ESXi Host Unexpectedly Reboots or Powers Off Without PSOD Due to "Processor Predictive Failure"

Products

• VMware vSphere ESXi

Issue/Introduction

An ESXi host unexpectedly reboots, shuts down, or power cycles without generating a Purple Screen of Death (PSOD) or vmcore dump files.
Upon checking the logs after the host boots back up, the following messages are observed in vobd.log, hostd.log, or vmksummary.log:

vobd.log and hostd.log:
YYYY-MM-DDTHH:MM:SS[esx.audit.host.poweroff.reason.unavailable] The host is being powered off. The poweroff was not the result of a kernel error, deliberate reboot, or shut down. This could indicate a hardware issue. Hardware may reboot abruptly due to power outages, faulty components, and heating issues. To investigate further, engage the hardware vendor.
vmksummary.log:
YYYY-MM-DDTHH:MM:SSNo(13) bootstop[2101074]: Host has booted

Check Hardware IPMI SEL (System Event Logs):
Inspect the IPMI System Event Logs (SEL) via the OEM hardware management controller (e.g., Cisco CIMC / UCSM / Intersight).

Look for CPU predictive failure assertions prior to each unexpected reboot timestamp:
Record Id: 4626
When: YYYY-MM-DDTHH:MM:SS
Event Type: 4 (Minor)
SEL Type: 2 (System Event)
Message: Assert + Processor Predictive Failure Asserted
Sensor Number: 80

Environment

VMware vSphere ESXi 8.x

Cause

The ungraceful host reboot is caused by a physical hardware component failure—specifically, a Processor (CPU) Predictive Failure or motherboard fault that triggers a hardware-level self-preservation power reset at the BMC/IPMI layer.
When a CPU or motherboard experiences an unrecoverable hardware fault or threshold breach, the System Management Controller (e.g., Cisco CIMC / BMC) cuts power or hard-resets the server instantly to protect the components from physical damage. Because power is abruptly cut at the electrical level, ESXi cannot generate a software crash dump (PSOD) and logs poweroff.reason.unavailable upon the subsequent system boot.

Resolution

Step 1: Isolate the Host (Prevent VM Corruption)
Immediately migrate all virtual machines off the affected host using vMotion.

Place the affected ESXi host into Maintenance Mode in vCenter.

Step 2: Collect Support Logs
Generate and download the full System Logs / Tech Support Bundle from the hardware vendor interface.

Step 3: Engage Hardware Vendor
Provide the IPMI SEL log entries (specifically Sensor / CPU Processor Predictive Failure records) to OEM Hardware Vendor.

Request diagnostic testing and physical component replacement (e.g., CPU, CPU Socket, or Motherboard replacement).