Having issue with VMware 6.0 U3 with PSOD

[djmistro1122]

Need some help here to figure what is going on with my vmware host .

2017-04-18T07:21:58.636Z cpu36:279875)ScsiDeviceIO: 2636: Cmd(0x43be144ee100) 0x1a, CmdSN 0xc4e5 from world 0 to dev "naa.xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" failed H:0x0 D:0x2 P:0x0 Valid sense data: 0x5 0x24 0x0.

2017-04-18T07:39:10.983Z cpu20:34858 opID=f785195)@BlueScreen: PCPU 22 locked up. Failed to ack TLB invalidate (total of 1 locked up, PCPU(s): 22). 

2017-04-18T07:39:10.983Z cpu20:34858 opID=f785195)Code start: 0x41802e000000 VMK uptime: 4:20:40:38.040

2017-04-18T07:39:10.984Z cpu20:34858 opID=f785195)0x43914151b8b0:[0x41802e0780da]PanicvPanicInt@vmkernel#nover+0x37e stack: 0x43914151b948

2017-04-18T07:39:10.984Z cpu20:34858 opID=f785195)0x43914151b940:[0x41802e0783a5]Panic_NoSave@vmkernel#nover+0x4d stack: 0x43914151b9a0

2017-04-18T07:39:10.984Z cpu20:34858 opID=f785195)0x43914151b9a0:[0x41802e08c435]TLBGetLockedCPUBacktraces@vmkernel#nover+0x25d stack: 0x9

2017-04-18T07:39:10.985Z cpu20:34858 opID=f785195)0x43914151bb60:[0x41802e08c726]TLBDoInvalidate@vmkernel#nover+0x21a stack: 0x220b

2017-04-18T07:39:10.985Z cpu20:34858 opID=f785195)0x43914151bbb0:[0x41802e5d5d70]UserMem_CartelFlush@<None>#<None>+0xc0 stack: 0x0

2017-04-18T07:39:10.985Z cpu20:34858 opID=f785195)0x43914151bc30:[0x41802e5d8a84]UserMemUnmapStateCleanup@<None>#<None>+0x60 stack: 0x295000

2017-04-18T07:39:10.985Z cpu20:34858 opID=f785195)0x43914151bd20:[0x41802e5d936e]UserMemUnmap@<None>#<None>+0xaa stack: 0x431229037c71

2017-04-18T07:39:10.986Z cpu20:34858 opID=f785195)0x43914151be80:[0x41802e5d997c]UserMem_Unmap@<None>#<None>+0xec stack: 0x43914151bf30

2017-04-18T07:39:10.986Z cpu20:34858 opID=f785195)0x43914151bee0:[0x41802e5f0f1d]LinuxMem_Munmap@<None>#<None>+0x6d stack: 0x0

2017-04-18T07:39:10.986Z cpu20:34858 opID=f785195)0x43914151bef0:[0x41802e5c5663]User_LinuxSyscallHandler@<None>#<None>+0xd7 stack: 0x2dfc0e68

2017-04-18T07:39:10.987Z cpu20:34858 opID=f785195)0x43914151bf20:[0x41802e08eb01]User_LinuxSyscallHandler@vmkernel#nover+0x1d stack: 0x0

2017-04-18T07:39:10.987Z cpu20:34858 opID=f785195)0x43914151bf30:[0x41802e0c8044]gate_entry_@vmkernel#nover+0x0 stack: 0x0

[dariusd]

I've moved your discussion to the VMware ESXi 6 forum.

What's your host hardware (motherboard, CPU)?  Is it on the vSphere Hardware Compatibility List (HCL)?  Have you applied the latest firmware (BIOS/EFI) updates for the host system?

Cheers,

--

Darius

[djmistro1122]

Here is my hardware spec .

Supermicro Motherboard x10dri

2x Intel Xeon CPU E5-2630 v4 @ 2.2Ghz

320GB Memory

Note: Have applied latest BIOS update.

[djmistro1122]

Can anyone provide some feedback solution to my issue ?

[virtualDD]

Hi,

I found a KB referencing the "failed to ack TLB invalidate": Understanding a "Failed to ack TLB invalidate" purple diagnostic screen (1020214) | VMware KB

Reading the KB suggests that this might be a misbehaving CPU or a software issue.

Which model of the supermicro server do you have?

[djmistro1122]

Hi ,

I have read through the KB previously but still not useful .  There is no model for the server but I have specified the motherboard model .

[OptimusP]

I would first check your microcode version:

ESXi host fails with PSOD when using Intel Xeon Processor E5 v4, E7 v4, and D-1500 families (2146388...

https://kb.vmware.com/kb/2146388

[virtualDD]

I have actually no experience with supermicro products. According to their website: Super Micro Computer, Inc. - Support | OS Compatibility Chart  (they haven't even listed Update 3 yet) the motherboard you mentioned is only compatible with ESXi 6.0 GA.

I think the BIOS Update that is mentioned by OptimusD is taken care because you mentioned to have updated the BIOS recently. Maybe check if there is already a new version available?

[djmistro1122]

Hi

I have already tried the BIOS update but it still does not help . Issue still persist. By the way , i need some clarification for this motherboard, is this model support RAID controller card ? i have a RAID controller card and also updated the firmware  as shown below;

LSI MegaRAID SAS 9260-8I controller card

[OptimusP]

Can you please check :

# zcat /var/log/boot.gz | grep MicrocodeUpdate

Should print 0x0b00001a or later

[djmistro1122]

Hi ,

It is showing as below;

0:00:00:07.245 cpu39:32807)MicrocodeUpdate: 243: Microcode Update Signature (MSR0x8b): 0x0b000010

[OptimusP]

Then, you are running the old one.

You can ask your motherboard vendor to provide the latest BIOS with microcode 0x0b00001a or later

[djmistro1122]

Hi

i have the impression that i was running the new one. Anyways , i'm awaiting for Supermicro to provide the latest BIOS version .

[djmistro1122]

Hi ,

Since the new BIOS firmware update , the vmware host has not crash since ..and i think this has solve the issue.

[OptimusP]

Good to hear that