanks,

tglx

#14 lore raw
Quoted 19 lines · Thomas Gleixner
Quoted 17 lines · On Mon, 13 Feb 2017, [email protected] wrote:
Quoted 15 lines · Pavel Machek

Hi!

Quoted 9 lines · Thomas Gleixner
Quoted 6 lines · Pavel Machek

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Can you tell where it crashes?

I did not expect a crash, so I was in X... I have a feeling that this will be reproducible on a lot of hardware, but let me try.

Quoted 9 lines
Quoted 6 lines

FYI: Lockup reproduced with 4.10.0-rc7 with an X61s.

Caught a glimpse of something about an RCU stall timeout before the system shut off. Prior to that, during the loop execution, a bunch of systemd processes were experiencing watchdog timeouts, and procps top would start but never refresh, leaving the CPU column all "nan".

Does the machine use intel_idle by chance?

It's not enabled in my kernel, /proc/config.gz attached FWIW.

Regards,
Vito Caputo

#15 lore raw
In reply to Thomas Gleixner
Quoted 19 lines · Thomas Gleixner
Quoted 17 lines · On Mon, 13 Feb 2017, [email protected] wrote:
Quoted 15 lines · Pavel Machek

Hi!

Quoted 9 lines · Thomas Gleixner
Quoted 6 lines · Pavel Machek

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Can you tell where it crashes?

I did not expect a crash, so I was in X... I have a feeling that this will be reproducible on a lot of hardware, but let me try.

Quoted 9 lines
Quoted 6 lines

FYI: Lockup reproduced with 4.10.0-rc7 with an X61s.

Caught a glimpse of something about an RCU stall timeout before the system shut off. Prior to that, during the loop execution, a bunch of systemd processes were experiencing watchdog timeouts, and procps top would start but never refresh, leaving the CPU column all "nan".

Does the machine use intel_idle by chance?

Config actually attached this time!

Regards,
Vito Caputo

#16 lore raw
In reply to [email protected]
Quoted 17 lines · On Mon 2017-02-13 04:18:51, [email protected] wrote:
Quoted 7 lines · Pavel Machek

Hi!

Quoted 4 lines · Thomas Gleixner
Quoted 3 lines · Pavel Machek

cd /sys/devices/system/cpu/cpu1
while true; do echo 0 > online; echo 1 > online; done

Quoted 8 lines
Quoted 5 lines
Quoted 3 lines

...crashes x60 with 4.10-rc in few minutes. [Which is bad -- it should not die, but also good -- this is easier to reproduce then running 100 suspend cycles.]

Can you tell where it crashes?

I did not expect a crash, so I was in X... I have a feeling that this will be reproducible on a lot of hardware, but let me try.

Quoted 6 lines

FYI: Lockup reproduced with 4.10.0-rc7 with an X61s.

Caught a glimpse of something about an RCU stall timeout before the system shut off. Prior to that, during the loop execution, a bunch of systemd processes were experiencing watchdog timeouts, and procps top would start but never refresh, leaving the CPU column all "nan".

Hmm. I was not able to reproduce the lockup when I was running "while true" over ssh. Some weird stuff happened when I suspended machine with that loop running, but... I guess that was expected.

Pavel

Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html