ESXi 6.5 host fails with PSOD: GP Exception 13 in world 73583:NetWorld-VM

Products

• VMware vSphere ESXi

Issue/Introduction

To work around this issue, re-boot the ESXi host.

Symptoms:

• ESXi 6.5 host fails with purple diagnostic screen when virtual machine migrates from ESXi 6.0 to ESXi 6.5.
• You see the stack traces similar to :
  
  2017-01-09T02:07:16.683Z cpu1:73583)Backtrace for current CPU #1, worldID=73583, fp=0x430449673880
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79b4d8:[0x4180319b757b]Pkt_CopyBytesOut@vmkernel#nover+0x1b stack: 0x43954dbbcb80, 0xffffff00, 0x4391fb79b7f0, 0x380fffffff000, 0x8000000000000000
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79b4e0:[0x418031a58e83]Vmxnet3VMKDevDeliverPktToQueue@vmkernel#nover+0x547 stack: 0xffffff00, 0x4391fb79b7f0, 0x380fffffff000, 0x8000000000000000, 0x3ffffff
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79b610:[0x418031a5a502]Vmxnet3VMKDevRxWithLock@vmkernel#nover+0x5d6 stack: 0x0, 0xffffffff00000002, 0x43041c664980, 0x0, 0x0
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79b860:[0x418031a5c547]Vmxnet3VMKDevRx@vmkernel#nover+0x4cf stack: 0x417ff1b1fd00, 0x4391fb7a8b40, 0x43041c662240, 0x0, 0x0
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79b910:[0x4180319d9381]IOChain_Resume@vmkernel#nover+0x1b5 stack: 0x43041c664d80, 0x0, 0x0, 0x101000000, 0x0
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79b9c0:[0x418031a09980]PortOutput@vmkernel#nover+0x118 stack: 0x1, 0x4395473ea480, 0x4395473ea508, 0x3, 0x4395443cb5c8
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79ba20:[0x41803215e8ea]EtherswitchForwardLeafPorts@(etherswitch)#<None>+0x21e stack: 0x4391fb79bbb0, 0x4395443cb5c8, 0x43041c5b9f40, 0x1b001c529660, 0x4395443cb9c8
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79ba90:[0x418032160831]EtherswitchPortDispatch@(etherswitch)#<None>+0x14c1 stack: 0x1, 0x4395443cb9c8, 0x430746001850, 0x4391fb79bd38, 0x4395443cb5c8
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79bc60:[0x418031a09b7c]Port_InputResume@vmkernel#nover+0x120 stack: 0x418031a09b6a, 0x0, 0x0, 0x0, 0x4391fb79bd38
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79bcb0:[0x418031a67a7b]Vmxnet3VMKDevTQDoTx@vmkernel#nover+0x13bf stack: 0x439000000000, 0x43041c5b9f40, 0x439200000001, 0x43044964a280, 0x1
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79be40:[0x418031a68fbb]Vmxnet3VMKDev_AsyncTx@vmkernel#nover+0x8f stack: 0x1000019fb7a7000, 0x180000000, 0xe00c7679afe, 0x28d0848bd9, 0x0
  2017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79bf80:[0x4180319f5d7b]NetWorldPerVMCB@vmkernel#nover+0x15b stack: 0x0, 0x43041c5b9f40, 0x0, 0x4391fb7a7000, 0x4391fbd271002017-01-09T02:07:16.683Z cpu1:73583)0x4391fb79bfe0:[0x418031ac8bd5]CpuSched_StartWorld@vmkernel#nover+0x99 stack: 0x0, 0x0, 0x0, 0x0, 0x0

Note: The preceding log excerpts are only examples. Date, time, and environmental variables may vary depending on your environment.

Environment

VMware vSphere ESXi 6.5

Cause

This issue occurs when the guest memory preallocation or pinning is in progress and VMXNET3 at the backend tries to access the memory address of the guest. This leads to invalid memory access which causes ESXi 6.5 host to fail.

Resolution

This issue is resolved in ESXi 6.5 U1, available at Support Documents and Downloads.

 

To workaround this issue, reboot the ESXi host.

Additional Information

To be alerted when this document is updated, click the Subscribe to Article link in the Actions box in the Actions box.