Hi,
We are using a proxmox cluster since 3 years now.
Here are the spec of the two physical servers:
2*16 cores Xeon E5-2640 v2 @ 2Ghz
64 Go of RAM
RAID10 of 4 * SAS 10K disk
4*NIC 1Gbit/s bonded with LACP
And we use a third node that is not hosting any VM for the quorum.
We are running PVE 3.2 (not updated yet)
We were exclusivly using linux KVM since this year.
We started some windows server 2008 R2 on the cluster and we are experiencing performance issue inside the VM.
RDP sessions are very slow (sometimes it freeze) and we see high CPU usage even if nothing is running on the system:
- VMID.conf:
- VM Hardware
- VM options
- CPU Usage
On the task manager we see that svchost.exe is taking 30% of CPU and 1GB of RAM but nothing to explain why RDP sessions are unusable.
On the same physical node Linux KVM are running without any issue.
What we tried:
- Increase CPU unit ==> No change
- Change disk to virtio ==> No change (better disk perf but nothing related to CPU usage)
- Change disk file from QCOW to RAW ==> No change (better disk perf but nothing related to CPU usage)
- Give 2 Socket and 4 core ==> No change
- Change CPU to Host CPU ==> No change
Here is a dd command on the physical node:
Any help would be appreciated.
Regards
We are using a proxmox cluster since 3 years now.
Here are the spec of the two physical servers:
2*16 cores Xeon E5-2640 v2 @ 2Ghz
64 Go of RAM
RAID10 of 4 * SAS 10K disk
4*NIC 1Gbit/s bonded with LACP
And we use a third node that is not hosting any VM for the quorum.
We are running PVE 3.2 (not updated yet)
Code:
[COLOR=#000000][FONT=monospace]proxmox-ve-2.6.32: 3.2-126 (running kernel: 2.6.32-29-pve)pve-manager: 3.2-4 (running version: 3.2-4/e24a91c1)pve-kernel-2.6.32-29-pve: 2.6.32-126lvm2: 2.02.98-pve4clvm: 2.02.98-pve4corosync-pve: 1.4.5-1openais-pve: 1.1.4-3libqb0: 0.11.1-2redhat-cluster-pve: 3.2.0-2resource-agents-pve: 3.9.2-4fence-agents-pve: 4.0.5-1pve-cluster: 3.0-12qemu-server: 3.1-16pve-firmware: 1.1-3libpve-common-perl: 3.0-18libpve-access-control: 3.0-11libpve-storage-perl: 3.0-19pve-libspice-server1: 0.12.4-3vncterm: 1.1-6vzctl: 4.0-1pve5vzprocps: 2.0.11-2vzquota: 3.1-2pve-qemu-kvm: 1.7-8ksm-control-daemon: 1.1-1glusterfs-client: 3.4.2-1[/FONT][/COLOR]We were exclusivly using linux KVM since this year.
We started some windows server 2008 R2 on the cluster and we are experiencing performance issue inside the VM.
RDP sessions are very slow (sometimes it freeze) and we see high CPU usage even if nothing is running on the system:
- VMID.conf:
Code:
bootdisk: ide0
cores: 4
cpuunits: 100000
ide0: local:114/vm-114-disk-1.qcow2,format=qcow2,size=30G
ide1: none,media=cdrom
ide2: none,media=cdrom
memory: 8192
name: ****
net0: e1000=D6:E1:CE:71:B4:75,bridge=vmbr0
ostype: win7
sockets: 1
- VM options
- CPU Usage
On the task manager we see that svchost.exe is taking 30% of CPU and 1GB of RAM but nothing to explain why RDP sessions are unusable.
On the same physical node Linux KVM are running without any issue.
What we tried:
- Increase CPU unit ==> No change
- Change disk to virtio ==> No change (better disk perf but nothing related to CPU usage)
- Change disk file from QCOW to RAW ==> No change (better disk perf but nothing related to CPU usage)
- Give 2 Socket and 4 core ==> No change
- Change CPU to Host CPU ==> No change
Here is a dd command on the physical node:
Code:
dd if=/dev/zero of=/tmp/testfile bs=1G count=1 oflag=direct
1+0 records in
1+0 records out
1073741824 bytes (1.1 GB) copied, 4.51222 s, 238 MB/sAny help would be appreciated.
Regards
