Monitor panic fault 14 - Guests crash every day

[averik]

Hi all,

I have a problem with some guests crashing on a Dell PowerEdge 2950 with ESXi 4.1.

I have googled but I didn't find any meaningful indication of what might be causing this dump.

Can someone help me?

In the attachment the log file. Let me know if you know more information.

Thank you very much!!

Nov 24 17:28:21.742: vcpu-1| MONITOR PANIC: vcpu-0:VMM64 fault 14: src=MONITOR rip=0xfffffffffc2aa237 regs=0xfffffffffc008a60

Nov 24 17:28:21.742: vcpu-0| Exiting vcpu-0

Nov 24 17:28:21.742: vcpu-1| Core dump with build build-320092

Nov 24 17:28:21.761: vcpu-1| Writing monitor corefile "/vmfs/volumes/4cd26dbf-46c7ef78-a4d7-001d091fbb23/Gis_Node_2/vmware64-core0.gz"

Nov 24 17:28:21.761: vcpu-1| CoreDump: dumping core with superuser privileges

Nov 24 17:28:21.763: vcpu-1| VMK Stack for vcpu 0 is at 0x417f84e09000

Nov 24 17:28:21.763: vcpu-1| Saving busmem frames

Nov 24 17:28:21.770: vcpu-1| Saving anonymous memory

Nov 24 17:28:21.778: vcpu-1| Beginning monitor coredump

Nov 24 17:28:22.749: vmx| VTHREAD watched thread 4 "vcpu-0" died

Nov 24 17:28:22.749: vcpu-1| End monitor coredump

Nov 24 17:28:22.750: vcpu-1| Beginning extended monitor coredump

Nov 24 17:28:22.750: vcpu-1| Writing anonymous pages at pos: 4008000

Nov 24 17:28:23.751: mks| VTHREAD watched thread 0 "vmx" died

Nov 24 17:28:24.288: vcpu-1| Writing monitor corefile "/vmfs/volumes/4cd26dbf-46c7ef78-a4d7-001d091fbb23/Gis_Node_2/vmware64-core1.gz"

Nov 24 17:28:24.288: vcpu-1| CoreDump: dumping core with superuser privileges

Nov 24 17:28:24.298: vcpu-1| VMK Stack for vcpu 1 is at 0x417f84e19000

Nov 24 17:28:24.298: vcpu-1| Saving busmem frames

Nov 24 17:28:24.306: vcpu-1| Saving anonymous memory

Nov 24 17:28:24.313: vcpu-1| Beginning monitor coredump

Nov 24 17:28:25.215: vcpu-1| End monitor coredump

Nov 24 17:28:25.215: vcpu-1| Beginning extended monitor coredump

Nov 24 17:28:25.215: vcpu-1| Writing anonymous pages at pos: 4008000

Nov 24 17:28:29.904: vcpu-1| Msg_Post: Error

Nov 24 17:28:29.905: vcpu-1| http://msg.log.monpanic *** VMware ESX internal monitor error ***

Nov 24 17:28:29.905: vcpu-1| vcpu-0:VMM64 fault 14: src=MONITOR rip=0xfffffffffc2aa237 regs=0xfffffffffc008a60

Nov 24 17:28:29.905: vcpu-1| http://msg.log.monpanic.report You can report this problem by selecting menu item Help > VMware on the Web > Request Support, or by going to "http://vmware.com/info?id=8&logFile=%2fvmfs%2fvolumes%2f4cd26dbf%2d46c7ef78%2da4d7%2d001d091fbb23%2fGis%5fNode%5f2%2fvmware%2elog&coreLocation=%2fvmfs%2fvolumes%2f4cd26dbf%2d46c7ef78%2da4d7%2d001d091fbb23%2fGis%5fNode%5f2%2fvmware64%2dcore%5b0%2d1%5d%2egz". Provide the log file (/vmfs/volumes/4cd26dbf-46c7ef78-a4d7-001d091fbb23/Gis_Node_2/vmware.log) and the core file(s) (/vmfs/volumes/4cd26dbf-46c7ef78-a4d7-001d091fbb23/Gis_Node_2/vmware64-core[0-1].gz, /vmfs/volumes/4cd26dbf-46c7ef78-a4d7-001d091fbb23/Gis_Node_2/vmx-zdump.000).

Nov 24 17:28:29.905: vcpu-1| http://msg.log.monpanic.serverdebug If the problem is repeatable, set 'Use Debug Monitor' to 'Yes' in the 'Misc' section of the Configure Virtual Machine Web page. Then reproduce the incident and file it according to the instructions.

Nov 24 17:28:29.905: vcpu-1| http://msg.log.monpanic.vmSupport.vmx86 To collect data to submit to VMware support, run "vm-support".

Nov 24 17:28:29.905: vcpu-1| http://msg.log.monpanic.entitlement We will respond on the basis of your support entitlement.

Nov 24 17:28:29.905: vcpu-1| http://msg.log.monpanic.finish We appreciate your feedback,

Nov 24 17:28:29.905: vcpu-1| -- the VMware ESX team.

Nov 24 17:28:29.905: vcpu-1| -

---

Nov 24 17:28:29.906: vcpu-1| VTHREAD watched thread 0 "vmx" died

[idle-jam · Accepted solution]

Not much i could see, why not create a SR? the last time i had this was due to fault CPU. when that virtual cpu used by the VM fall on the bad CPU socket it will crash. You could do a CPU affinity to fix to to certain CPU and see if it happens or not.

iDLE-jAM | VCP 2, VCP 3 & VCP 4

If you found this or any other answer useful please consider the use of the Helpful or correct buttons to award points

[dcoz]

These are generally caused by an underlying hardware fault.

I would run a hardware diags especially the memory.

Dougie

[averik]

Hi,

I'm doing some tests on the CPU affinity. I'll let you know the test result.

What is a SR? A support request?

Thank you for your fast help!

Giorgio

[averik]

Yes!!

one CPU have 2 cores that crash my VM!!!

Thank you for your help.