Tested 7.0.0-1023-nvidia (7.0.0-1023.24~24.04.1) on a Vera system. The tests exercised CPU contention between busy tasks and heartbeat tasks, frequent changes to cgroup CPU weights, nested cgroups with 128 runnable tasks, and periodic wakeups under load. Trace-buffer resizing also checked kernel-worker progress.
Tests completed successfully: - All heartbeats continued receiving runtime; no zero-runtime intervals. - Trace-buffer resizing completed in approximately 0.05–0.06 seconds under load. - Maximum periodic-wakeup lateness was 1.4 ms. - No scheduler stalls, workqueue lockups, or hung-task reports. ** Tags removed: verification-needed-noble-linux-nvidia-7.0 ** Tags added: verification-done-noble-linux-nvidia-7.0 -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/2170798 Title: sched/fair: Prevent runnable tasks from starving during cgroup reweighting To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux-nvidia/+bug/2170798/+subscriptions -- ubuntu-bugs mailing list [email protected] https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
