Network bandwidth QoS in Hyper-V August 19, 2012Posted by vbry21 in Windows 2012 Hyper-V.
Tags: Hyper-V, Microsoft, Windows 2012
One of the problems with Virtualisation is potentially ensuring that a VM or process gets the resource that is required.
Networking is one the areas that causes concern, so wouldn’t it be nice if we could prioritise the networking traffic based on its function.
Well in Windows 2012 Hyper-V we can, we can use Quality of Service (QoS) bandwidth management; we can also define minimum and maximum network bandwidth for each Virtual Machine.
Below is a brief description of the technology and its uses
“Windows Server 2012 includes new Quality of Service (QoS) bandwidth management features that enable cloud hosting providers and enterprises to provide services that deliver predictable network performance to virtual machines on a server running Hyper-V. In Windows Server 2012, QoS supports the management of upper-allowed and lower-allowed bandwidth limits, referred to in this document as maximum bandwidth and minimum bandwidth. Windows Server 2012 also takes advantage of data centre bridging (DCB)-capable hardware to converge multiple types of network traffic on a single network adapter with a guaranteed level of service to each type. With Windows PowerShell, you can configure all these new features manually or enable automation in a script to manage a group of servers, regardless of whether they stand alone or are joined to a domain.
For example, cloud hosting providers want to use servers running Hyper-V to host customers and still guarantee a specific level of performance based on service level agreements (SLAs). They want to ensure that no customer is impacted or compromised by other customers on their shared infrastructure, which includes computing, storage, and network resources. Likewise, enterprises have similar requirements. They want to run multiple application servers on a server running Hyper-V and be confident that each application server delivers predictable performance. Lack of performance predictability often drives administrators to put fewer virtual machines on a capable server or simply avoid virtualization, causing them to spend more money on physical equipment and infrastructure.
Furthermore, most cloud hosting providers and enterprises today use a dedicated network adapter and a dedicated subnet for a specific type of workload such as storage or live migration to achieve network performance isolation on a server running Hyper-V. Although this deployment strategy works for those using 1-gigabit Ethernet network adapters, it becomes impractical for those who are using or plan to use 10-gigabit Ethernet network adapters. Not only does one 10-gigabit Ethernet network adapter (or two for high availability) already provide sufficient bandwidth for all the workloads on a server running Hyper-V in most deployments, but 10-gigabit Ethernet network adapters and switches are considerably more expensive than their 1-gigabit Ethernet counterparts. To best utilize 10-gigabit Ethernet hardware, a server running Hyper-V requires new capabilities to manage bandwidth.”