Four kacpi_notify kernel threads are continuously using CPU, makes the laptop warm, fans run continuosly. This is a Fedora debug kernel, it's not intended for production. But I'm wondering if this performance hit is expected and if it's worth it (for kernel developers). PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 19429 root 20 0 0 0 0 D 26.5 0.0 3:01.99 kworker/4:3+kacpi_notify 21018 root 20 0 0 0 0 R 26.1 0.0 2:59.99 kworker/4:4+kacpi_notify 19753 root 20 0 0 0 0 R 24.5 0.0 3:28.92 kworker/4:0+kacpi_notify 21919 root 20 0 0 0 0 D 21.9 0.0 1:06.62 kworker/4:1+kacpi_notify 21206 root 20 0 38052 8192 3312 R 3.6 0.1 0:38.19 (udev-worker) A possible hint is in dmesg [ 874.399128] kernel: workqueue: acpi_os_execute_deferred hogged CPU for >13333us 1027 times, consider switching to WQ_UNBOUND [ 960.050165] kernel: workqueue: delayed_fput hogged CPU for >13333us 259 times, consider switching to WQ_UNBOUND [ 1678.780253] kernel: workqueue: acpi_ec_event_processor hogged CPU for >13333us 35 times, consider switching to WQ_UNBOUND Full dmesg and kernel config attached to the downstream bug report: https://bugzilla.redhat.com/show_bug.cgi?id=2351405 Thanks, -- Chris Murphy
