PSOD observed on ESXi host : "#DF Exception 8 IP 0x############## SP 0x##############"
search cancel

PSOD observed on ESXi host : "#DF Exception 8 IP 0x############## SP 0x##############"

book

Article ID: 426181

calendar_today

Updated On:

Products

VMware vSAN

Issue/Introduction

Symptoms:

  • One of the ESXi host 8.0 U3 reports PSOD.

  • Backtrace of the PSOD as captured from LogEFI.log of ESX host:

    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)[45m[33;1mVMware ESXi 8.0.3 [Releasebuild-24674464 x86_64][0m
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI[#######]: #DF Exception 8 IP 0x############ SP 0x##############
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI[#######]:
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI[#######]: Module(s) involved in panic: [vsanutil  (External)]
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)cr0=0x80050033 cr2=0x28f0d6e3ffa cr3=0x26e000 cr4=0x146660
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)FMS=06/55/7 uCode=0x5003901
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)frame=0x452a00158f40 ip=0x42000d60f1c6 err=0x0 rflags=0x10202
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)rax=0x432547300ab0 rbx=0x4325472dc7ec rcx=0x4325472dc700
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)rdx=0x432547a91ca8 rbp=0x4325472dc83c rsi=0x2b5c4513d10
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)rdi=0x9f902b29e41c63 r8=0x9f902cba8301f6 r9=0x1a46
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)r10=0xe7f9 r11=0x432547300ab0 r12=0x45db0b7f0410
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)r13=0x4325472dc834 r14=0x432547300ab0 r15=0x432547300a98
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI[#######]: *PCPU21:#######/VSAN_0x4325472dc700_Owner
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI[#######]: PCPU  0: VVVVVVVSVVVVVVSVVVVVVSVVVVVVVVVVVSVVVVVVVVVVVVVVVVVVSVVVVVVVSVVV
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI[#######]: PCPU 64: SSVVVVVVVVVVVVSVVSVVVVVVVVVVSVVS
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)Code start: 0x42000bc00000 VMK uptime: 173:16:21:06.866
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)0x9f909469773e68:[0x42000d60f1c6][email protected]#0.0.0.1+0x23e stack: 0x0
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI: cpu21:#######)base fs=0x0 gs=0x420045400000 Kgs=0x0
    YYYY-MM-DDTHH:MM:SS.###Z In(14) LogEFI[#######]:

Environment

Vmware vSAN 8.x

Cause

  • Host crash occurs due to DF (Double Fault) exception which in turn occurs due to CPU/ECC related errors.

  • For e.g. -- in this instance failure occurred at CPU21.

Resolution

  • Contact server hardware vendor to get the CPU replaced if the backtrace of PSOD reports failure on thread of same CPU in multiple occasions.

  • In other instances, contact Broadcom Technical support for further investigation.