Hi Viktor, thanks, that's a plausible explanation and it matches the random corruption pattern. Could you point me to the upstream commits (or the lore.kernel.org thread) for that TDP MMU invalidation rework? Krystian may want to reference them in the Launchpad bug, since other noble 6.8 users running KVM could be affected.
One thing I can't fully square: our Intel hosts (Xeon E5520/E5530/X5670) run the same Ubuntu 6.8.0-137 KVM and have been stable for 56 days. Do you think that's just the lighter load (5-6 VMs vs 14-20 on the AMD hosts), or is there something AMD/NPT-specific in that race? We're proceeding with HWE 7.0 on all AMD hosts. Thanks, Radovan -- 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
