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

Re: [Xen-users] Stall on CPU



Hi,

I've also seen that "rcu sched detected stalls on CPU x", but on dom0, not domU.
The dom0 which had this error (leading to a complete system stop) is running xen 4.1.3
and vanilla 3.5.2 as dom0 kernel.
I know, I should go with the xenified kernels, but I'm currently evaluating tmem features on recent
kernels.

Another machine which hit that "rcu sched" was a baremetal 3.1.1 acting as scst target.

I've got the feeling the error can be triggered by heavy I/O, but to be honest, I don't have
any glue what to do against it.


Cheers,

- Stephan




Am Sonntag, den 09.09.2012, 23:27 +0100 schrieb Ian:
Hi,

I have been receiving messages on a new DomU's kern.log. I've done a lot 
of googling, but haven't came up with anything very useful, at least not 
in a Xen context.

I was wondering if anyone had any suggestions about what could be wrong. 
From everything I have read, there should be a stack trace included, but 
I am not seeing one.

Thanks in advance,

Ian.

on Xen 4.1.2...
Sep  6 13:04:07 davical kernel: [12008.080091] INFO: rcu_sched detected 
stall on CPU 1 (t=50460 jiffies)
Sep  6 13:04:07 davical kernel: [12008.084081] sending NMI to all CPUs:
Sep  6 13:04:07 davical kernel: [11806.576064] INFO: rcu_sched detected 
stalls on CPUs/tasks: { 1} (detected by 0, t=566314 jiffies)
Sep  6 13:04:07 davical kernel: [75644.150936] INFO: rcu_sched detected 
stall on  CPU 0 (t=15393163 jiffies)
Sep  6 13:04:07 davical kernel: [75644.304186] sched: RT throttling 
activated

on Xen 4.1.3...
Sep  8 11:39:40 davical kernel: [62220.039363] INFO: rcu_sched detected 
stall on CPU 1 (t=355732 jiffies)
Sep  8 11:39:40 davical kernel: [62220.039363] sending NMI to all CPUs:
Sep  8 11:39:40 davical kernel: [124714.197152] INFO: rcu_sched detected 
stalls on CPUs/tasks: { 1} (detected by 0, t=355732 jiffies)
Sep  8 11:39:48 davical kernel: [124721.756263] INFO: rcu_sched detected 
stall on CPU 1 (t=15751455 jiffies)
Sep  8 11:39:48 davical kernel: [124721.756328] sending NMI to all CPUs:
Sep  8 11:39:48 davical kernel: [124721.760199] INFO: rcu_sched detected 
stalls on CPUs/tasks: { 1} (detected by 0, t=15751455 jiffies)
Sep  8 11:39:52 davical kernel: [124725.855952] ipv6_create_tempaddr(): 
retry temporary address regeneration.
Sep  8 11:40:08 davical kernel: [124721.760226] INFO: rcu_bh detected 
stall on CPU 1 (t=15395723 jiffies)
Sep  8 11:40:08 davical kernel: [124721.760226] sending NMI to all CPUs:
Sep  8 11:40:08 davical kernel: [124742.485888] sched: RT throttling 
activated



I have tried it on two Xen Dom0 installations, one of 4.1.2 and the 
other on 4.1.3.

The 4.1.2 Dom0 machine is a scientific linux installation using a custom 
compiled kernel, 3.4.0+.

The 4.1.3 Dom0 machine is using a standard Ubuntu server kernel 
3.2.0-29-generic-pae

The domU is an Ubuntu 12.04.1 server based using a standard Ubuntu 
12.04.1 kernel, also 3.2.0-29-generic-pae.

xl info of the 4.1.2 machine:

host                   : xen3
release                : 3.4.0+
version                : #1 SMP Mon Jun 4 12:41:14 BST 2012
machine                : x86_64
nr_cpus                : 4
nr_nodes               : 1
cores_per_socket       : 4
threads_per_core       : 1
cpu_mhz                : 2300
hw_caps                : 
178bf3ff:efd3fbff:00000000:00001310:00802001:00000000:000007ff:00000000
virt_caps              : hvm
total_memory           : 8159
free_memory            : 3866
free_cpus              : 0
xen_major              : 4
xen_minor              : 1
xen_extra              : .2
xen_caps               : xen-3.0-x86_64 xen-3.0-x86_32p hvm-3.0-x86_32 
hvm-3.0-x86_32p hvm-3.0-x86_64
xen_scheduler          : credit
xen_pagesize           : 4096
platform_params        : virt_start=0xffff800000000000
xen_changeset          : unavailable
xen_commandline        : loglvl=all guesloglvl=all
cc_compiler            : gcc version 4.4.5 20110214 (Red Hat 4.4.5-6) (GCC)
cc_compile_by          : root
cc_compile_domain      : (none)
cc_compile_date        : Sun Jan 22 01:18:42 GMT 2012
xend_config_format     : 4


