Also having this issue, after about 4 days of uptime the network adapter seems to have delays introduced, so pinging other systems on our external interface gets wildly swinging ping times. It does not appear on our internal network which is strange because it's the same model of network card. A reboot seems to fix it for a few days.
This is on a Dell T630 with all firmware up to date. Ubuntu 24.04 kernel 6.8.0-44-generic [356601.173313] workqueue: psi_avgs_work hogged CPU for >10000us 2048 times, consider switching to WQ_UNBOUND [358332.263215] workqueue: process_srcu hogged CPU for >10000us 16 times, consider switching to WQ_UNBOUND [358997.675712] workqueue: kfree_rcu_work hogged CPU for >10000us 128 times, consider switching to WQ_UNBOUND root@nike:~# ping www.google.com PING www.google.com (142.250.189.196) 56(84) bytes of data. 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=1 ttl=119 time=1.25 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=2 ttl=119 time=1.17 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=3 ttl=119 time=51.3 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=4 ttl=119 time=11.3 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=5 ttl=119 time=1.18 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=7 ttl=119 time=105 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=8 ttl=119 time=85.4 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=9 ttl=119 time=1.24 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=10 ttl=119 time=6.30 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=11 ttl=119 time=2.14 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=12 ttl=119 time=1.28 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=13 ttl=119 time=39.3 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=14 ttl=119 time=45.8 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=15 ttl=119 time=1.20 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=16 ttl=119 time=47.6 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=17 ttl=119 time=37.1 ms 64 bytes from sfo03s25-in-f4.1e100.net (142.250.189.196): icmp_seq=18 ttl=119 time=12.2 ms -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/2038492 Title: workqueue: inode_switch_wbs_work_fn hogged CPU for >10000us 16 times, consider switching to WQ_UNBOUND To manage notifications about this bug go to: https://bugs.launchpad.net/ubuntu/+source/linux-oem-6.5/+bug/2038492/+subscriptions -- ubuntu-bugs mailing list [email protected] https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
