Re: rcu_preempt detected stalls [5.9.1-rt]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 2021-01-31 10:13:30 [+0100], Udo van den Heuvel wrote:
> Hello,
Hi,

> Found these loggings in journal, what happened here?

09:20:24 RCU stalled on CPU0. 
09:21:08 Networking was not able to send packets.

The RCU part indicates that something is blocking the CPU. The network
part might be related (it is not bound to a CPU but if the IRQ-thread is
blocked then packets won't be sent/acked).

09:21:19 systemd's watchdog killed tor because it was not responding.

Most of tor's threads were waiting in pthread_cond_wait().
One thread was in getsockopt(sock, SOL_TCP, TCP_INFO, ,,). This could
block/sleep in lock_sock_fast() but shouldn't since all threads were
idle. Unless a packet would be received at that time. tor does not
changes its priority so everything should run at SCHED_OTHER.

tor got killed in the end and you did not attach any more rcu warnings
so it appears that CPU0 is no longer blocked. I don't know what blocked
the CPU for the time.

> Kind regards,
> Udo

Sebastian



[Index of Archives]     [RT Stable]     [Kernel Newbies]     [IDE]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux ATA RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]

  Powered by Linux