Question (maybe problems) - network

[Okumba]

Hello,

versioninfo:

# pveversion -v
pve-manager: 2.1-14 (pve-manager/2.1/f32f3f46)
running kernel: 2.6.32-14-pve
proxmox-ve-2.6.32: 2.1-74
pve-kernel-2.6.32-13-pve: 2.6.32-72
pve-kernel-2.6.32-14-pve: 2.6.32-74
lvm2: 2.02.95-1pve2
clvm: 2.02.95-1pve2
corosync-pve: 1.4.3-1
openais-pve: 1.1.4-2
libqb: 0.10.1-2
redhat-cluster-pve: 3.1.92-3
resource-agents-pve: 3.9.2-3
fence-agents-pve: 3.1.8-1
pve-cluster: 1.0-27
qemu-server: 2.0-49
pve-firmware: 1.0-18
libpve-common-perl: 1.0-30
libpve-access-control: 1.0-24
libpve-storage-perl: 2.0-31
vncterm: 1.0-3
vzctl: 3.0.30-2pve5
vzprocps: 2.0.11-2
vzquota: 3.0.12-3
pve-qemu-kvm: 1.1-8
ksm-control-daemon: 1.1-1

question:
We have a debian squeeze 64bit vm running (KVM) where only some teamspeak and steam-servers are running.
The VM uses virtio network / harddisc.
When i update/ one of the steam-servers and it actually downloads something, the teamspeak get lags and ping to the vm has spikes up to 300-1000ms (from 16ms constantly).
It downloads very fast (4092336 bytes (4gb) in 223 seconds), but should it really affect my ping to the vm?
The interesting point here is, that ping to the hostsystem which runs proxmox or other VMs is not affected by this, only the VM that downloads gets that high ping spikes.


Thanks for any help.

 

[dietmar]

Re: Question (maybe problems)

First question, why do i have two "not correctly installed" entries and how can i fix that?

Most likely those packages are missing - simply install them.

 

[Okumba]

Re: Question (maybe problems)

Most likely those packages are missing - simply install them.

Thank you. They were missing indeed, stupid me; must have forgotten the last aptitude install command. postfix, ssh, vzprocps and ksm-control-daemon were missing, lvm2 was already installed.
At the moment there are 2 VMs created/running (KVM), do i need to recreate them or restart them or are they not affected by the packages that were missing?

Any ideas on the second problem?

 

[dietmar]

Re: Question (maybe problems)

At the moment there are 2 VMs created/running (KVM), do i need to recreate them or restart them or are they not affected by the packages that were missing?

Seem the information about the missing packages is lost - you edited the post and removed that information?! So it is hard to answer that question.

 

[Okumba]

Re: Question (maybe problems)

The packages that were missing when i created the KVM VMs are: postfix, ssh, vzprocps and ksm-control-daemon
The ntp/lvm2 package was already installed along with the pve-kernel and proxmox-ve-2.6.32.

 

[dietmar]

Re: Question (maybe problems)

The packages that were missing when i created the KVM VMs are: postfix, ssh, vzprocps and ksm-control-daemon

That should not affect existing VMs.

 

[Okumba]

Re: Question (maybe problems)

Ok, thx for the help.

So lets get back to the other question:

We have a debian squeeze 64bit vm running (KVM) where only some teamspeak and steam servers are running.
The VM uses virtio network / harddisc.
When i update one of the steam-servers and it actually downloads something, the teamspeak-server get lags and ping to the vm has spikes up to 300-1000ms (from 16ms constantly).
The VM downloads very fast (4gb in 223 seconds), but should it really affect my ping to the vm?

The interesting point here is, ping to the hostsystem which runs proxmox or other VMs is not affected by this, only the VM that downloads, gets that high ping spikes.

So as far as i understand this behaviour, i would say the virtio nic gets to its limit?

iperf results vm -> host:

Client connecting to x.x.x.x, TCP port 5001
TCP window size: 16.0 KByte (default)
------------------------------------------------------------
[  3] local x.x.x.x port 34226 connected with x.x.x.x port 5001
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-10.0 sec  16.6 GBytes  14.2 Gbits/sec

iperf results host -> vm:

Client connecting to x.x.x.x, TCP port 5001
TCP window size: 23.8 KByte (default)
------------------------------------------------------------
[  3] local x.x.x.x port 51145 connected with x.x.x.x port 5001
[ ID] Interval       Transfer     Bandwidth
[  3]  0.0-10.0 sec  16.9 GBytes  14.6 Gbits/sec

This seems to be far above the limit of the servers real connection, since the servers in the serverfarm are connected with 100mbit/s. Which makes me think, because if I hit the real network limit of the server, the ping to the host and all VMs should get higher, but thats not the case, only the ping to the VM gets higher.

Thanks.