WP_Term Object
(
    [term_id] => 13
    [name] => Arm
    [slug] => arm
    [term_group] => 0
    [term_taxonomy_id] => 13
    [taxonomy] => category
    [description] => 
    [parent] => 178
    [count] => 392
    [filter] => raw
    [cat_ID] => 13
    [category_count] => 392
    [category_description] => 
    [cat_name] => Arm
    [category_nicename] => arm
    [category_parent] => 178
)
            
Mobile Unleashed Banner SemiWiki
WP_Term Object
(
    [term_id] => 13
    [name] => Arm
    [slug] => arm
    [term_group] => 0
    [term_taxonomy_id] => 13
    [taxonomy] => category
    [description] => 
    [parent] => 178
    [count] => 392
    [filter] => raw
    [cat_ID] => 13
    [category_count] => 392
    [category_description] => 
    [cat_name] => Arm
    [category_nicename] => arm
    [category_parent] => 178
)

Webinar alert – ARM and Enea explore NFV

Webinar alert – ARM and Enea explore NFV
by Don Dingee on 06-22-2016 at 4:00 pm

In the Open Source IP panel at 53DAC, we explored the idea of workload-optimized servers. One panelist observation stuck with me: if one chooses to deviate from the Intel-based norm in a data center, you essentially have to spray paint a line around any boxes that don’t comply. In other words, not just any application can go on a workload-optimized server.

Kind of a “duh” observation? Not really; our panelists were very experienced technologists on the front lines of open data center projects. The reason Intel has so much power in the data center is the ecosystem and the ease of application development and portability.

However, not every server is an application server. In many cases other CPU architectures do a better job than the X86 camp, and there is still a compelling need for workload-optimization. In the days of the carrier-telecom boom with Power Architecture, we learned very quickly to segment the targets – there were media servers, storage appliances, network service platforms, and other gear where the playing field was more level. Most of those “other” server platforms deployed a carrier-grade operating system, with embedded code targeting the specifics of the networking stack and associated features.


The virtualization boom took hold as a way to scale application server platforms cost-effectively, keeping hardware utilization high by allowing multiple software instances on a single box. Networking types added a slightly different twist with network functions virtualization (NFV), providing building blocks of virtualized network functions (VNFs) with orchestration to create a flexible yet powerful infrastructure.

The hardware platform for NFV infrastructure is up for grabs. When we talk about “ARM servers”, we’re really talking about NFV platforms as one of the first targets. ARM is teaming with long-time carrier-grade operating system vendor Enea for an upcoming Light Reading webinar describing how a scale-out NFV architecture using ARM-based SoCs would work. I first wrote about this for SemiWiki a bit more than a year ago, back when people were predicting an ARM server “stampede”. It will be interesting to see how the story is evolving now.

Registration for next week’s live event is here (pithy title aside, I’m sitting in to learn more):

Better Living Through the ARM NFV Ecosystem

If you’re trying to come to grips with what an “ARM server” is – and isn’t – this should be worth time to catch. According to IHS, we’re in the early phase of a 10- to 15-year transformation, and the outcome depends on who gets a viable NFV software ecosystem put together. ARM looks poised to be one of those players.

Share this post via:

Comments

There are no comments yet.

You must register or log in to view/post comments.