On Sun, 2018-01-21 at 12:39 -0500, David Zarzycki wrote: > Hi Bart, > > I can do [1] and [2] but I won’t be able to provide the command output > because the hang is almost total. No new commands can run because the > scheduler is hung. For example, see this backtrace: > > http://znu.io/IMG_0362.jpg > > Is there another approach I can use? Hello Dave, What I proposed is an approach to find the cause of a block layer queue that got stuck due to a missing queue run. However, the screenshot that you shared in your e-mail shows that something else is going on. If the message "rcu_sched detected stalls" then that means that something prevented the RCU code to be scheduled, e.g. because interrupts occur at a frequency that is so high that the RCU code doesn't get a chance to run. For more information, see also https://www.kernel.org/doc/Documentation/RCU/stallwarn.txt. I think you will need the help of an NVMe expert to analyze this further. If you would not be aware of this, there is a mailing list that is dedicated to NVMe. See also https://lists.infradead.org/mailman/listinfo/linux-nvme. Bart.
