On 9/6/20 10:34 pm, Patrick O'Callaghan wrote:
On Tue, 2020-06-09 at 22:10 +1000, Stephen Morris wrote:
Hi,
I have the following messages in dmesg output, are they indicating
a cpu issue, or are they just indicating that because linux is running
in a vm under windows, and hence sharing the cpu cores with windows that
windows was using core 7 at the time the process checked?
[16236.896502] rcu: INFO: rcu_sched detected stalls on CPUs/tasks:
[16236.896506] rcu: 7-...!: (0 ticks this GP) idle=d48/0/0x0
softirq=207101/207101 fqs=0
[16236.896508] (detected by 4, t=60008 jiffies, g=263697, q=1058)
[16236.896510] Sending NMI from CPU 4 to CPUs 7:
[16236.896563] NMI backtrace for cpu 7 skipped: idling at
native_safe_halt+0xe/0x10
[16236.897522] rcu: rcu_sched kthread starved for 60008 jiffies! g263697
f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 ->cpu=7
[16236.897522] rcu: RCU grace-period kthread stack dump:
[16236.897524] rcu_sched I 0 11 2 0x80004000
[16236.897526] Call Trace:
[16236.897532] __schedule+0x26f/0x760
[16236.897535] schedule+0x4a/0xb0
[16236.897536] schedule_timeout+0x7b/0x140
[16236.897539] ? __next_timer_interrupt+0xd0/0xd0
[16236.897541] rcu_gp_kthread+0x4db/0xa90
[16236.897543] ? rcu_nocb_cb_kthread+0x210/0x210
[16236.897545] kthread+0x115/0x140
[16236.897547] ? __kthread_bind_mask+0x60/0x60
[16236.897549] ret_from_fork+0x22/0x40
Surely a VM would see only virtual cores and not be aware of the host.
However this is running on Windows, so who knows. You might want to
mention which VM it is (VirtualBox, VMware, Microsoft's, ...)
Thanks Patrick, I'm using VirtualBox now, I was using Vmware Player, but
I switched to VirtualBox because VirtualBox supports uefi where as
Vmware doesn't. I was just wondering whether because the VM is sharing
the cpu cores with windows, because it is running under windows, could
the issue be that windows itself was using Core 7 and hence rcu couldn't
get to it at the time it checked?
regards,
Steve
poc
_______________________________________________
users mailing list -- users@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to users-leave@xxxxxxxxxxxxxxxxxxxxxxx
Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/
List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines
List Archives: https://lists.fedoraproject.org/archives/list/users@xxxxxxxxxxxxxxxxxxxxxxx
_______________________________________________
users mailing list -- users@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to users-leave@xxxxxxxxxxxxxxxxxxxxxxx
Fedora Code of Conduct: https://docs.fedoraproject.org/en-US/project/code-of-conduct/
List Guidelines: https://fedoraproject.org/wiki/Mailing_list_guidelines
List Archives: https://lists.fedoraproject.org/archives/list/users@xxxxxxxxxxxxxxxxxxxxxxx
