The AMD-Vi: IO_PAGE_FAULT right before the panic suggests a DMA translation error that corrupted memory, which broke the rt_mutex priority chain. This looks like an IOMMU/hardware issue rather than the migrate_swap stopper deadlock.
IMHO, moving srv06 to HWE 7.0 was the right call for prod. stability. Having srv04 at 12+ days and the other hosts past 10 days is a good sign that the scheduler fixes work. -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/2163642 Title: Kernel panic "Attempted to kill the idle task" on AMD Opteron multi- node NUMA under KVM (6.8.0-137) To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2163642/+subscriptions -- ubuntu-bugs mailing list [email protected] https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
