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

[Xen-users] Nested Xen Boot problem over 8 cpu



Greetings All

I have the following problem:
I am running ESXI 5.1, inside of that I have created a centos 6 machine then put the 4.4.0 xen kernel in it. On boot if the VM has more than 8 cpu's on it the VM gets hung during the boot process after printing the following:
cpu X spinlock event irq Y
Disabled fast string operations
Installing Xen timer for CPU X
Brought up all 16 CPUs

Is anyone aware of a fix or a configuration option that needs to be set that would cause dom0/xen to fail on boot in this situation? If I set the vm's cpu count to 8 or less it works fine with the exact same grub. This seems unrelated to the way the cores are distributed, I have tried I socket with 16 cores, 4 sockets with 4 cores each, as well as 16 sockets with 1 core each.

Due to the nature of the project I can't change the version but I could patch the kernel if that is what is required. Any help would be greatly appreciated.

Including my grub call in case it has something to do with the way I am booting.

    kernel /xen-4.4.0.gz loglvl=all guest_loglvl=all dom0_mem=8704M bootscrub=false dom0_max_vcpus=4 dom0_vcpus_pin=true com1=115200 console=com1,vga
    root (hd0,0)
    module /vmlinuz-3.10.45-xen ro root=/dev/mapper/vg_ga-lv_ra rd_NO_LUKS rd_LVM_LV=vg_ga/lv_ra LANG=en_US.UTF-8 rd_LVM_LV=vg_ga/lv_swap rd_NO_MD SYSFONT=latarcyrheb-sun16 KEYBOARDTYPE=pc KEYTABLE=us rd_NO_DM BOOT_OPTION=disk-A OS_TYPE=Xen earlyprintk=xen nomodeset console=tty1 console=hvc0
    module Â/initramfs-3.10.45-xen.img
_______________________________________________
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®.