Effects of virtualization and cloud computing on data center networks

Latency

In many cases, latency may be more of a challenge than oversubscription and raw bandwidth. As

pointed out in the “Changing Business Applications” section, as businesses need to supply immediate,

context-sensitive information to end users (remember that travel website on page 7?), latency and

application responsiveness are driving network designs. Traditional hierarchical and newer

architectures like the fabric extension technology require more network hops and increase latency.

When running even moderate levels of traffic in these systems, latencies increase because of the

multiple hops through the congested and oversubscribed points in the network.

Practical solutions for optimizing E/W traffic flow

This section describes some different architectures and technologies to consider when optimizing your

data center structure for E/W traffic flows. They include:

• Fostering E/W traffic flow at the physical server-network edge

• Distributing management intelligence at the physical server-network edge rather than concentrating

it at higher layers in your network

• Flattening your L2 network by using technologies like HP Intelligent Resilient Framework™ (IRF)

• Making your L2 network more efficient by implementing future multi-path standards

Identify your traffic bottlenecks

It is important to identify where the E/W traffic flows are occurring in your data center: at the

physical switch-server edge between physical servers, or internal to the virtualized server (VM-to-VM).

You can make tradeoffs, depending on two criteria:

• Whether you want to optimize the E/W traffic flow by providing intelligent management at the

physical switch-server edge

• Whether you want to optimize for performance inside a physical server between multiple VMs (with

possible degradation of network management visibility and control)

Virtual switch architectures

Today’s hypervisors implement a virtualized network switch commonly known as a vSwitch. It is also

known as a Virtual Ethernet Bridge (VEB). The vSwitch supports communication between VMs, the

hypervisor, and external network switches. It provides efficient and low latency traffic flow between

local VM-to-VM servers without the need to go to an external network switch (Figure 5).