xl info of the 4.1.3 machine:

host                   : xen5
release                : 3.2.0-29-generic-pae
version                : #46-Ubuntu SMP Fri Jul 27 17:25:43 UTC 2012
machine                : i686
nr_cpus                : 2
nr_nodes               : 1
cores_per_socket       : 2
threads_per_core       : 1
cpu_mhz                : 1995
hw_caps                : 
bfe9fbff:00100000:00000000:00000940:0000c1a9:00000000:00000000:00000000
virt_caps              :
total_memory           : 3062
free_memory            : 173
free_cpus              : 0
xen_major              : 4
xen_minor              : 1
xen_extra              : .3
xen_caps               : xen-3.0-x86_32p
xen_scheduler          : credit
xen_pagesize           : 4096
platform_params        : virt_start=0xf5800000
xen_changeset          : unavailable
xen_commandline        : placeholder
cc_compiler            : gcc version 4.6.3 (Ubuntu/Linaro 4.6.3-1ubuntu5)
cc_compile_by          : root
cc_compile_domain      : local
cc_compile_date        : Thu Sep  6 01:53:48 BST 2012
xend_config_format     : 4

DomU config file:

cat ubuntu-calendar
name      = "ubuntu-calendar"
memory    = 1024
disk      = ['phy:/dev/xen5/ubuntu-calendar,xvda,w']
vif = [ 'mac=00:16:31:50:01:03' ]
bootloader="/usr/bin/pygrub"
vfb = [ "type=vnc,vncunused=1,vnclisten=0.0.0.0" ]
vcpus     = 2



DomU's grub.lst....

menuentry 'Ubuntu, with Linux 3.2.0-29-generic' --class ubuntu --class 
gnu-linux
  --class gnu --class os {
         recordfail
         insmod ext2
         set root='(hd0,1)'
         search --no-floppy --fs-uuid --set=root 
70149f72-3c4f-4608-bebd-06825b91
ce29
         linux   /boot/vmlinuz-3.2.0-29-generic-pae 
root=UUID=70149f72-3c4f-4608-
bebd-06825b91ce29 ro   quiet splash set default="0"
set timeout=5
menuentry 'Ubuntu GNU/Linux, with Xen 4.1-amd64 and Linux 
3.2.0-23-generic' --class ubuntu --class gnu-linux --class gnu --class 
os --class xen {
     insmod part_msdos
     insmod ext2
     set root='(hd0,msdos1)'
     search --no-floppy --fs-uuid --set=root 
1b478986-8c02-4a79-ad61-cf8f418e35ad
     echo    'Loading Xen 4.1-amd64 ...'
     multiboot    /xen.gz placeholder
     echo    'Loading Linux 3.2.0-29-generic-pae ...'
     module    /vmlinuz-3.2.0-29-generic-pae placeholder 
root=/dev/mapper/xen5-root ro
     echo    'Loading initial ramdisk ...'
     module    /initrd.img-3.2.0-29-generic-pae
}
xen-fbfront.video=16,1024,768 $vt_handoff
         initrd  /boot/initrd.img-3.2.0-29-generic-pae


Dom0's grub.lst (4.1.3)...

set default="0"
set timeout=5
menuentry 'Ubuntu GNU/Linux, with Xen 4.1-amd64 and Linux 
3.2.0-23-generic' --class ubuntu --class gnu-linux --class gnu --class 
os --class xen {
     insmod part_msdos
     insmod ext2
     set root='(hd0,msdos1)'
     search --no-floppy --fs-uuid --set=root 
1b478986-8c02-4a79-ad61-cf8f418e35ad
     echo    'Loading Xen 4.1-amd64 ...'
     multiboot    /xen.gz placeholder
     echo    'Loading Linux 3.2.0-29-generic-pae ...'
     module    /vmlinuz-3.2.0-29-generic-pae placeholder 
root=/dev/mapper/xen5-root ro
     echo    'Loading initial ramdisk ...'
     module    /initrd.img-3.2.0-29-generic-pae
}









_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxx
http://lists.xen.org/xen-users

Attachment: signature.asc
Description: This is a digitally signed message part

_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxx
http://lists.xen.org/xen-users

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.