Hello List, I am testing a XCP1 CentOS 5 paravirt vm with CloudLinux. http://cloudlinux.com/ CloudLinux is a great product for shared hosting and I was evaluation same on a paravirt guest. I found a strange thing in XCP. CloudLinux provides xen kernel for DomUs and after installing the CloudLinux in a DomU it actually got 32 cpus inside. I had assigned only 2 vCPU to that DomU. To confirm this I started generating load on that DomU and in no time it ate all my node''s CPUs. Is it an expected behavior that one of your DomU can eat all node with few modifications in kernel ? Or is Paravirt not a Hardware Virtualized guest ? Regards, R J _______________________________________________ xen-api mailing list xen-api@lists.xensource.com http://lists.xensource.com/mailman/listinfo/xen-api
On Mon, 24 Oct 2011, R J wrote:> I found a strange thing in XCP. CloudLinux provides xen kernel for DomUs and > after installing the CloudLinux in a DomU it actually got 32 cpus inside. > I had assigned only 2 vCPU to that DomU. To confirm this I started > generating load on that DomU and in no time it ate all my node''s CPUs.How many physical CPUs do you have installed and how did you verify how many VCPUs your domU was allocated? What does /proc/cpuinfo contain?> Is it an expected behavior that one of your DomU can eat all node with few > modifications in kernel ? > Or is Paravirt not a Hardware Virtualized guest ?You might want to take a look at the docs that describe how the Credit Scheduler used in Xen works: http://wiki.xen.org/xenwiki/CreditScheduler _______________________________________________ xen-api mailing list xen-api@lists.xensource.com http://lists.xensource.com/mailman/listinfo/xen-api
Hi Brooks, Thanks for the reply. I have X5650 node with 24 CPUs. This is Dual Socket Hexacore machine. I used XenCenter to monitor the node and it showed 2 vCPUs for that DomU. I rechecked it with vm-param-list, it showed 2. When I checked /proc/cpuinfo in DomU, it shows 32. Regards, R J On Mon, Oct 24, 2011 at 9:57 PM, <brooks@netgate.net> wrote:> > On Mon, 24 Oct 2011, R J wrote: > > I found a strange thing in XCP. CloudLinux provides xen kernel for DomUs >> and >> after installing the CloudLinux in a DomU it actually got 32 cpus inside. >> I had assigned only 2 vCPU to that DomU. To confirm this I started >> generating load on that DomU and in no time it ate all my node''s CPUs. >> > > How many physical CPUs do you have installed and how did you verify how > many VCPUs your domU was allocated? What does /proc/cpuinfo contain? > > > Is it an expected behavior that one of your DomU can eat all node with few >> modifications in kernel ? >> Or is Paravirt not a Hardware Virtualized guest ? >> > > You might want to take a look at the docs that describe how the Credit > Scheduler used in Xen works: > > http://wiki.xen.org/xenwiki/**CreditScheduler<http://wiki.xen.org/xenwiki/CreditScheduler> >_______________________________________________ xen-api mailing list xen-api@lists.xensource.com http://lists.xensource.com/mailman/listinfo/xen-api
On Mon, 24 Oct 2011, R J wrote:> Hi Brooks, > > Thanks for the reply. > I have X5650 node with 24 CPUs. This is Dual Socket Hexacore machine. > > I used XenCenter to monitor the node and it showed 2 vCPUs for that DomU. I > rechecked it with vm-param-list, it showed 2. > When I checked /proc/cpuinfo in DomU, it shows 32.That''s (very) strange. I have a similar environment set up and running with CloudLinux 5 under XenServer 5.5 and all of the CPU/VCPU mapping is working as expected. I''m currently testing XCP 1.1 but have yet to bring up a CL VM on it. Are you using CL 5 or CL 6, and is this XCP 1.0 or 1.1? Did you happen to check /proc/cpuinfo before applying the CL RPMs? _______________________________________________ xen-api mailing list xen-api@lists.xensource.com http://lists.xensource.com/mailman/listinfo/xen-api
Yes its strange.
I have XCP1 with following version of CloudLinux Kernel.
Please see if the same issue replicates at your environment.
