Poor LVM performance.

Hi, I have been doing some testing with KVM and Virtuozzo(containers based virtualisation) and various storage devices and have some results I would like some help analyzing. I have a nice big ZFS box from Oracle (Yes, evil but Solaris NFS is amazing). I have 10G and IB connecting these to

I/O scheduling on block devices

Hello, I have a iSCSI storage array connected to 4 physical hosts. On these 4 hosts I have configured 40 odd logical volumes with clvm. each logical volume is the root volume for a VM. How should I set up io scheduling with this configuration. Performance is not so great and I have a feeling

NFS mount options

Hello, I have been using NFS with kvm for a little while and have been wondering about appropriate NFS mount options. Could someone please explain to me what mount options should be used and why? Also, what are the differences between NFSv3 and NFSv4 in regards to KVM? Thanks, Andrew -- To

Re: Process blocked for more than 120 seconds.

Hi, No the NFS is not hung and yes I can access the image on the host. Its just seems to happen occasionally with some VMs.. Thanks, Andrew On Dec 11, 2012, at 11:59 AM, Stefan Hajnoczi wrote: On Fri, Dec 7, 2012 at 1:09 PM, Andrew Holway a.hol...@syseleven.de wrote: -drivefile=/rhev/data

Process blocked for more than 120 seconds.

Hello, I have been using rhev 3.1 and created a few VMs. I have provisioning system that boots machines via pxe with centos 6.3 images. It creates the following: /dev/vda1 on / type ext3 (rw,noatime,nodiratime) /dev/vda6 on /local type ext3 (rw,noatime,nodiratime) /dev/vda3 on /tmp type ext3

Re: Process blocked for more than 120 seconds.

sorry. I forgot to mention that my images are being created on a Solaris based NFS / ZFS server. Thanks, Andrew On Dec 7, 2012, at 1:09 PM, Andrew Holway wrote: Hello, I have been using rhev 3.1 and created a few VMs. I have provisioning system that boots machines via pxe with centos

KVM on NFS

Hello, I am testing KVM on an Oracle NFS box that I have. Does the list have any advice on best practice? I remember reading that there is stuff you can do with I/O schedulers and stuff to make it more efficient. My VMs will primarily be running mysql databases. I am currently using o_direct.

Re: KVM on NFS

O_DIRECT is good. I/O schedulers don't affect NFS so no need to tune anything on the host. You might experiment with switching to the deadline scheduler in the guest. Ill give it a go. Any ideas how I should be tuning my NFS? -- error compiling committee.c: too many arguments to

Re: NFS over RDMA small block DIRECT_IO bug

Hi Steve, Do you think these patches will make their way into the redhat kernel sometime soon? What is the state of support for NFS over RDMA support at redhat? Thanks, Andrew On Sep 11, 2012, at 7:03 PM, Steve Dickson wrote: On 09/04/2012 05:31 AM, Andrew Holway wrote: Hello

Re: NFS over RDMA small block DIRECT_IO bug

On Sep 5, 2012, at 4:02 PM, Avi Kivity wrote: On 09/04/2012 03:04 PM, Myklebust, Trond wrote: On Tue, 2012-09-04 at 11:31 +0200, Andrew Holway wrote: Hello. # Avi Kivity avi(a)redhat recommended I copy kvm in on this. It would also seem relevent to libvirt. # I have a Centos 6.2

NFS over RDMA small block DIRECT_IO bug

Hello. # Avi Kivity avi(a)redhat recommended I copy kvm in on this. It would also seem relevent to libvirt. # I have a Centos 6.2 server and Centos 6.2 client. [root@store ~]# cat /etc/exports /dev/shm 10.149.0.0/16(rw,fsid=1,no_root_squash,insecure)(I have

Re: NFS over RDMA small block DIRECT_IO bug

That is expected behaviour. DIRECT_IO over RDMA needs to be page aligned so that it can use the more efficient RDMA READ and RDMA WRITE memory semantics (instead of the SEND/RECEIVE channel semantics). Yes, I think I am understanding that now. I need to find a way of getting around the

Re: NFSoRDMA not working with KVM when cache disabled

and report which (if any) of the output files (x1, x2, y1, y2) are corrupted, by comparing them against the original. This will tell us whether O_DIRECT is broken, or 512 byte block size, or neither. Looks like you were directly on the money there. 512, 1K and 2K O_DIRECT looks broken.

