Length: 22 Pages
10 Server Platform, Components & Software Suppliers Profiled
Click here for the full list of companies covered.
22 pages of analysis of new requirements that are emerging from telcos as they transition to NFV, exploring the technologies that are being deployed to meet telcos' needs for performance, availability and portability
Key insights into the critical differences between cloud and telecom environments, including the potential impact of using common infrastructure for all services within a telco data center
In-depth profiles of 10 critical players in this sector, including both key server vendors and some of their suppliers whose technologies are critical in server platforms
Roz focuses on how innovation and change are impacting the compute, network and storage infrastructure domains, with particular emphasis on virtualization... MORE
To view reports you will need Adobe's Acrobat Reader. If you do not have it, it can be obtained for free at the Adobe web site.
Length: 22 Pages
One of the most significant changes that network functions virtualization (NFV) will introduce into the telco environment is the use of generic IT servers rather than purpose-built, dedicated hardware platforms to run network applications and services. In addition to lowering the cost of the underlying hardware, it is expected that running virtualized network functions (VNFs) on standardized servers will give telcos greater flexibility, improve resource utilization, and potentially converge networks and IT onto a common infrastructure.
However, these servers are generally designed for enterprise applications, not telecom functions. VNFs consume server hardware resources differently than everyday IT applications. Data plane-heavy functions present a particular challenge. Differences in resource requirements for various categories of application must be well understood in order to ensure the needed performance can be achieved.
The European Telecommunications Standards Institute (ETSI) NFV Industry Specification Group (ISG) has published a series of documents that outline its requirements for the infrastructure to support NFV. The excerpt below summarizes these documents, along with the shorthand we will use to refer to them throughout this report.
In its Compute specification, the ETSI NFV ISG states:
The vision and objective of NFV is to implement network functions in portable code which can be executed on generic compute node infrastructure. However, in practical reality, "generic" does not mean completely identical, and even in the cloud computing environment, there are options and differences in the detailed specification of compute nodes. In the context of NFV, these options and differences often affect the packet throughput performance and therefore there is advantage in exploiting optional features if they are available.
The hypervisor-managed approach introduces a performance hit, and several technologies are being proposed to address this. ETSI believes that hypervisors play a key role in creating the execution environment, so it recommends their use rather than bare metal for most applications. Ultimately, ETSI wants services to be cloudified, so that resources can be pooled, shared and dynamically allocated.
In addition, ETSI also presents high-level architectural goals in the areas of portability, reliability, security and manageability, but has stopped short of publishing specifications for the hardware platform. The Open Compute Project (OCP) has developed a reference architecture – but only for servers destined for cloud applications, which differ from telecom applications in important ways. By contrast, the Open Platform for NFV (OPNFV) is focused on telecom, but does not provide any specifications for the underlying hardware platform.
NFV & Telco Data Center Servers: Key Considerations & Technologies looks at the new requirements that are emerging from telcos as they transition to NFV. It highlights the technologies being deployed to meet ETSI's design goals to support telcos' need for performance, availability and portability. The report discusses workload categories to discern how they can impact underlying hardware decisions, and presents different implementation approaches. It also highlights how cloud and telecom environments differ, with discussion of the potential impact of using common infrastructure for all services within a telco data center.
DOWNLOAD TABLE OF CONTENTS
PRINT EXECUTIVE SUMMARY
The report also profiles 10 critical players in this sector, including both key server vendors and some of their suppliers whose technologies are critical in server platforms.
Report Scope & Structure
NFV & Telco Data Center Servers: Key Considerations & Technologies is structured as follows:
Section I is an introduction to the report, including the key findings of our research.
Section II compares IT and telco workloads, highlighting their similarities and differences. It discusses how cloud and telco data center providers approach design.
Section III discusses the different implementation approaches to servers – bare metal, hypervisor-managed and cloudified. It explains why performance is such an important challenge, and explores the innovations being proposed to address this. It also discusses the role servers play in achieving ETSI's design goals, including the potential use of a disaggregated model.
Section IV provides an overview of key server vendors, along with some of their suppliers whose technologies are critical in server platforms.
NFV & Telco Data Center Servers: Key Considerations & Technologies is published in PDF format.