Windows stops with MEMORY MANAGEMENT code on low latency storage

Environment

• OpenShift Container Platform 4.20
  • OpenShift Virtualization 4.20
• Red Hat Enterprise Linux 9.6
  • qemu-kvm-9.1.0-15.el9_6.18.x86_64
• Microsoft Windows Guest
  • virtio-win-1.9.50-0.el9_6

Issue

• Windows Virtual Machines BSOD with "MEMORY MANAGEMENT" code (0x1A).
• There is no storage latency present at the time, its not Windows stops with MEMORY MANAGEMENT code.
• Increasing or decreating the IoTimeoutValue makes no difference.

Resolution

• Please upgrade the Guest drivers to virtio-win-1.9.53-0.el9_6 or later. This was fixed by RHBA-2026:2280.
• As a workaround, in In RHEL KVM, disable multiqueue in the domain XML by adding queues='1' to each virtio-blk disk:

    <disk type='block' device='disk' model='virtio-non-transitional'>
      <driver [...] queues='1'/>
      [...]
    </disk>

Root Cause

• This is was investigated in This content is not included.RHEL-141510"MEMORY MANAGEMENT" BSOD with no storage delay and only on virtio-blk.
• There is a problem affecting virtio-blk with Multiqueue, causing the BSOD.
• Similar problems exists on virtio-scsi, but its more rare.

Diagnostic Steps

• Monitoring shows very low latency on the storage devices of the VM disks prior and at the time of the BSOD.
• No Event 129 in Windows Guest Event Logs.

This solution is part of Red Hat’s fast-track publication program, providing a huge library of solutions that Red Hat engineers have created while supporting our customers. To give you the knowledge you need the instant it becomes available, these articles may be presented in a raw and unedited form.