Re: [Bright Cluster Manager Support #2699] NFSoRDMA not working with KVM when cache disabled

tried doing a FULL install? Best regards, Martijn On Fri, Aug 31, 2012 at 7:06 PM, Andrew Holway supp...@brightcomputing.comwrote: Fri Aug 31 19:06:00 2012: Request 2699 was acted upon. Transaction: Ticket created by a.hol...@syseleven.de Queue: Bright Subject: NFSoRDMA

virtIO disks not usable

Hi, I am creating a VM with the following command: virt-install --connect qemu:///system -n vm001 -r 2048 --vcpus=2 --disk path=/local/vm001.img,device=disk,bus=virtio,size=45 --vnc --noautoconsole --os-type linux --accelerate --network=bridge:br0,mac=00:00:00:00:00:0E

Re: [libvirt-users] vm pxe fail

pxelinux.cfg' to show your pxelinux configuration, thanks. -- Regards, Alex - Original Message - From: Andrew Holway a.hol...@syseleven.de To: kvm@vger.kernel.org Sent: Thursday, August 16, 2012 8:25:35 PM Subject: [libvirt-users] vm pxe fail Hallo I have a kvm vm that I am

Re: virtIO disks not usable

Stupid boy. I didnt have the virtIO modules loaded. On Aug 31, 2012, at 3:19 PM, Andrew Holway wrote: Hi, I am creating a VM with the following command: virt-install --connect qemu:///system -n vm001 -r 2048 --vcpus=2 --disk path=/local/vm001.img,device=disk,bus=virtio,size=45 --vnc

NFSoRDMA not working with KVM when cache disabled

Hi, I am trying to host KVM machines on an NFSoRDMA mount. This works: -drive file=/mnt/vm001.img,if=none,id=drive-virtio-disk0,format=raw -device virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,id=virtio-disk0 This Doesn't! -drive

Re: NFSoRDMA not working with KVM when cache disabled

82 Linux swap / Solaris /dev/vda68000716894371839 7182336 83 LinuxOn Aug 31, 2012, at 7:05 PM, Andrew Holway wrote: Hi, I am trying to host KVM machines on an NFSoRDMA mount. This works: -drive file=/mnt/vm001.img,if=none,id=drive-virtio-disk0,format=raw -device

Getting VLANS to the vm ping / UDP working but TCP not

Hi, I am trying out a couple of methods to get VLANs to the VM. In both cases the VM can ping google et all without problem and DNS works fine but it does not want to do any TCP. I thought this might be a frame size problem but even using telnet (which I understand sends tiny packets) fails to

Re: [libvirt-users] vm pxe fail

Message - From: Andrew Holway a.hol...@syseleven.de To: kvm@vger.kernel.org Sent: Thursday, August 16, 2012 8:25:35 PM Subject: [libvirt-users] vm pxe fail Hallo I have a kvm vm that I am attempting to boot from pxe. The dhcp works perfectly and I can see the VM in the pxe server arp

Re: [libvirt-users] vm pxe fail

Hostname Option 12, length 17: vm001.internalnet Domain-Name Option 15, length 65: eth.cluster brightcomputing.com ib.cluster ilo.cluster cm.cluster -- Regards, Alex - Original Message - From: Andrew Holway a.hol...@syseleven.de To: kvm@vger.kernel.org

vm pxe fail

Hallo I have a kvm vm that I am attempting to boot from pxe. The dhcp works perfectly and I can see the VM in the pxe server arp. but the tftp just times out. I don't see any tftp traffic on either the physical host or on the pie server. I am using a bridged interface. I have tried using

Re: vm pxe fail

On Aug 16, 2012, at 3:54 PM, Stefan Hajnoczi wrote: On Thu, Aug 16, 2012 at 1:25 PM, Andrew Holway a.hol...@syseleven.de wrote: I have a kvm vm that I am attempting to boot from pxe. The dhcp works perfectly and I can see the VM in the pxe server arp. but the tftp just times out. I don't