kernel:BUG: soft lockup - CPU#19 stuck for

[Anon Anon]

Hi guys,

 

I used to install LISA devtest 9.0 on Linux Ubuntu, Java 7. I have just started to pass to Linux Redhat 7.1 and Java 8 and I have this bug:
kernel:BUG: soft lockup - CPU#19 stuck for 23s! [java:25236]

java:25236 is a LISA process (as the picture below)

My server stopped running right after

I would like to know if this problem comes from a LISA bug. FYI, our server has 20 CPUs and 32Gb RAM. Our network administrator told that the bug can't come from OS or Hardware...

 

Architecture: x86_64

CPU op-mode(s):        32-bit, 64-bit

Byte Order:            Little Endian

CPU(s): 20

On-line CPU(s) list:   0-19

Thread(s) per core:    1

Core(s) per socket:    1

Socket(s): 20

NUMA node(s):          2

Vendor ID: GenuineIntel

CPU family:            6

Model: 63

Model name: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz

Stepping: 2

CPU MHz: 2297.339

BogoMIPS: 4594.67

Hypervisor vendor:     VMware

Virtualization type:   full

L1d cache: 32K

L1i cache: 32K

L2 cache: 256K

L3 cache: 46080K

NUMA node0 CPU(s):     0-9

NUMA node1 CPU(s):     10-19

 

Thanks in advance

[Rick.Brown]

I used to see this error quite often in Linux, when the power supply wasn't rated high enough for the load that the CPUs were drawing when being exercised hard.

 

This is just a guess, but can you ask your administrator if that machine provides the ability to monitor its voltages? I would tend to look there first. I see from your post that it's running in a VMWare session. Are there lots of VMWare sessions running on that hardware, causing IO delays?

 

Your second screenshot shows every CPU in a stuck mode, with different Java process IDs. Is DevTest running on each of these? If so, your administrator might want to install cpulimit to restrict the number of CPUs that DevTest can use (equivalent to "set affinity" on Windows), or nice them to a lower priority.

 

Rick