Veeam Causes lockups of VMs and real time applications

[seanv]

We have a Hyper-V Cluster through SCVMM 2012 SP1
All hosts are Server 2012 - All are HP DL360p Gen8, 2x E5-2650 (32 Logical Cores), 256GB of memory - All are connected to 3x4GB Luns on an EMC vnx5300
Our backup host is a DL180 G6, 1x Xeon E5620 with 24GB of Memory, running server 2008 R2 SP1 and Veeam 6.5.0.144 (64Bit).

During our Backup schedule using Veeam we get (what appears to be intermittent) failures of applications, including our web servers, telephony control services and even delayed mail.

I have run some monitoring of the performance collection stats and I can see that the CPU spikes drastically during this period vs normal operation.

Our CPU contention ratio is about 1:0.73 (1 logical core per 0.73 vCPU assigned). 96 Logical cores with 132 vCPU assigned.

Network throttling still doesn't alleviate the issue (at all).

Your help is appreciated.

[Gostev]

This is most likely due to Microsoft VSS quiescing operating system and applications, which includes pausing their activities for a brief moment. Basically, you need to chose between crash-consistent backups with no impact on applications, or application-consistent backup with some impact (this impact is the reason why most people try to schedule their backups for off-hours). Microsoft only supports backups created with VSS processing enabled though. Thanks!

[seanv]

We don't have any 100% off hours. 'Off hours' are when I can deal with server support issues and are impossible to do due to the performance issues - And when we used VMware there were no issues with performance on slower performing lower spec machines...

[veremin]

Hi, Sean.

When you used VMware and didn’t have any issues related to backup, etc. was the Application Aware Image Processing option enabled or not?

Thanks.

[seanv]

We did not have Application Aware Image Processing option enabled and also do not have it enabled on our Hyper-V cluster backups either.

I understand that this may not give us consistent backups of some of our data. As I didn't set up the original (Vmware) system, I am unsure why it was turned off.

[foggy]

Then I suggest contacting Veeam technical support for assistance, as most likely logs review is required to reveal the reason of these lockups.