[root@centos ~]# cat /etc/grub.conf
# grub.conf generated by anaconda
#
# Note that you do not have to rerun grub after making changes to this file
# NOTICE: You have a /boot partition. This means that
# all kernel and initrd paths are relative to /boot/, eg.
# root (hd0,0)
# kernel /vmlinuz-version ro root=/dev/xvda3
# initrd /initrd-version.img
#boot=/dev/xvda
default=1
timeout=5
splashimage=(hd0,0)/grub/splash.xpm.gz
hiddenmenu
title CloudLinux Server (2.6.18-374.3.1.el5.lve0.8.44xen)
root (hd0,0)
kernel /vmlinuz-2.6.18-374.3.1.el5.lve0.8.44xen ro root=LABEL=/
console=xvc0
initrd /initrd-2.6.18-374.3.1.el5.lve0.8.44xen.img
title CentOS (2.6.18-194.el5xen)
root (hd0,0)
kernel /vmlinuz-2.6.18-194.el5xen ro root=LABEL=/ console=xvc0
initrd /initrd-2.6.18-194.el5xen.img
I''m using CloudLinux 5 on XCP1 and not 1.1
On default xen kernel it boots and runs fine on allocated vCPUs but
2.6.18-374.3.1.el5.lve0.8.44xen kernel is making things strange.
Regards,
R J
On Mon, Oct 24, 2011 at 10:34 PM, <brooks@netgate.net> wrote:
>
> On Mon, 24 Oct 2011, R J wrote:
>
> Hi Brooks,
>>
>> Thanks for the reply.
>> I have X5650 node with 24 CPUs. This is Dual Socket Hexacore machine.
>>
>> I used XenCenter to monitor the node and it showed 2 vCPUs for that
DomU.
>> I
>> rechecked it with vm-param-list, it showed 2.
>> When I checked /proc/cpuinfo in DomU, it shows 32.
>>
>
> That''s (very) strange. I have a similar environment set up and
running
> with CloudLinux 5 under XenServer 5.5 and all of the CPU/VCPU mapping is
> working as expected. I''m currently testing XCP 1.1 but have yet
to bring up
> a CL VM on it. Are you using CL 5 or CL 6, and is this XCP 1.0 or 1.1?
> Did you happen to check /proc/cpuinfo before applying the CL RPMs?
>
_______________________________________________
xen-api mailing list
xen-api@lists.xensource.com
http://lists.xensource.com/mailman/listinfo/xen-api
I try to get that installed today and let you know what I find. In the mean time you should shoot Igor (at CL) an email and see what he thinks. On Mon, 24 Oct 2011, R J wrote:> Yes its strange. > > I have XCP1 with following version of CloudLinux Kernel. > Please see if the same issue replicates at your environment. > > [root@centos ~]# cat /etc/grub.conf > # grub.conf generated by anaconda > # > # Note that you do not have to rerun grub after making changes to this file > # NOTICE: You have a /boot partition. This means that > # all kernel and initrd paths are relative to /boot/, eg. > # root (hd0,0) > # kernel /vmlinuz-version ro root=/dev/xvda3 > # initrd /initrd-version.img > #boot=/dev/xvda > default=1 > timeout=5 > splashimage=(hd0,0)/grub/splash.xpm.gz > hiddenmenu > title CloudLinux Server (2.6.18-374.3.1.el5.lve0.8.44xen) > root (hd0,0) > kernel /vmlinuz-2.6.18-374.3.1.el5.lve0.8.44xen ro root=LABEL=/ > console=xvc0 > initrd /initrd-2.6.18-374.3.1.el5.lve0.8.44xen.img > title CentOS (2.6.18-194.el5xen) > root (hd0,0) > kernel /vmlinuz-2.6.18-194.el5xen ro root=LABEL=/ console=xvc0 > initrd /initrd-2.6.18-194.el5xen.img > > > I''m using CloudLinux 5 on XCP1 and not 1.1 > On default xen kernel it boots and runs fine on allocated vCPUs but > 2.6.18-374.3.1.el5.lve0.8.44xen kernel is making things strange._______________________________________________ xen-api mailing list xen-api@lists.xensource.com http://lists.xensource.com/mailman/listinfo/xen-api