Tuesday, August 21, 2012

A Greener Field: SDNs: Love 'em or Leave 'em?

Are Software Defined Networks (SDN) on your short list yet? Two recent surveys suggest it depends on where you work. I say that given our recent experiences with SDN, within five years and everyone will adopt or have definitive plans to adopt SDN technology. Here’s why:

SDNs, for those who’ve been sleeping with the pinecones of late, move intelligence previously locked within proprietary switching and routing hardware into open software. To put that in “networkese,” we separate the control plane from the forwarding plane using a protocol like OpenFlow. As such, SDN delivers on eight benefits:

  • Agility. OpenFlow-based SDNs create flexibility in how the network is used, operated, and sold. The software that governs it can be written by enterprises and service providers using ordinary software environments.
  • Speed. SDNs promote rapid service introduction through customization, because network operators can implement the features they want in software they control, rather than having to wait for a vendor to put it into plans for their proprietary products.
  • Cost Savings. Software Defined Networking lowers operating expenses and results in fewer errors and less network downtime because it enables automated configuration of the network and reduces manual configuration.
  • Better Management. OpenFlow-based SDN enables virtualization of the network, and therefore the integration of the network with computing and storage. This allows the entire IT operation to be governed more sleekly with a single viewpoint and toolset.
  • Planning. OpenFlow can be easily integrated with computing for resource management and maintenance.
  • Focus. OpenFlow-based SDN can better align the network with business objectives.
  • More Competition. As a standard way of conveying flow-table information to the network devices, it fosters open, multi-vendor markets.
  • Table Conversation. Instead of saying you working in networking at the next party, now you can say “I program the enterprise.” Now, how cool is that?

It’s no wonder in that a recent survey of service providers, Infonetics Research found that 80 percent of survey respondents are including OpenFlow in their purchase considerations. Rapid delivery of new services is essential for service providers and it’s a key benefit to SDN.

"While many uncertainties surround SDNs due to their newness, our survey confirms that the programmable network movement is real, with a good majority of service providers worldwide considering or planning purchases of SDN technologies to simplify network provisioning and to create services and virtual networks in ways not previously possible,” notes Michael Howard, co-founder and principal analyst for carrier networks at Infonetics Research.

On the more “curmudgeonary” side of life you have Mike Fratto noting that enterprises haven’t yet gone gaga over the whole SDN thing. “Enterprises aren't really ready for SDN quite yet, as the results from a recent InformationWeek survey of 250 IT professionals showed. Some 70% of respondents said they weren't even going to start testing SDN for at least a year.”

So which is it for you? Are you a service provider kind of guy or an enterprise kind of gal?

Monday, August 20, 2012

Virtualization of Data Centers: New Options in the Control & Data Planes (Part II)


RAGHU KONDAPALLI
LSI Corp.

This Industry Perspectives article is the second in a series of three that analyzes the network-related issues being caused by the Data Deluge in virtualized data centers, and how these are having an effect on both cloud service providers and the enterprise. The focus of the first article was on the overall effect server virtualization is having on storage virtualization and traffic flows in the datacenter network. This article dives a bit deeper into the network challenges in virtualized data centers as well as the network management complexities and control plane requirements needed to address those challenges.

Server Virtualization Overhead

Server virtualization has enabled tens to hundreds of VMs per server in data centers using multi-core CPU technology. As a result, packet processing functions, such as packet classification, routing decisions, encryption/decryption, etc., have increased exponentially. Because discrete networking systems may not scale cost-effectively to meet these increased processing demands, some changes are also needed in the network.

Networking functions that are implemented in software in network hypervisors are not very efficient, because x86 servers are not optimized for packet processing. The control plane, therefore, needs to be scaled somehow by adding communications processors capable of offloading network control tasks, and both the control and data planes stand to benefit substantially from hardware assistance provided by such function-specific acceleration.

The table below shows the effect on packet processing overhead of virtualizing 1,000 servers. As shown, by mapping each CPU core to four virtual machines (VMs), and assuming 1 percent traffic management overhead with a 25 percent east-west traffic flow, the network management overhead increases by a factor of 32 times in this example of a virtualized data center.

traditional-v-virtualized-data-centersClick to enlarge chart.This table shows the effect on network management overhead of virtualizing 1,000 servers.

Virtual Machine Migration

Support for VM migration among servers, either within one server cluster or across multiple clusters, creates additional management complexity and packet processing overhead. IT administrators may decide to move a VM from one server to another for a variety of reasons, including resource availability, quality-of-experience, maintenance, and hardware/software or network failures. The hypervisor handles these VM migration scenarios by first reserving a VM on the destination server, then moving the VM to its new destination, and finally tearing down the original VM.

Hypervisors are not capable of the timely generation of address resolution protocol (ARP) broadcasts to notify of the VM moves, especially in large-scale virtualized environments. The network can even become so congested from the control overhead occurring during a VM migration that the ARP messages fail to get through in a timely manner. With such a significant impact on network behavior being caused by rapid changes in connections, ARP messages and routing tables, existing control plane solutions need an upgrade to more scalable architectures.

Multi-tenancy and Security

Owing to the high costs associated with building and operating a data center, many IT organizations are moving to a multi-tenant model where different departments or even different companies (in the cloud) share a common infrastructure of virtualized resources. Data protection and security are critical needs in multi-tenant environments, which require logical isolation of resources without dedicating physical resources to any customer.

The control plane must, therefore, provide secure access to data center resources and be able to change the security posture dynamically during VM migrations. The control plane may also need to implement customer-specific policies and Quality of Service (QoS) levels.

Service Level Agreements and Resource Metering

The network-as-a-service paradigm requires active resource metering to ensure SLAs are maintained. Resource metering through the collection of network statistics is useful for calculating return on investment, and evaluating infrastructure expansion and upgrades, as well as for monitoring SLAs.

The network monitoring tasks are currently spread across the hypervisor, legacy management tools, and some newer infrastructure monitoring tools. Collecting and consolidating this management information adds further complexity to the control plane for both the data center operator and multi-tenant enterprises.

The next article in the series will examine two ways of scaling the control plane to accommodate these additional packet processing requirements in virtualized data centers.

http://www.datacenterknowledge.com/archives/2012/08/20/virtualization-of-data...